cmenguy / toshiro-ai-1_5
A stable diffusion model trained on pictures from my buddy Toshiro (truly the best boy there is)
- Public
- 111 runs
-
T4
Prediction
cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8IDmeaay5bbwxf2udfaebwqc6v4buStatusSucceededSourceWebHardwareT4Total durationCreatedInput
- width
- 512
- height
- 512
- prompt
- a photo of a qdg dog puppy posing in front of the Eiffel Tower in Van Gogh style
- scheduler
- DDIM
- num_outputs
- 1
- guidance_scale
- 7.5
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 512, "height": 512, "prompt": "a photo of a qdg dog puppy posing in front of the Eiffel Tower in Van Gogh style", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "prompt_strength": 0.8, "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", { input: { width: 512, height: 512, prompt: "a photo of a qdg dog puppy posing in front of the Eiffel Tower in Van Gogh style", scheduler: "DDIM", num_outputs: 1, guidance_scale: 7.5, prompt_strength: 0.8, num_inference_steps: 50 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", input={ "width": 512, "height": 512, "prompt": "a photo of a qdg dog puppy posing in front of the Eiffel Tower in Van Gogh style", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "prompt_strength": 0.8, "num_inference_steps": 50 } ) # To access the file URL: print(output[0].url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output[0].read())To learn more, take a look at the guide on getting started with Python.
Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", "input": { "width": 512, "height": 512, "prompt": "a photo of a qdg dog puppy posing in front of the Eiffel Tower in Van Gogh style", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8 \ -i 'width=512' \ -i 'height=512' \ -i 'prompt="a photo of a qdg dog puppy posing in front of the Eiffel Tower in Van Gogh style"' \ -i 'scheduler="DDIM"' \ -i 'num_outputs=1' \ -i 'guidance_scale=7.5' \ -i 'prompt_strength=0.8' \ -i 'num_inference_steps=50'To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 512, "height": 512, "prompt": "a photo of a qdg dog puppy posing in front of the Eiffel Tower in Van Gogh style", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-06-18T19:16:40.851198Z", "created_at": "2023-06-18T19:13:19.230631Z", "data_removed": false, "error": null, "id": "meaay5bbwxf2udfaebwqc6v4bu", "input": { "width": 512, "height": 512, "prompt": "a photo of a qdg dog puppy posing in front of the Eiffel Tower in Van Gogh style", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 1191\nusing txt2img\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:01<01:33, 1.91s/it]\n 4%|▍ | 2/50 [00:02<00:42, 1.12it/s]\n 6%|▌ | 3/50 [00:02<00:26, 1.77it/s]\n 8%|▊ | 4/50 [00:02<00:18, 2.42it/s]\n 10%|█ | 5/50 [00:02<00:14, 3.05it/s]\n 12%|█▏ | 6/50 [00:02<00:12, 3.61it/s]\n 14%|█▍ | 7/50 [00:02<00:10, 4.05it/s]\n 16%|█▌ | 8/50 [00:03<00:09, 4.44it/s]\n 18%|█▊ | 9/50 [00:03<00:08, 4.76it/s]\n 20%|██ | 10/50 [00:03<00:08, 4.99it/s]\n 22%|██▏ | 11/50 [00:03<00:07, 5.16it/s]\n 24%|██▍ | 12/50 [00:03<00:07, 5.28it/s]\n 26%|██▌ | 13/50 [00:04<00:06, 5.36it/s]\n 28%|██▊ | 14/50 [00:04<00:06, 5.45it/s]\n 30%|███ | 15/50 [00:04<00:06, 5.49it/s]\n 32%|███▏ | 16/50 [00:04<00:06, 5.52it/s]\n 34%|███▍ | 17/50 [00:04<00:05, 5.53it/s]\n 36%|███▌ | 18/50 [00:04<00:05, 5.53it/s]\n 38%|███▊ | 19/50 [00:05<00:05, 5.54it/s]\n 40%|████ | 20/50 [00:05<00:05, 5.58it/s]\n 42%|████▏ | 21/50 [00:05<00:05, 5.60it/s]\n 44%|████▍ | 22/50 [00:05<00:05, 5.60it/s]\n 46%|████▌ | 23/50 [00:05<00:04, 5.58it/s]\n 48%|████▊ | 24/50 [00:06<00:04, 5.55it/s]\n 50%|█████ | 25/50 [00:06<00:04, 5.54it/s]\n 52%|█████▏ | 26/50 [00:06<00:04, 5.55it/s]\n 54%|█████▍ | 27/50 [00:06<00:04, 5.55it/s]\n 56%|█████▌ | 28/50 [00:06<00:03, 5.59it/s]\n 58%|█████▊ | 29/50 [00:06<00:03, 5.60it/s]\n 60%|██████ | 30/50 [00:07<00:03, 5.58it/s]\n 62%|██████▏ | 31/50 [00:07<00:03, 5.57it/s]\n 64%|██████▍ | 32/50 [00:07<00:03, 5.56it/s]\n 66%|██████▌ | 33/50 [00:07<00:03, 5.55it/s]\n 68%|██████▊ | 34/50 [00:07<00:02, 5.55it/s]\n 70%|███████ | 35/50 [00:08<00:02, 5.55it/s]\n 72%|███████▏ | 36/50 [00:08<00:02, 5.57it/s]\n 74%|███████▍ | 37/50 [00:08<00:02, 5.60it/s]\n 76%|███████▌ | 38/50 [00:08<00:02, 5.60it/s]\n 78%|███████▊ | 39/50 [00:08<00:01, 5.59it/s]\n 80%|████████ | 40/50 [00:08<00:01, 5.57it/s]\n 82%|████████▏ | 41/50 [00:09<00:01, 5.54it/s]\n 84%|████████▍ | 42/50 [00:09<00:01, 5.53it/s]\n 86%|████████▌ | 43/50 [00:09<00:01, 5.53it/s]\n 88%|████████▊ | 44/50 [00:09<00:01, 5.53it/s]\n 90%|█████████ | 45/50 [00:09<00:00, 5.53it/s]\n 92%|█████████▏| 46/50 [00:09<00:00, 5.53it/s]\n 94%|█████████▍| 47/50 [00:10<00:00, 5.53it/s]\n 96%|█████████▌| 48/50 [00:10<00:00, 5.56it/s]\n 98%|█████████▊| 49/50 [00:10<00:00, 5.58it/s]\n100%|██████████| 50/50 [00:10<00:00, 5.59it/s]\n100%|██████████| 50/50 [00:10<00:00, 4.67it/s]", "metrics": { "predict_time": 11.866184, "total_time": 201.620567 }, "output": [ "https://replicate.delivery/pbxt/2IBNF3bMkMLxJle9v8ba8KffiudSWBWJ88ZI1iKmSe0ihCdEB/out-0.png" ], "started_at": "2023-06-18T19:16:28.985014Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/meaay5bbwxf2udfaebwqc6v4bu", "cancel": "https://api.replicate.com/v1/predictions/meaay5bbwxf2udfaebwqc6v4bu/cancel" }, "version": "e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8" }Generated inUsing seed: 1191 using txt2img 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:01<01:33, 1.91s/it] 4%|▍ | 2/50 [00:02<00:42, 1.12it/s] 6%|▌ | 3/50 [00:02<00:26, 1.77it/s] 8%|▊ | 4/50 [00:02<00:18, 2.42it/s] 10%|█ | 5/50 [00:02<00:14, 3.05it/s] 12%|█▏ | 6/50 [00:02<00:12, 3.61it/s] 14%|█▍ | 7/50 [00:02<00:10, 4.05it/s] 16%|█▌ | 8/50 [00:03<00:09, 4.44it/s] 18%|█▊ | 9/50 [00:03<00:08, 4.76it/s] 20%|██ | 10/50 [00:03<00:08, 4.99it/s] 22%|██▏ | 11/50 [00:03<00:07, 5.16it/s] 24%|██▍ | 12/50 [00:03<00:07, 5.28it/s] 26%|██▌ | 13/50 [00:04<00:06, 5.36it/s] 28%|██▊ | 14/50 [00:04<00:06, 5.45it/s] 30%|███ | 15/50 [00:04<00:06, 5.49it/s] 32%|███▏ | 16/50 [00:04<00:06, 5.52it/s] 34%|███▍ | 17/50 [00:04<00:05, 5.53it/s] 36%|███▌ | 18/50 [00:04<00:05, 5.53it/s] 38%|███▊ | 19/50 [00:05<00:05, 5.54it/s] 40%|████ | 20/50 [00:05<00:05, 5.58it/s] 42%|████▏ | 21/50 [00:05<00:05, 5.60it/s] 44%|████▍ | 22/50 [00:05<00:05, 5.60it/s] 46%|████▌ | 23/50 [00:05<00:04, 5.58it/s] 48%|████▊ | 24/50 [00:06<00:04, 5.55it/s] 50%|█████ | 25/50 [00:06<00:04, 5.54it/s] 52%|█████▏ | 26/50 [00:06<00:04, 5.55it/s] 54%|█████▍ | 27/50 [00:06<00:04, 5.55it/s] 56%|█████▌ | 28/50 [00:06<00:03, 5.59it/s] 58%|█████▊ | 29/50 [00:06<00:03, 5.60it/s] 60%|██████ | 30/50 [00:07<00:03, 5.58it/s] 62%|██████▏ | 31/50 [00:07<00:03, 5.57it/s] 64%|██████▍ | 32/50 [00:07<00:03, 5.56it/s] 66%|██████▌ | 33/50 [00:07<00:03, 5.55it/s] 68%|██████▊ | 34/50 [00:07<00:02, 5.55it/s] 70%|███████ | 35/50 [00:08<00:02, 5.55it/s] 72%|███████▏ | 36/50 [00:08<00:02, 5.57it/s] 74%|███████▍ | 37/50 [00:08<00:02, 5.60it/s] 76%|███████▌ | 38/50 [00:08<00:02, 5.60it/s] 78%|███████▊ | 39/50 [00:08<00:01, 5.59it/s] 80%|████████ | 40/50 [00:08<00:01, 5.57it/s] 82%|████████▏ | 41/50 [00:09<00:01, 5.54it/s] 84%|████████▍ | 42/50 [00:09<00:01, 5.53it/s] 86%|████████▌ | 43/50 [00:09<00:01, 5.53it/s] 88%|████████▊ | 44/50 [00:09<00:01, 5.53it/s] 90%|█████████ | 45/50 [00:09<00:00, 5.53it/s] 92%|█████████▏| 46/50 [00:09<00:00, 5.53it/s] 94%|█████████▍| 47/50 [00:10<00:00, 5.53it/s] 96%|█████████▌| 48/50 [00:10<00:00, 5.56it/s] 98%|█████████▊| 49/50 [00:10<00:00, 5.58it/s] 100%|██████████| 50/50 [00:10<00:00, 5.59it/s] 100%|██████████| 50/50 [00:10<00:00, 4.67it/s]Prediction
cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8IDvdzyawjbhtoeskkli26rqi4ol4StatusSucceededSourceWebHardwareT4Total durationCreatedInput
- width
- 512
- height
- 512
- prompt
- Adorably cute qdg dog portrait, artstation winner by Victo Ngai, Kilian Eng and by Jake Parker, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution
- scheduler
- DDIM
- num_outputs
- 1
- guidance_scale
- 7.5
- negative_prompt
- cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 512, "height": 512, "prompt": "Adorably cute qdg dog portrait, artstation winner by Victo Ngai, Kilian Eng and by Jake Parker, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", { input: { width: 512, height: 512, prompt: "Adorably cute qdg dog portrait, artstation winner by Victo Ngai, Kilian Eng and by Jake Parker, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution", scheduler: "DDIM", num_outputs: 1, guidance_scale: 7.5, negative_prompt: "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", prompt_strength: 0.8, num_inference_steps: 50 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", input={ "width": 512, "height": 512, "prompt": "Adorably cute qdg dog portrait, artstation winner by Victo Ngai, Kilian Eng and by Jake Parker, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } ) # To access the file URL: print(output[0].url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output[0].read())To learn more, take a look at the guide on getting started with Python.
Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", "input": { "width": 512, "height": 512, "prompt": "Adorably cute qdg dog portrait, artstation winner by Victo Ngai, Kilian Eng and by Jake Parker, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8 \ -i 'width=512' \ -i 'height=512' \ -i 'prompt="Adorably cute qdg dog portrait, artstation winner by Victo Ngai, Kilian Eng and by Jake Parker, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution"' \ -i 'scheduler="DDIM"' \ -i 'num_outputs=1' \ -i 'guidance_scale=7.5' \ -i 'negative_prompt="cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark"' \ -i 'prompt_strength=0.8' \ -i 'num_inference_steps=50'To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 512, "height": 512, "prompt": "Adorably cute qdg dog portrait, artstation winner by Victo Ngai, Kilian Eng and by Jake Parker, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-06-18T20:09:18.614783Z", "created_at": "2023-06-18T20:05:48.534744Z", "data_removed": false, "error": null, "id": "vdzyawjbhtoeskkli26rqi4ol4", "input": { "width": 512, "height": 512, "prompt": "Adorably cute qdg dog portrait, artstation winner by Victo Ngai, Kilian Eng and by Jake Parker, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 62756\nusing txt2img\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:03<02:40, 3.28s/it]\n 4%|▍ | 2/50 [00:03<01:09, 1.45s/it]\n 6%|▌ | 3/50 [00:03<00:40, 1.15it/s]\n 8%|▊ | 4/50 [00:03<00:27, 1.67it/s]\n 10%|█ | 5/50 [00:03<00:20, 2.24it/s]\n 12%|█▏ | 6/50 [00:04<00:15, 2.81it/s]\n 14%|█▍ | 7/50 [00:04<00:12, 3.34it/s]\n 16%|█▌ | 8/50 [00:04<00:10, 3.84it/s]\n 18%|█▊ | 9/50 [00:04<00:09, 4.26it/s]\n 20%|██ | 10/50 [00:04<00:08, 4.59it/s]\n 22%|██▏ | 11/50 [00:05<00:08, 4.87it/s]\n 24%|██▍ | 12/50 [00:05<00:07, 5.08it/s]\n 26%|██▌ | 13/50 [00:05<00:07, 5.22it/s]\n 28%|██▊ | 14/50 [00:05<00:06, 5.35it/s]\n 30%|███ | 15/50 [00:05<00:06, 5.41it/s]\n 32%|███▏ | 16/50 [00:05<00:06, 5.46it/s]\n 34%|███▍ | 17/50 [00:06<00:05, 5.50it/s]\n 36%|███▌ | 18/50 [00:06<00:05, 5.53it/s]\n 38%|███▊ | 19/50 [00:06<00:05, 5.57it/s]\n 40%|████ | 20/50 [00:06<00:05, 5.59it/s]\n 42%|████▏ | 21/50 [00:06<00:05, 5.58it/s]\n 44%|████▍ | 22/50 [00:07<00:05, 5.57it/s]\n 46%|████▌ | 23/50 [00:07<00:04, 5.55it/s]\n 48%|████▊ | 24/50 [00:07<00:04, 5.54it/s]\n 50%|█████ | 25/50 [00:07<00:04, 5.55it/s]\n 52%|█████▏ | 26/50 [00:07<00:04, 5.59it/s]\n 54%|█████▍ | 27/50 [00:07<00:04, 5.59it/s]\n 56%|█████▌ | 28/50 [00:08<00:03, 5.58it/s]\n 58%|█████▊ | 29/50 [00:08<00:03, 5.56it/s]\n 60%|██████ | 30/50 [00:08<00:03, 5.54it/s]\n 62%|██████▏ | 31/50 [00:08<00:03, 5.53it/s]\n 64%|██████▍ | 32/50 [00:08<00:03, 5.53it/s]\n 66%|██████▌ | 33/50 [00:09<00:03, 5.54it/s]\n 68%|██████▊ | 34/50 [00:09<00:02, 5.54it/s]\n 70%|███████ | 35/50 [00:09<00:02, 5.53it/s]\n 72%|███████▏ | 36/50 [00:09<00:02, 5.53it/s]\n 74%|███████▍ | 37/50 [00:09<00:02, 5.56it/s]\n 76%|███████▌ | 38/50 [00:09<00:02, 5.59it/s]\n 78%|███████▊ | 39/50 [00:10<00:01, 5.57it/s]\n 80%|████████ | 40/50 [00:10<00:01, 5.58it/s]\n 82%|████████▏ | 41/50 [00:10<00:01, 5.57it/s]\n 84%|████████▍ | 42/50 [00:10<00:01, 5.55it/s]\n 86%|████████▌ | 43/50 [00:10<00:01, 5.54it/s]\n 88%|████████▊ | 44/50 [00:10<00:01, 5.55it/s]\n 90%|█████████ | 45/50 [00:11<00:00, 5.57it/s]\n 92%|█████████▏| 46/50 [00:11<00:00, 5.59it/s]\n 94%|█████████▍| 47/50 [00:11<00:00, 5.60it/s]\n 96%|█████████▌| 48/50 [00:11<00:00, 5.57it/s]\n 98%|█████████▊| 49/50 [00:11<00:00, 5.56it/s]\n100%|██████████| 50/50 [00:12<00:00, 5.57it/s]\n100%|██████████| 50/50 [00:12<00:00, 4.14it/s]", "metrics": { "predict_time": 15.297736, "total_time": 210.080039 }, "output": [ "https://replicate.delivery/pbxt/LdVnInAek00es0EQlKtS9dGVs4IHyCnROIKSUEf4gVJbziOiA/out-0.png" ], "started_at": "2023-06-18T20:09:03.317047Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/vdzyawjbhtoeskkli26rqi4ol4", "cancel": "https://api.replicate.com/v1/predictions/vdzyawjbhtoeskkli26rqi4ol4/cancel" }, "version": "e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8" }Generated inUsing seed: 62756 using txt2img 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:03<02:40, 3.28s/it] 4%|▍ | 2/50 [00:03<01:09, 1.45s/it] 6%|▌ | 3/50 [00:03<00:40, 1.15it/s] 8%|▊ | 4/50 [00:03<00:27, 1.67it/s] 10%|█ | 5/50 [00:03<00:20, 2.24it/s] 12%|█▏ | 6/50 [00:04<00:15, 2.81it/s] 14%|█▍ | 7/50 [00:04<00:12, 3.34it/s] 16%|█▌ | 8/50 [00:04<00:10, 3.84it/s] 18%|█▊ | 9/50 [00:04<00:09, 4.26it/s] 20%|██ | 10/50 [00:04<00:08, 4.59it/s] 22%|██▏ | 11/50 [00:05<00:08, 4.87it/s] 24%|██▍ | 12/50 [00:05<00:07, 5.08it/s] 26%|██▌ | 13/50 [00:05<00:07, 5.22it/s] 28%|██▊ | 14/50 [00:05<00:06, 5.35it/s] 30%|███ | 15/50 [00:05<00:06, 5.41it/s] 32%|███▏ | 16/50 [00:05<00:06, 5.46it/s] 34%|███▍ | 17/50 [00:06<00:05, 5.50it/s] 36%|███▌ | 18/50 [00:06<00:05, 5.53it/s] 38%|███▊ | 19/50 [00:06<00:05, 5.57it/s] 40%|████ | 20/50 [00:06<00:05, 5.59it/s] 42%|████▏ | 21/50 [00:06<00:05, 5.58it/s] 44%|████▍ | 22/50 [00:07<00:05, 5.57it/s] 46%|████▌ | 23/50 [00:07<00:04, 5.55it/s] 48%|████▊ | 24/50 [00:07<00:04, 5.54it/s] 50%|█████ | 25/50 [00:07<00:04, 5.55it/s] 52%|█████▏ | 26/50 [00:07<00:04, 5.59it/s] 54%|█████▍ | 27/50 [00:07<00:04, 5.59it/s] 56%|█████▌ | 28/50 [00:08<00:03, 5.58it/s] 58%|█████▊ | 29/50 [00:08<00:03, 5.56it/s] 60%|██████ | 30/50 [00:08<00:03, 5.54it/s] 62%|██████▏ | 31/50 [00:08<00:03, 5.53it/s] 64%|██████▍ | 32/50 [00:08<00:03, 5.53it/s] 66%|██████▌ | 33/50 [00:09<00:03, 5.54it/s] 68%|██████▊ | 34/50 [00:09<00:02, 5.54it/s] 70%|███████ | 35/50 [00:09<00:02, 5.53it/s] 72%|███████▏ | 36/50 [00:09<00:02, 5.53it/s] 74%|███████▍ | 37/50 [00:09<00:02, 5.56it/s] 76%|███████▌ | 38/50 [00:09<00:02, 5.59it/s] 78%|███████▊ | 39/50 [00:10<00:01, 5.57it/s] 80%|████████ | 40/50 [00:10<00:01, 5.58it/s] 82%|████████▏ | 41/50 [00:10<00:01, 5.57it/s] 84%|████████▍ | 42/50 [00:10<00:01, 5.55it/s] 86%|████████▌ | 43/50 [00:10<00:01, 5.54it/s] 88%|████████▊ | 44/50 [00:10<00:01, 5.55it/s] 90%|█████████ | 45/50 [00:11<00:00, 5.57it/s] 92%|█████████▏| 46/50 [00:11<00:00, 5.59it/s] 94%|█████████▍| 47/50 [00:11<00:00, 5.60it/s] 96%|█████████▌| 48/50 [00:11<00:00, 5.57it/s] 98%|█████████▊| 49/50 [00:11<00:00, 5.56it/s] 100%|██████████| 50/50 [00:12<00:00, 5.57it/s] 100%|██████████| 50/50 [00:12<00:00, 4.14it/s]Prediction
cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8IDinpzeybb25drt5momqq44fnk5uStatusSucceededSourceWebHardwareT4Total durationCreatedInput
- width
- 512
- height
- 512
- prompt
- a high quality painting of a very cute qdg dog puppy, friendly, curious expression. painting by artgerm and greg rutkowski and alphonse mucha
- scheduler
- DDIM
- num_outputs
- 1
- guidance_scale
- 7.5
- negative_prompt
- cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 512, "height": 512, "prompt": "a high quality painting of a very cute qdg dog puppy, friendly, curious expression. painting by artgerm and greg rutkowski and alphonse mucha", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", { input: { width: 512, height: 512, prompt: "a high quality painting of a very cute qdg dog puppy, friendly, curious expression. painting by artgerm and greg rutkowski and alphonse mucha", scheduler: "DDIM", num_outputs: 1, guidance_scale: 7.5, negative_prompt: "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", prompt_strength: 0.8, num_inference_steps: 50 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", input={ "width": 512, "height": 512, "prompt": "a high quality painting of a very cute qdg dog puppy, friendly, curious expression. painting by artgerm and greg rutkowski and alphonse mucha", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } ) # To access the file URL: print(output[0].url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output[0].read())To learn more, take a look at the guide on getting started with Python.
Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", "input": { "width": 512, "height": 512, "prompt": "a high quality painting of a very cute qdg dog puppy, friendly, curious expression. painting by artgerm and greg rutkowski and alphonse mucha", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8 \ -i 'width=512' \ -i 'height=512' \ -i 'prompt="a high quality painting of a very cute qdg dog puppy, friendly, curious expression. painting by artgerm and greg rutkowski and alphonse mucha"' \ -i 'scheduler="DDIM"' \ -i 'num_outputs=1' \ -i 'guidance_scale=7.5' \ -i 'negative_prompt="cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark"' \ -i 'prompt_strength=0.8' \ -i 'num_inference_steps=50'To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 512, "height": 512, "prompt": "a high quality painting of a very cute qdg dog puppy, friendly, curious expression. painting by artgerm and greg rutkowski and alphonse mucha", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-06-18T20:30:32.016055Z", "created_at": "2023-06-18T20:30:20.887468Z", "data_removed": false, "error": null, "id": "inpzeybb25drt5momqq44fnk5u", "input": { "width": 512, "height": 512, "prompt": "a high quality painting of a very cute qdg dog puppy, friendly, curious expression. painting by artgerm and greg rutkowski and alphonse mucha", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 307\nusing txt2img\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:11, 4.09it/s]\n 4%|▍ | 2/50 [00:00<00:10, 4.58it/s]\n 6%|▌ | 3/50 [00:00<00:09, 4.84it/s]\n 8%|▊ | 4/50 [00:00<00:09, 5.02it/s]\n 10%|█ | 5/50 [00:01<00:08, 5.06it/s]\n 12%|█▏ | 6/50 [00:01<00:08, 5.01it/s]\n 14%|█▍ | 7/50 [00:01<00:08, 5.04it/s]\n 16%|█▌ | 8/50 [00:01<00:08, 5.10it/s]\n 18%|█▊ | 9/50 [00:01<00:07, 5.14it/s]\n 20%|██ | 10/50 [00:01<00:07, 5.17it/s]\n 22%|██▏ | 11/50 [00:02<00:07, 5.12it/s]\n 24%|██▍ | 12/50 [00:02<00:07, 5.08it/s]\n 26%|██▌ | 13/50 [00:02<00:07, 5.10it/s]\n 28%|██▊ | 14/50 [00:02<00:07, 5.10it/s]\n 30%|███ | 15/50 [00:02<00:06, 5.11it/s]\n 32%|███▏ | 16/50 [00:03<00:06, 5.07it/s]\n 34%|███▍ | 17/50 [00:03<00:06, 5.05it/s]\n 36%|███▌ | 18/50 [00:03<00:06, 5.05it/s]\n 38%|███▊ | 19/50 [00:03<00:06, 5.03it/s]\n 40%|████ | 20/50 [00:03<00:05, 5.04it/s]\n 42%|████▏ | 21/50 [00:04<00:05, 5.04it/s]\n 44%|████▍ | 22/50 [00:04<00:05, 5.02it/s]\n 46%|████▌ | 23/50 [00:04<00:05, 5.05it/s]\n 48%|████▊ | 24/50 [00:04<00:05, 5.05it/s]\n 50%|█████ | 25/50 [00:04<00:04, 5.06it/s]\n 52%|█████▏ | 26/50 [00:05<00:04, 5.07it/s]\n 54%|█████▍ | 27/50 [00:05<00:04, 5.02it/s]\n 56%|█████▌ | 28/50 [00:05<00:04, 5.02it/s]\n 58%|█████▊ | 29/50 [00:05<00:04, 4.96it/s]\n 60%|██████ | 30/50 [00:05<00:04, 4.96it/s]\n 62%|██████▏ | 31/50 [00:06<00:03, 4.98it/s]\n 64%|██████▍ | 32/50 [00:06<00:03, 4.96it/s]\n 66%|██████▌ | 33/50 [00:06<00:03, 4.98it/s]\n 68%|██████▊ | 34/50 [00:06<00:03, 4.93it/s]\n 70%|███████ | 35/50 [00:06<00:03, 4.94it/s]\n 72%|███████▏ | 36/50 [00:07<00:02, 4.94it/s]\n 74%|███████▍ | 37/50 [00:07<00:02, 4.96it/s]\n 76%|███████▌ | 38/50 [00:07<00:02, 4.99it/s]\n 78%|███████▊ | 39/50 [00:07<00:02, 4.98it/s]\n 80%|████████ | 40/50 [00:07<00:01, 5.01it/s]\n 82%|████████▏ | 41/50 [00:08<00:01, 5.01it/s]\n 84%|████████▍ | 42/50 [00:08<00:01, 5.05it/s]\n 86%|████████▌ | 43/50 [00:08<00:01, 5.03it/s]\n 88%|████████▊ | 44/50 [00:08<00:01, 4.94it/s]\n 90%|█████████ | 45/50 [00:08<00:01, 4.94it/s]\n 92%|█████████▏| 46/50 [00:09<00:00, 4.93it/s]\n 94%|█████████▍| 47/50 [00:09<00:00, 4.95it/s]\n 96%|█████████▌| 48/50 [00:09<00:00, 4.95it/s]\n 98%|█████████▊| 49/50 [00:09<00:00, 4.93it/s]\n100%|██████████| 50/50 [00:10<00:00, 4.94it/s]\n100%|██████████| 50/50 [00:10<00:00, 5.00it/s]", "metrics": { "predict_time": 11.156779, "total_time": 11.128587 }, "output": [ "https://replicate.delivery/pbxt/W8GV2Dg9ISp8O5KK9F0n46rGD4Yra4GXepy0rmhwWfBntRHRA/out-0.png" ], "started_at": "2023-06-18T20:30:20.859276Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/inpzeybb25drt5momqq44fnk5u", "cancel": "https://api.replicate.com/v1/predictions/inpzeybb25drt5momqq44fnk5u/cancel" }, "version": "e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8" }Generated inUsing seed: 307 using txt2img 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:11, 4.09it/s] 4%|▍ | 2/50 [00:00<00:10, 4.58it/s] 6%|▌ | 3/50 [00:00<00:09, 4.84it/s] 8%|▊ | 4/50 [00:00<00:09, 5.02it/s] 10%|█ | 5/50 [00:01<00:08, 5.06it/s] 12%|█▏ | 6/50 [00:01<00:08, 5.01it/s] 14%|█▍ | 7/50 [00:01<00:08, 5.04it/s] 16%|█▌ | 8/50 [00:01<00:08, 5.10it/s] 18%|█▊ | 9/50 [00:01<00:07, 5.14it/s] 20%|██ | 10/50 [00:01<00:07, 5.17it/s] 22%|██▏ | 11/50 [00:02<00:07, 5.12it/s] 24%|██▍ | 12/50 [00:02<00:07, 5.08it/s] 26%|██▌ | 13/50 [00:02<00:07, 5.10it/s] 28%|██▊ | 14/50 [00:02<00:07, 5.10it/s] 30%|███ | 15/50 [00:02<00:06, 5.11it/s] 32%|███▏ | 16/50 [00:03<00:06, 5.07it/s] 34%|███▍ | 17/50 [00:03<00:06, 5.05it/s] 36%|███▌ | 18/50 [00:03<00:06, 5.05it/s] 38%|███▊ | 19/50 [00:03<00:06, 5.03it/s] 40%|████ | 20/50 [00:03<00:05, 5.04it/s] 42%|████▏ | 21/50 [00:04<00:05, 5.04it/s] 44%|████▍ | 22/50 [00:04<00:05, 5.02it/s] 46%|████▌ | 23/50 [00:04<00:05, 5.05it/s] 48%|████▊ | 24/50 [00:04<00:05, 5.05it/s] 50%|█████ | 25/50 [00:04<00:04, 5.06it/s] 52%|█████▏ | 26/50 [00:05<00:04, 5.07it/s] 54%|█████▍ | 27/50 [00:05<00:04, 5.02it/s] 56%|█████▌ | 28/50 [00:05<00:04, 5.02it/s] 58%|█████▊ | 29/50 [00:05<00:04, 4.96it/s] 60%|██████ | 30/50 [00:05<00:04, 4.96it/s] 62%|██████▏ | 31/50 [00:06<00:03, 4.98it/s] 64%|██████▍ | 32/50 [00:06<00:03, 4.96it/s] 66%|██████▌ | 33/50 [00:06<00:03, 4.98it/s] 68%|██████▊ | 34/50 [00:06<00:03, 4.93it/s] 70%|███████ | 35/50 [00:06<00:03, 4.94it/s] 72%|███████▏ | 36/50 [00:07<00:02, 4.94it/s] 74%|███████▍ | 37/50 [00:07<00:02, 4.96it/s] 76%|███████▌ | 38/50 [00:07<00:02, 4.99it/s] 78%|███████▊ | 39/50 [00:07<00:02, 4.98it/s] 80%|████████ | 40/50 [00:07<00:01, 5.01it/s] 82%|████████▏ | 41/50 [00:08<00:01, 5.01it/s] 84%|████████▍ | 42/50 [00:08<00:01, 5.05it/s] 86%|████████▌ | 43/50 [00:08<00:01, 5.03it/s] 88%|████████▊ | 44/50 [00:08<00:01, 4.94it/s] 90%|█████████ | 45/50 [00:08<00:01, 4.94it/s] 92%|█████████▏| 46/50 [00:09<00:00, 4.93it/s] 94%|█████████▍| 47/50 [00:09<00:00, 4.95it/s] 96%|█████████▌| 48/50 [00:09<00:00, 4.95it/s] 98%|█████████▊| 49/50 [00:09<00:00, 4.93it/s] 100%|██████████| 50/50 [00:10<00:00, 4.94it/s] 100%|██████████| 50/50 [00:10<00:00, 5.00it/s]Prediction
cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8IDoju3qhrbc5bs4xw3brkqbgdugqStatusSucceededSourceWebHardwareT4Total durationCreatedInput
- width
- 512
- height
- 512
- prompt
- a high quality painting of a very cute qdg dog puppy, friendly, curious expression. painting by artgerm and greg rutkowski and alphonse mucha
- scheduler
- DDIM
- num_outputs
- 1
- guidance_scale
- 7.5
- negative_prompt
- cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 512, "height": 512, "prompt": "a high quality painting of a very cute qdg dog puppy, friendly, curious expression. painting by artgerm and greg rutkowski and alphonse mucha", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", { input: { width: 512, height: 512, prompt: "a high quality painting of a very cute qdg dog puppy, friendly, curious expression. painting by artgerm and greg rutkowski and alphonse mucha", scheduler: "DDIM", num_outputs: 1, guidance_scale: 7.5, negative_prompt: "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", prompt_strength: 0.8, num_inference_steps: 50 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", input={ "width": 512, "height": 512, "prompt": "a high quality painting of a very cute qdg dog puppy, friendly, curious expression. painting by artgerm and greg rutkowski and alphonse mucha", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } ) # To access the file URL: print(output[0].url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output[0].read())To learn more, take a look at the guide on getting started with Python.
Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", "input": { "width": 512, "height": 512, "prompt": "a high quality painting of a very cute qdg dog puppy, friendly, curious expression. painting by artgerm and greg rutkowski and alphonse mucha", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8 \ -i 'width=512' \ -i 'height=512' \ -i 'prompt="a high quality painting of a very cute qdg dog puppy, friendly, curious expression. painting by artgerm and greg rutkowski and alphonse mucha"' \ -i 'scheduler="DDIM"' \ -i 'num_outputs=1' \ -i 'guidance_scale=7.5' \ -i 'negative_prompt="cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark"' \ -i 'prompt_strength=0.8' \ -i 'num_inference_steps=50'To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 512, "height": 512, "prompt": "a high quality painting of a very cute qdg dog puppy, friendly, curious expression. painting by artgerm and greg rutkowski and alphonse mucha", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-06-18T20:31:29.452317Z", "created_at": "2023-06-18T20:31:17.294254Z", "data_removed": false, "error": null, "id": "oju3qhrbc5bs4xw3brkqbgdugq", "input": { "width": 512, "height": 512, "prompt": "a high quality painting of a very cute qdg dog puppy, friendly, curious expression. painting by artgerm and greg rutkowski and alphonse mucha", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 27456\nusing txt2img\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:11, 4.31it/s]\n 4%|▍ | 2/50 [00:00<00:10, 4.65it/s]\n 6%|▌ | 3/50 [00:00<00:09, 4.75it/s]\n 8%|▊ | 4/50 [00:00<00:09, 4.75it/s]\n 10%|█ | 5/50 [00:01<00:09, 4.61it/s]\n 12%|█▏ | 6/50 [00:01<00:09, 4.58it/s]\n 14%|█▍ | 7/50 [00:01<00:09, 4.68it/s]\n 16%|█▌ | 8/50 [00:01<00:08, 4.77it/s]\n 18%|█▊ | 9/50 [00:01<00:08, 4.77it/s]\n 20%|██ | 10/50 [00:02<00:08, 4.70it/s]\n 22%|██▏ | 11/50 [00:02<00:08, 4.60it/s]\n 24%|██▍ | 12/50 [00:02<00:08, 4.63it/s]\n 26%|██▌ | 13/50 [00:02<00:07, 4.67it/s]\n 28%|██▊ | 14/50 [00:02<00:07, 4.69it/s]\n 30%|███ | 15/50 [00:03<00:07, 4.55it/s]\n 32%|███▏ | 16/50 [00:03<00:07, 4.56it/s]\n 34%|███▍ | 17/50 [00:03<00:07, 4.65it/s]\n 36%|███▌ | 18/50 [00:03<00:06, 4.70it/s]\n 38%|███▊ | 19/50 [00:04<00:06, 4.63it/s]\n 40%|████ | 20/50 [00:04<00:06, 4.52it/s]\n 42%|████▏ | 21/50 [00:04<00:06, 4.59it/s]\n 44%|████▍ | 22/50 [00:04<00:06, 4.59it/s]\n 46%|████▌ | 23/50 [00:04<00:05, 4.66it/s]\n 48%|████▊ | 24/50 [00:05<00:05, 4.60it/s]\n 50%|█████ | 25/50 [00:05<00:05, 4.52it/s]\n 52%|█████▏ | 26/50 [00:05<00:05, 4.58it/s]\n 54%|█████▍ | 27/50 [00:05<00:05, 4.58it/s]\n 56%|█████▌ | 28/50 [00:06<00:04, 4.57it/s]\n 58%|█████▊ | 29/50 [00:06<00:04, 4.52it/s]\n 60%|██████ | 30/50 [00:06<00:04, 4.54it/s]\n 62%|██████▏ | 31/50 [00:06<00:04, 4.60it/s]\n 64%|██████▍ | 32/50 [00:06<00:03, 4.59it/s]\n 66%|██████▌ | 33/50 [00:07<00:03, 4.56it/s]\n 68%|██████▊ | 34/50 [00:07<00:03, 4.53it/s]\n 70%|███████ | 35/50 [00:07<00:03, 4.55it/s]\n 72%|███████▏ | 36/50 [00:07<00:03, 4.58it/s]\n 74%|███████▍ | 37/50 [00:08<00:02, 4.57it/s]\n 76%|███████▌ | 38/50 [00:08<00:02, 4.54it/s]\n 78%|███████▊ | 39/50 [00:08<00:02, 4.52it/s]\n 80%|████████ | 40/50 [00:08<00:02, 4.54it/s]\n 82%|████████▏ | 41/50 [00:08<00:01, 4.54it/s]\n 84%|████████▍ | 42/50 [00:09<00:01, 4.51it/s]\n 86%|████████▌ | 43/50 [00:09<00:01, 4.50it/s]\n 88%|████████▊ | 44/50 [00:09<00:01, 4.49it/s]\n 90%|█████████ | 45/50 [00:09<00:01, 4.53it/s]\n 92%|█████████▏| 46/50 [00:10<00:00, 4.51it/s]\n 94%|█████████▍| 47/50 [00:10<00:00, 4.48it/s]\n 96%|█████████▌| 48/50 [00:10<00:00, 4.45it/s]\n 98%|█████████▊| 49/50 [00:10<00:00, 4.46it/s]\n100%|██████████| 50/50 [00:10<00:00, 4.47it/s]\n100%|██████████| 50/50 [00:10<00:00, 4.57it/s]", "metrics": { "predict_time": 12.204896, "total_time": 12.158063 }, "output": [ "https://replicate.delivery/pbxt/J2sXfhERhmwycCHlfPsbQ0kGBDIA8fVwLhfyGGsqKIrC6GdEB/out-0.png" ], "started_at": "2023-06-18T20:31:17.247421Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/oju3qhrbc5bs4xw3brkqbgdugq", "cancel": "https://api.replicate.com/v1/predictions/oju3qhrbc5bs4xw3brkqbgdugq/cancel" }, "version": "e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8" }Generated inUsing seed: 27456 using txt2img 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:11, 4.31it/s] 4%|▍ | 2/50 [00:00<00:10, 4.65it/s] 6%|▌ | 3/50 [00:00<00:09, 4.75it/s] 8%|▊ | 4/50 [00:00<00:09, 4.75it/s] 10%|█ | 5/50 [00:01<00:09, 4.61it/s] 12%|█▏ | 6/50 [00:01<00:09, 4.58it/s] 14%|█▍ | 7/50 [00:01<00:09, 4.68it/s] 16%|█▌ | 8/50 [00:01<00:08, 4.77it/s] 18%|█▊ | 9/50 [00:01<00:08, 4.77it/s] 20%|██ | 10/50 [00:02<00:08, 4.70it/s] 22%|██▏ | 11/50 [00:02<00:08, 4.60it/s] 24%|██▍ | 12/50 [00:02<00:08, 4.63it/s] 26%|██▌ | 13/50 [00:02<00:07, 4.67it/s] 28%|██▊ | 14/50 [00:02<00:07, 4.69it/s] 30%|███ | 15/50 [00:03<00:07, 4.55it/s] 32%|███▏ | 16/50 [00:03<00:07, 4.56it/s] 34%|███▍ | 17/50 [00:03<00:07, 4.65it/s] 36%|███▌ | 18/50 [00:03<00:06, 4.70it/s] 38%|███▊ | 19/50 [00:04<00:06, 4.63it/s] 40%|████ | 20/50 [00:04<00:06, 4.52it/s] 42%|████▏ | 21/50 [00:04<00:06, 4.59it/s] 44%|████▍ | 22/50 [00:04<00:06, 4.59it/s] 46%|████▌ | 23/50 [00:04<00:05, 4.66it/s] 48%|████▊ | 24/50 [00:05<00:05, 4.60it/s] 50%|█████ | 25/50 [00:05<00:05, 4.52it/s] 52%|█████▏ | 26/50 [00:05<00:05, 4.58it/s] 54%|█████▍ | 27/50 [00:05<00:05, 4.58it/s] 56%|█████▌ | 28/50 [00:06<00:04, 4.57it/s] 58%|█████▊ | 29/50 [00:06<00:04, 4.52it/s] 60%|██████ | 30/50 [00:06<00:04, 4.54it/s] 62%|██████▏ | 31/50 [00:06<00:04, 4.60it/s] 64%|██████▍ | 32/50 [00:06<00:03, 4.59it/s] 66%|██████▌ | 33/50 [00:07<00:03, 4.56it/s] 68%|██████▊ | 34/50 [00:07<00:03, 4.53it/s] 70%|███████ | 35/50 [00:07<00:03, 4.55it/s] 72%|███████▏ | 36/50 [00:07<00:03, 4.58it/s] 74%|███████▍ | 37/50 [00:08<00:02, 4.57it/s] 76%|███████▌ | 38/50 [00:08<00:02, 4.54it/s] 78%|███████▊ | 39/50 [00:08<00:02, 4.52it/s] 80%|████████ | 40/50 [00:08<00:02, 4.54it/s] 82%|████████▏ | 41/50 [00:08<00:01, 4.54it/s] 84%|████████▍ | 42/50 [00:09<00:01, 4.51it/s] 86%|████████▌ | 43/50 [00:09<00:01, 4.50it/s] 88%|████████▊ | 44/50 [00:09<00:01, 4.49it/s] 90%|█████████ | 45/50 [00:09<00:01, 4.53it/s] 92%|█████████▏| 46/50 [00:10<00:00, 4.51it/s] 94%|█████████▍| 47/50 [00:10<00:00, 4.48it/s] 96%|█████████▌| 48/50 [00:10<00:00, 4.45it/s] 98%|█████████▊| 49/50 [00:10<00:00, 4.46it/s] 100%|██████████| 50/50 [00:10<00:00, 4.47it/s] 100%|██████████| 50/50 [00:10<00:00, 4.57it/s]Prediction
cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8IDwbebd2zberml3yawy4r6uoozcqStatusSucceededSourceWebHardwareT4Total durationCreatedInput
- width
- 512
- height
- 512
- prompt
- a high quality painting of a very cute qdg dog puppy, friendly, curious expression. painting by artgerm and greg rutkowski and alphonse mucha
- scheduler
- DDIM
- num_outputs
- 1
- guidance_scale
- 7.5
- negative_prompt
- cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 512, "height": 512, "prompt": "a high quality painting of a very cute qdg dog puppy, friendly, curious expression. painting by artgerm and greg rutkowski and alphonse mucha", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", { input: { width: 512, height: 512, prompt: "a high quality painting of a very cute qdg dog puppy, friendly, curious expression. painting by artgerm and greg rutkowski and alphonse mucha", scheduler: "DDIM", num_outputs: 1, guidance_scale: 7.5, negative_prompt: "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", prompt_strength: 0.8, num_inference_steps: 50 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", input={ "width": 512, "height": 512, "prompt": "a high quality painting of a very cute qdg dog puppy, friendly, curious expression. painting by artgerm and greg rutkowski and alphonse mucha", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } ) # To access the file URL: print(output[0].url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output[0].read())To learn more, take a look at the guide on getting started with Python.
Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", "input": { "width": 512, "height": 512, "prompt": "a high quality painting of a very cute qdg dog puppy, friendly, curious expression. painting by artgerm and greg rutkowski and alphonse mucha", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8 \ -i 'width=512' \ -i 'height=512' \ -i 'prompt="a high quality painting of a very cute qdg dog puppy, friendly, curious expression. painting by artgerm and greg rutkowski and alphonse mucha"' \ -i 'scheduler="DDIM"' \ -i 'num_outputs=1' \ -i 'guidance_scale=7.5' \ -i 'negative_prompt="cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark"' \ -i 'prompt_strength=0.8' \ -i 'num_inference_steps=50'To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 512, "height": 512, "prompt": "a high quality painting of a very cute qdg dog puppy, friendly, curious expression. painting by artgerm and greg rutkowski and alphonse mucha", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-06-18T20:32:57.440302Z", "created_at": "2023-06-18T20:32:45.568890Z", "data_removed": false, "error": null, "id": "wbebd2zberml3yawy4r6uoozcq", "input": { "width": 512, "height": 512, "prompt": "a high quality painting of a very cute qdg dog puppy, friendly, curious expression. painting by artgerm and greg rutkowski and alphonse mucha", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 37642\nusing txt2img\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:12, 4.03it/s]\n 4%|▍ | 2/50 [00:00<00:10, 4.54it/s]\n 6%|▌ | 3/50 [00:00<00:09, 4.71it/s]\n 8%|▊ | 4/50 [00:00<00:09, 4.79it/s]\n 10%|█ | 5/50 [00:01<00:09, 4.72it/s]\n 12%|█▏ | 6/50 [00:01<00:09, 4.59it/s]\n 14%|█▍ | 7/50 [00:01<00:09, 4.70it/s]\n 16%|█▌ | 8/50 [00:01<00:08, 4.79it/s]\n 18%|█▊ | 9/50 [00:01<00:08, 4.83it/s]\n 20%|██ | 10/50 [00:02<00:08, 4.70it/s]\n 22%|██▏ | 11/50 [00:02<00:08, 4.64it/s]\n 24%|██▍ | 12/50 [00:02<00:08, 4.71it/s]\n 26%|██▌ | 13/50 [00:02<00:07, 4.72it/s]\n 28%|██▊ | 14/50 [00:02<00:07, 4.72it/s]\n 30%|███ | 15/50 [00:03<00:07, 4.64it/s]\n 32%|███▏ | 16/50 [00:03<00:07, 4.63it/s]\n 34%|███▍ | 17/50 [00:03<00:07, 4.70it/s]\n 36%|███▌ | 18/50 [00:03<00:06, 4.77it/s]\n 38%|███▊ | 19/50 [00:04<00:06, 4.73it/s]\n 40%|████ | 20/50 [00:04<00:06, 4.65it/s]\n 42%|████▏ | 21/50 [00:04<00:06, 4.64it/s]\n 44%|████▍ | 22/50 [00:04<00:06, 4.66it/s]\n 46%|████▌ | 23/50 [00:04<00:05, 4.71it/s]\n 48%|████▊ | 24/50 [00:05<00:05, 4.66it/s]\n 50%|█████ | 25/50 [00:05<00:05, 4.62it/s]\n 52%|█████▏ | 26/50 [00:05<00:05, 4.67it/s]\n 54%|█████▍ | 27/50 [00:05<00:04, 4.66it/s]\n 56%|█████▌ | 28/50 [00:05<00:04, 4.71it/s]\n 58%|█████▊ | 29/50 [00:06<00:04, 4.67it/s]\n 60%|██████ | 30/50 [00:06<00:04, 4.66it/s]\n 62%|██████▏ | 31/50 [00:06<00:04, 4.67it/s]\n 64%|██████▍ | 32/50 [00:06<00:03, 4.70it/s]\n 66%|██████▌ | 33/50 [00:07<00:03, 4.67it/s]\n 68%|██████▊ | 34/50 [00:07<00:03, 4.63it/s]\n 70%|███████ | 35/50 [00:07<00:03, 4.66it/s]\n 72%|███████▏ | 36/50 [00:07<00:03, 4.65it/s]\n 74%|███████▍ | 37/50 [00:07<00:02, 4.64it/s]\n 76%|███████▌ | 38/50 [00:08<00:02, 4.63it/s]\n 78%|███████▊ | 39/50 [00:08<00:02, 4.59it/s]\n 80%|████████ | 40/50 [00:08<00:02, 4.62it/s]\n 82%|████████▏ | 41/50 [00:08<00:01, 4.62it/s]\n 84%|████████▍ | 42/50 [00:09<00:01, 4.64it/s]\n 86%|████████▌ | 43/50 [00:09<00:01, 4.61it/s]\n 88%|████████▊ | 44/50 [00:09<00:01, 4.59it/s]\n 90%|█████████ | 45/50 [00:09<00:01, 4.61it/s]\n 92%|█████████▏| 46/50 [00:09<00:00, 4.63it/s]\n 94%|█████████▍| 47/50 [00:10<00:00, 4.60it/s]\n 96%|█████████▌| 48/50 [00:10<00:00, 4.58it/s]\n 98%|█████████▊| 49/50 [00:10<00:00, 4.62it/s]\n100%|██████████| 50/50 [00:10<00:00, 4.64it/s]\n100%|██████████| 50/50 [00:10<00:00, 4.66it/s]", "metrics": { "predict_time": 11.928974, "total_time": 11.871412 }, "output": [ "https://replicate.delivery/pbxt/c5WNiAiEirI9BRiVo7djNOsZiDia4jjGsww1HlrTJwJe3ojIA/out-0.png" ], "started_at": "2023-06-18T20:32:45.511328Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/wbebd2zberml3yawy4r6uoozcq", "cancel": "https://api.replicate.com/v1/predictions/wbebd2zberml3yawy4r6uoozcq/cancel" }, "version": "e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8" }Generated inUsing seed: 37642 using txt2img 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:12, 4.03it/s] 4%|▍ | 2/50 [00:00<00:10, 4.54it/s] 6%|▌ | 3/50 [00:00<00:09, 4.71it/s] 8%|▊ | 4/50 [00:00<00:09, 4.79it/s] 10%|█ | 5/50 [00:01<00:09, 4.72it/s] 12%|█▏ | 6/50 [00:01<00:09, 4.59it/s] 14%|█▍ | 7/50 [00:01<00:09, 4.70it/s] 16%|█▌ | 8/50 [00:01<00:08, 4.79it/s] 18%|█▊ | 9/50 [00:01<00:08, 4.83it/s] 20%|██ | 10/50 [00:02<00:08, 4.70it/s] 22%|██▏ | 11/50 [00:02<00:08, 4.64it/s] 24%|██▍ | 12/50 [00:02<00:08, 4.71it/s] 26%|██▌ | 13/50 [00:02<00:07, 4.72it/s] 28%|██▊ | 14/50 [00:02<00:07, 4.72it/s] 30%|███ | 15/50 [00:03<00:07, 4.64it/s] 32%|███▏ | 16/50 [00:03<00:07, 4.63it/s] 34%|███▍ | 17/50 [00:03<00:07, 4.70it/s] 36%|███▌ | 18/50 [00:03<00:06, 4.77it/s] 38%|███▊ | 19/50 [00:04<00:06, 4.73it/s] 40%|████ | 20/50 [00:04<00:06, 4.65it/s] 42%|████▏ | 21/50 [00:04<00:06, 4.64it/s] 44%|████▍ | 22/50 [00:04<00:06, 4.66it/s] 46%|████▌ | 23/50 [00:04<00:05, 4.71it/s] 48%|████▊ | 24/50 [00:05<00:05, 4.66it/s] 50%|█████ | 25/50 [00:05<00:05, 4.62it/s] 52%|█████▏ | 26/50 [00:05<00:05, 4.67it/s] 54%|█████▍ | 27/50 [00:05<00:04, 4.66it/s] 56%|█████▌ | 28/50 [00:05<00:04, 4.71it/s] 58%|█████▊ | 29/50 [00:06<00:04, 4.67it/s] 60%|██████ | 30/50 [00:06<00:04, 4.66it/s] 62%|██████▏ | 31/50 [00:06<00:04, 4.67it/s] 64%|██████▍ | 32/50 [00:06<00:03, 4.70it/s] 66%|██████▌ | 33/50 [00:07<00:03, 4.67it/s] 68%|██████▊ | 34/50 [00:07<00:03, 4.63it/s] 70%|███████ | 35/50 [00:07<00:03, 4.66it/s] 72%|███████▏ | 36/50 [00:07<00:03, 4.65it/s] 74%|███████▍ | 37/50 [00:07<00:02, 4.64it/s] 76%|███████▌ | 38/50 [00:08<00:02, 4.63it/s] 78%|███████▊ | 39/50 [00:08<00:02, 4.59it/s] 80%|████████ | 40/50 [00:08<00:02, 4.62it/s] 82%|████████▏ | 41/50 [00:08<00:01, 4.62it/s] 84%|████████▍ | 42/50 [00:09<00:01, 4.64it/s] 86%|████████▌ | 43/50 [00:09<00:01, 4.61it/s] 88%|████████▊ | 44/50 [00:09<00:01, 4.59it/s] 90%|█████████ | 45/50 [00:09<00:01, 4.61it/s] 92%|█████████▏| 46/50 [00:09<00:00, 4.63it/s] 94%|█████████▍| 47/50 [00:10<00:00, 4.60it/s] 96%|█████████▌| 48/50 [00:10<00:00, 4.58it/s] 98%|█████████▊| 49/50 [00:10<00:00, 4.62it/s] 100%|██████████| 50/50 [00:10<00:00, 4.64it/s] 100%|██████████| 50/50 [00:10<00:00, 4.66it/s]Prediction
cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8IDwbfitobb6p5axbvxanfduiwsjmStatusSucceededSourceWebHardwareT4Total durationCreatedInput
- width
- 512
- height
- 512
- prompt
- magnificent qdg dog portrait masterpiece work of art. oil on canvas. Digitally painted. Realistic. 3D. 8k. UHD.
- scheduler
- DDIM
- num_outputs
- 1
- guidance_scale
- 7.5
- negative_prompt
- cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 512, "height": 512, "prompt": "magnificent qdg dog portrait masterpiece work of art. oil on canvas. Digitally painted. Realistic. 3D. 8k. UHD.", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", { input: { width: 512, height: 512, prompt: "magnificent qdg dog portrait masterpiece work of art. oil on canvas. Digitally painted. Realistic. 3D. 8k. UHD.", scheduler: "DDIM", num_outputs: 1, guidance_scale: 7.5, negative_prompt: "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", prompt_strength: 0.8, num_inference_steps: 50 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", input={ "width": 512, "height": 512, "prompt": "magnificent qdg dog portrait masterpiece work of art. oil on canvas. Digitally painted. Realistic. 3D. 8k. UHD.", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } ) # To access the file URL: print(output[0].url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output[0].read())To learn more, take a look at the guide on getting started with Python.
Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", "input": { "width": 512, "height": 512, "prompt": "magnificent qdg dog portrait masterpiece work of art. oil on canvas. Digitally painted. Realistic. 3D. 8k. UHD.", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8 \ -i 'width=512' \ -i 'height=512' \ -i 'prompt="magnificent qdg dog portrait masterpiece work of art. oil on canvas. Digitally painted. Realistic. 3D. 8k. UHD."' \ -i 'scheduler="DDIM"' \ -i 'num_outputs=1' \ -i 'guidance_scale=7.5' \ -i 'negative_prompt="cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark"' \ -i 'prompt_strength=0.8' \ -i 'num_inference_steps=50'To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 512, "height": 512, "prompt": "magnificent qdg dog portrait masterpiece work of art. oil on canvas. Digitally painted. Realistic. 3D. 8k. UHD.", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-06-18T20:36:12.348349Z", "created_at": "2023-06-18T20:36:00.417741Z", "data_removed": false, "error": null, "id": "wbfitobb6p5axbvxanfduiwsjm", "input": { "width": 512, "height": 512, "prompt": "magnificent qdg dog portrait masterpiece work of art. oil on canvas. Digitally painted. Realistic. 3D. 8k. UHD.", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 11850\nusing txt2img\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:12, 3.94it/s]\n 4%|▍ | 2/50 [00:00<00:10, 4.51it/s]\n 6%|▌ | 3/50 [00:00<00:09, 4.71it/s]\n 8%|▊ | 4/50 [00:00<00:09, 4.79it/s]\n 10%|█ | 5/50 [00:01<00:09, 4.77it/s]\n 12%|█▏ | 6/50 [00:01<00:09, 4.60it/s]\n 14%|█▍ | 7/50 [00:01<00:09, 4.69it/s]\n 16%|█▌ | 8/50 [00:01<00:08, 4.76it/s]\n 18%|█▊ | 9/50 [00:01<00:08, 4.82it/s]\n 20%|██ | 10/50 [00:02<00:08, 4.70it/s]\n 22%|██▏ | 11/50 [00:02<00:08, 4.64it/s]\n 24%|██▍ | 12/50 [00:02<00:08, 4.73it/s]\n 26%|██▌ | 13/50 [00:02<00:07, 4.80it/s]\n 28%|██▊ | 14/50 [00:02<00:07, 4.82it/s]\n 30%|███ | 15/50 [00:03<00:07, 4.73it/s]\n 32%|███▏ | 16/50 [00:03<00:07, 4.68it/s]\n 34%|███▍ | 17/50 [00:03<00:06, 4.74it/s]\n 36%|███▌ | 18/50 [00:03<00:06, 4.80it/s]\n 38%|███▊ | 19/50 [00:04<00:06, 4.79it/s]\n 40%|████ | 20/50 [00:04<00:06, 4.66it/s]\n 42%|████▏ | 21/50 [00:04<00:06, 4.68it/s]\n 44%|████▍ | 22/50 [00:04<00:05, 4.73it/s]\n 46%|████▌ | 23/50 [00:04<00:05, 4.71it/s]\n 48%|████▊ | 24/50 [00:05<00:05, 4.72it/s]\n 50%|█████ | 25/50 [00:05<00:05, 4.62it/s]\n 52%|█████▏ | 26/50 [00:05<00:05, 4.65it/s]\n 54%|█████▍ | 27/50 [00:05<00:04, 4.74it/s]\n 56%|█████▌ | 28/50 [00:05<00:04, 4.74it/s]\n 58%|█████▊ | 29/50 [00:06<00:04, 4.68it/s]\n 60%|██████ | 30/50 [00:06<00:04, 4.63it/s]\n 62%|██████▏ | 31/50 [00:06<00:04, 4.62it/s]\n 64%|██████▍ | 32/50 [00:06<00:03, 4.69it/s]\n 66%|██████▌ | 33/50 [00:07<00:03, 4.68it/s]\n 68%|██████▊ | 34/50 [00:07<00:03, 4.63it/s]\n 70%|███████ | 35/50 [00:07<00:03, 4.62it/s]\n 72%|███████▏ | 36/50 [00:07<00:03, 4.64it/s]\n 74%|███████▍ | 37/50 [00:07<00:02, 4.72it/s]\n 76%|███████▌ | 38/50 [00:08<00:02, 4.67it/s]\n 78%|███████▊ | 39/50 [00:08<00:02, 4.67it/s]\n 80%|████████ | 40/50 [00:08<00:02, 4.66it/s]\n 82%|████████▏ | 41/50 [00:08<00:01, 4.65it/s]\n 84%|████████▍ | 42/50 [00:08<00:01, 4.72it/s]\n 86%|████████▌ | 43/50 [00:09<00:01, 4.69it/s]\n 88%|████████▊ | 44/50 [00:09<00:01, 4.69it/s]\n 90%|█████████ | 45/50 [00:09<00:01, 4.66it/s]\n 92%|█████████▏| 46/50 [00:09<00:00, 4.67it/s]\n 94%|█████████▍| 47/50 [00:10<00:00, 4.69it/s]\n 96%|█████████▌| 48/50 [00:10<00:00, 4.68it/s]\n 98%|█████████▊| 49/50 [00:10<00:00, 4.69it/s]\n100%|██████████| 50/50 [00:10<00:00, 4.65it/s]\n100%|██████████| 50/50 [00:10<00:00, 4.69it/s]", "metrics": { "predict_time": 11.952534, "total_time": 11.930608 }, "output": [ "https://replicate.delivery/pbxt/YvYthaMyIx76NRN8jB8OWVfCecdXeuefbAxB7elqjWU0uc0RE/out-0.png" ], "started_at": "2023-06-18T20:36:00.395815Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/wbfitobb6p5axbvxanfduiwsjm", "cancel": "https://api.replicate.com/v1/predictions/wbfitobb6p5axbvxanfduiwsjm/cancel" }, "version": "e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8" }Generated inUsing seed: 11850 using txt2img 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:12, 3.94it/s] 4%|▍ | 2/50 [00:00<00:10, 4.51it/s] 6%|▌ | 3/50 [00:00<00:09, 4.71it/s] 8%|▊ | 4/50 [00:00<00:09, 4.79it/s] 10%|█ | 5/50 [00:01<00:09, 4.77it/s] 12%|█▏ | 6/50 [00:01<00:09, 4.60it/s] 14%|█▍ | 7/50 [00:01<00:09, 4.69it/s] 16%|█▌ | 8/50 [00:01<00:08, 4.76it/s] 18%|█▊ | 9/50 [00:01<00:08, 4.82it/s] 20%|██ | 10/50 [00:02<00:08, 4.70it/s] 22%|██▏ | 11/50 [00:02<00:08, 4.64it/s] 24%|██▍ | 12/50 [00:02<00:08, 4.73it/s] 26%|██▌ | 13/50 [00:02<00:07, 4.80it/s] 28%|██▊ | 14/50 [00:02<00:07, 4.82it/s] 30%|███ | 15/50 [00:03<00:07, 4.73it/s] 32%|███▏ | 16/50 [00:03<00:07, 4.68it/s] 34%|███▍ | 17/50 [00:03<00:06, 4.74it/s] 36%|███▌ | 18/50 [00:03<00:06, 4.80it/s] 38%|███▊ | 19/50 [00:04<00:06, 4.79it/s] 40%|████ | 20/50 [00:04<00:06, 4.66it/s] 42%|████▏ | 21/50 [00:04<00:06, 4.68it/s] 44%|████▍ | 22/50 [00:04<00:05, 4.73it/s] 46%|████▌ | 23/50 [00:04<00:05, 4.71it/s] 48%|████▊ | 24/50 [00:05<00:05, 4.72it/s] 50%|█████ | 25/50 [00:05<00:05, 4.62it/s] 52%|█████▏ | 26/50 [00:05<00:05, 4.65it/s] 54%|█████▍ | 27/50 [00:05<00:04, 4.74it/s] 56%|█████▌ | 28/50 [00:05<00:04, 4.74it/s] 58%|█████▊ | 29/50 [00:06<00:04, 4.68it/s] 60%|██████ | 30/50 [00:06<00:04, 4.63it/s] 62%|██████▏ | 31/50 [00:06<00:04, 4.62it/s] 64%|██████▍ | 32/50 [00:06<00:03, 4.69it/s] 66%|██████▌ | 33/50 [00:07<00:03, 4.68it/s] 68%|██████▊ | 34/50 [00:07<00:03, 4.63it/s] 70%|███████ | 35/50 [00:07<00:03, 4.62it/s] 72%|███████▏ | 36/50 [00:07<00:03, 4.64it/s] 74%|███████▍ | 37/50 [00:07<00:02, 4.72it/s] 76%|███████▌ | 38/50 [00:08<00:02, 4.67it/s] 78%|███████▊ | 39/50 [00:08<00:02, 4.67it/s] 80%|████████ | 40/50 [00:08<00:02, 4.66it/s] 82%|████████▏ | 41/50 [00:08<00:01, 4.65it/s] 84%|████████▍ | 42/50 [00:08<00:01, 4.72it/s] 86%|████████▌ | 43/50 [00:09<00:01, 4.69it/s] 88%|████████▊ | 44/50 [00:09<00:01, 4.69it/s] 90%|█████████ | 45/50 [00:09<00:01, 4.66it/s] 92%|█████████▏| 46/50 [00:09<00:00, 4.67it/s] 94%|█████████▍| 47/50 [00:10<00:00, 4.69it/s] 96%|█████████▌| 48/50 [00:10<00:00, 4.68it/s] 98%|█████████▊| 49/50 [00:10<00:00, 4.69it/s] 100%|██████████| 50/50 [00:10<00:00, 4.65it/s] 100%|██████████| 50/50 [00:10<00:00, 4.69it/s]Prediction
cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8IDfms6m7jbqvdjpijbbkv2iiiqhmStatusSucceededSourceWebHardwareT4Total durationCreatedInput
- width
- 512
- height
- 512
- prompt
- intricate five star qdg dog facial portrait by casey weldon, oil on canvas, hdr, high detail, photo realistic, hyperrealism, matte finish, high contrast, 3 d depth, centered, masterpiece, vivid and vibrant colors, enhanced light effect, enhanced eye detail, artstationhd
- scheduler
- DDIM
- num_outputs
- 1
- guidance_scale
- 7.5
- negative_prompt
- cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 512, "height": 512, "prompt": "intricate five star qdg dog facial portrait by casey weldon, oil on canvas, hdr, high detail, photo realistic, hyperrealism, matte finish, high contrast, 3 d depth, centered, masterpiece, vivid and vibrant colors, enhanced light effect, enhanced eye detail, artstationhd", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", { input: { width: 512, height: 512, prompt: "intricate five star qdg dog facial portrait by casey weldon, oil on canvas, hdr, high detail, photo realistic, hyperrealism, matte finish, high contrast, 3 d depth, centered, masterpiece, vivid and vibrant colors, enhanced light effect, enhanced eye detail, artstationhd", scheduler: "DDIM", num_outputs: 1, guidance_scale: 7.5, negative_prompt: "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", prompt_strength: 0.8, num_inference_steps: 50 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", input={ "width": 512, "height": 512, "prompt": "intricate five star qdg dog facial portrait by casey weldon, oil on canvas, hdr, high detail, photo realistic, hyperrealism, matte finish, high contrast, 3 d depth, centered, masterpiece, vivid and vibrant colors, enhanced light effect, enhanced eye detail, artstationhd", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } ) # To access the file URL: print(output[0].url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output[0].read())To learn more, take a look at the guide on getting started with Python.
Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", "input": { "width": 512, "height": 512, "prompt": "intricate five star qdg dog facial portrait by casey weldon, oil on canvas, hdr, high detail, photo realistic, hyperrealism, matte finish, high contrast, 3 d depth, centered, masterpiece, vivid and vibrant colors, enhanced light effect, enhanced eye detail, artstationhd", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8 \ -i 'width=512' \ -i 'height=512' \ -i 'prompt="intricate five star qdg dog facial portrait by casey weldon, oil on canvas, hdr, high detail, photo realistic, hyperrealism, matte finish, high contrast, 3 d depth, centered, masterpiece, vivid and vibrant colors, enhanced light effect, enhanced eye detail, artstationhd"' \ -i 'scheduler="DDIM"' \ -i 'num_outputs=1' \ -i 'guidance_scale=7.5' \ -i 'negative_prompt="cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark"' \ -i 'prompt_strength=0.8' \ -i 'num_inference_steps=50'To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 512, "height": 512, "prompt": "intricate five star qdg dog facial portrait by casey weldon, oil on canvas, hdr, high detail, photo realistic, hyperrealism, matte finish, high contrast, 3 d depth, centered, masterpiece, vivid and vibrant colors, enhanced light effect, enhanced eye detail, artstationhd", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-06-18T20:37:21.412197Z", "created_at": "2023-06-18T20:37:08.989184Z", "data_removed": false, "error": null, "id": "fms6m7jbqvdjpijbbkv2iiiqhm", "input": { "width": 512, "height": 512, "prompt": "intricate five star qdg dog facial portrait by casey weldon, oil on canvas, hdr, high detail, photo realistic, hyperrealism, matte finish, high contrast, 3 d depth, centered, masterpiece, vivid and vibrant colors, enhanced light effect, enhanced eye detail, artstationhd", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 41701\nusing txt2img\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:12, 3.90it/s]\n 4%|▍ | 2/50 [00:00<00:11, 4.36it/s]\n 6%|▌ | 3/50 [00:00<00:10, 4.58it/s]\n 8%|▊ | 4/50 [00:00<00:09, 4.66it/s]\n 10%|█ | 5/50 [00:01<00:10, 4.44it/s]\n 12%|█▏ | 6/50 [00:01<00:09, 4.48it/s]\n 14%|█▍ | 7/50 [00:01<00:09, 4.52it/s]\n 16%|█▌ | 8/50 [00:01<00:09, 4.56it/s]\n 18%|█▊ | 9/50 [00:01<00:08, 4.58it/s]\n 20%|██ | 10/50 [00:02<00:08, 4.45it/s]\n 22%|██▏ | 11/50 [00:02<00:08, 4.48it/s]\n 24%|██▍ | 12/50 [00:02<00:08, 4.54it/s]\n 26%|██▌ | 13/50 [00:02<00:08, 4.58it/s]\n 28%|██▊ | 14/50 [00:03<00:08, 4.48it/s]\n 30%|███ | 15/50 [00:03<00:07, 4.44it/s]\n 32%|███▏ | 16/50 [00:03<00:07, 4.47it/s]\n 34%|███▍ | 17/50 [00:03<00:07, 4.52it/s]\n 36%|███▌ | 18/50 [00:04<00:07, 4.50it/s]\n 38%|███▊ | 19/50 [00:04<00:06, 4.44it/s]\n 40%|████ | 20/50 [00:04<00:06, 4.47it/s]\n 42%|████▏ | 21/50 [00:04<00:06, 4.52it/s]\n 44%|████▍ | 22/50 [00:04<00:06, 4.53it/s]\n 46%|████▌ | 23/50 [00:05<00:06, 4.46it/s]\n 48%|████▊ | 24/50 [00:05<00:05, 4.44it/s]\n 50%|█████ | 25/50 [00:05<00:05, 4.47it/s]\n 52%|█████▏ | 26/50 [00:05<00:05, 4.48it/s]\n 54%|█████▍ | 27/50 [00:06<00:05, 4.47it/s]\n 56%|█████▌ | 28/50 [00:06<00:04, 4.42it/s]\n 58%|█████▊ | 29/50 [00:06<00:04, 4.40it/s]\n 60%|██████ | 30/50 [00:06<00:04, 4.43it/s]\n 62%|██████▏ | 31/50 [00:06<00:04, 4.43it/s]\n 64%|██████▍ | 32/50 [00:07<00:04, 4.44it/s]\n 66%|██████▌ | 33/50 [00:07<00:03, 4.41it/s]\n 68%|██████▊ | 34/50 [00:07<00:03, 4.39it/s]\n 70%|███████ | 35/50 [00:07<00:03, 4.40it/s]\n 72%|███████▏ | 36/50 [00:08<00:03, 4.40it/s]\n 74%|███████▍ | 37/50 [00:08<00:02, 4.35it/s]\n 76%|███████▌ | 38/50 [00:08<00:02, 4.37it/s]\n 78%|███████▊ | 39/50 [00:08<00:02, 4.39it/s]\n 80%|████████ | 40/50 [00:08<00:02, 4.36it/s]\n 82%|████████▏ | 41/50 [00:09<00:02, 4.35it/s]\n 84%|████████▍ | 42/50 [00:09<00:01, 4.34it/s]\n 86%|████████▌ | 43/50 [00:09<00:01, 4.37it/s]\n 88%|████████▊ | 44/50 [00:09<00:01, 4.38it/s]\n 90%|█████████ | 45/50 [00:10<00:01, 4.39it/s]\n 92%|█████████▏| 46/50 [00:10<00:00, 4.33it/s]\n 94%|█████████▍| 47/50 [00:10<00:00, 4.35it/s]\n 96%|█████████▌| 48/50 [00:10<00:00, 4.32it/s]\n 98%|█████████▊| 49/50 [00:11<00:00, 4.34it/s]\n100%|██████████| 50/50 [00:11<00:00, 4.30it/s]\n100%|██████████| 50/50 [00:11<00:00, 4.43it/s]", "metrics": { "predict_time": 12.450169, "total_time": 12.423013 }, "output": [ "https://replicate.delivery/pbxt/i5fvWQ2GcXQ5GqOWHRHyerK6AghIx3CfPRSNeQDlK9mAQHdEB/out-0.png" ], "started_at": "2023-06-18T20:37:08.962028Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/fms6m7jbqvdjpijbbkv2iiiqhm", "cancel": "https://api.replicate.com/v1/predictions/fms6m7jbqvdjpijbbkv2iiiqhm/cancel" }, "version": "e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8" }Generated inUsing seed: 41701 using txt2img 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:12, 3.90it/s] 4%|▍ | 2/50 [00:00<00:11, 4.36it/s] 6%|▌ | 3/50 [00:00<00:10, 4.58it/s] 8%|▊ | 4/50 [00:00<00:09, 4.66it/s] 10%|█ | 5/50 [00:01<00:10, 4.44it/s] 12%|█▏ | 6/50 [00:01<00:09, 4.48it/s] 14%|█▍ | 7/50 [00:01<00:09, 4.52it/s] 16%|█▌ | 8/50 [00:01<00:09, 4.56it/s] 18%|█▊ | 9/50 [00:01<00:08, 4.58it/s] 20%|██ | 10/50 [00:02<00:08, 4.45it/s] 22%|██▏ | 11/50 [00:02<00:08, 4.48it/s] 24%|██▍ | 12/50 [00:02<00:08, 4.54it/s] 26%|██▌ | 13/50 [00:02<00:08, 4.58it/s] 28%|██▊ | 14/50 [00:03<00:08, 4.48it/s] 30%|███ | 15/50 [00:03<00:07, 4.44it/s] 32%|███▏ | 16/50 [00:03<00:07, 4.47it/s] 34%|███▍ | 17/50 [00:03<00:07, 4.52it/s] 36%|███▌ | 18/50 [00:04<00:07, 4.50it/s] 38%|███▊ | 19/50 [00:04<00:06, 4.44it/s] 40%|████ | 20/50 [00:04<00:06, 4.47it/s] 42%|████▏ | 21/50 [00:04<00:06, 4.52it/s] 44%|████▍ | 22/50 [00:04<00:06, 4.53it/s] 46%|████▌ | 23/50 [00:05<00:06, 4.46it/s] 48%|████▊ | 24/50 [00:05<00:05, 4.44it/s] 50%|█████ | 25/50 [00:05<00:05, 4.47it/s] 52%|█████▏ | 26/50 [00:05<00:05, 4.48it/s] 54%|█████▍ | 27/50 [00:06<00:05, 4.47it/s] 56%|█████▌ | 28/50 [00:06<00:04, 4.42it/s] 58%|█████▊ | 29/50 [00:06<00:04, 4.40it/s] 60%|██████ | 30/50 [00:06<00:04, 4.43it/s] 62%|██████▏ | 31/50 [00:06<00:04, 4.43it/s] 64%|██████▍ | 32/50 [00:07<00:04, 4.44it/s] 66%|██████▌ | 33/50 [00:07<00:03, 4.41it/s] 68%|██████▊ | 34/50 [00:07<00:03, 4.39it/s] 70%|███████ | 35/50 [00:07<00:03, 4.40it/s] 72%|███████▏ | 36/50 [00:08<00:03, 4.40it/s] 74%|███████▍ | 37/50 [00:08<00:02, 4.35it/s] 76%|███████▌ | 38/50 [00:08<00:02, 4.37it/s] 78%|███████▊ | 39/50 [00:08<00:02, 4.39it/s] 80%|████████ | 40/50 [00:08<00:02, 4.36it/s] 82%|████████▏ | 41/50 [00:09<00:02, 4.35it/s] 84%|████████▍ | 42/50 [00:09<00:01, 4.34it/s] 86%|████████▌ | 43/50 [00:09<00:01, 4.37it/s] 88%|████████▊ | 44/50 [00:09<00:01, 4.38it/s] 90%|█████████ | 45/50 [00:10<00:01, 4.39it/s] 92%|█████████▏| 46/50 [00:10<00:00, 4.33it/s] 94%|█████████▍| 47/50 [00:10<00:00, 4.35it/s] 96%|█████████▌| 48/50 [00:10<00:00, 4.32it/s] 98%|█████████▊| 49/50 [00:11<00:00, 4.34it/s] 100%|██████████| 50/50 [00:11<00:00, 4.30it/s] 100%|██████████| 50/50 [00:11<00:00, 4.43it/s]Prediction
cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8IDanbsoerbpug7rzmfckh4awqc7uStatusSucceededSourceWebHardwareT4Total durationCreatedInput
- width
- 512
- height
- 512
- prompt
- a portrait of a qdg dog in a scenic environment by mary beale and rembrandt, royal, noble, baroque art, trending on artstation
- scheduler
- DDIM
- num_outputs
- 1
- guidance_scale
- 7.5
- negative_prompt
- cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 512, "height": 512, "prompt": "a portrait of a qdg dog in a scenic environment by mary beale and rembrandt, royal, noble, baroque art, trending on artstation", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", { input: { width: 512, height: 512, prompt: "a portrait of a qdg dog in a scenic environment by mary beale and rembrandt, royal, noble, baroque art, trending on artstation", scheduler: "DDIM", num_outputs: 1, guidance_scale: 7.5, negative_prompt: "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", prompt_strength: 0.8, num_inference_steps: 50 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", input={ "width": 512, "height": 512, "prompt": "a portrait of a qdg dog in a scenic environment by mary beale and rembrandt, royal, noble, baroque art, trending on artstation", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } ) # To access the file URL: print(output[0].url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output[0].read())To learn more, take a look at the guide on getting started with Python.
Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", "input": { "width": 512, "height": 512, "prompt": "a portrait of a qdg dog in a scenic environment by mary beale and rembrandt, royal, noble, baroque art, trending on artstation", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8 \ -i 'width=512' \ -i 'height=512' \ -i 'prompt="a portrait of a qdg dog in a scenic environment by mary beale and rembrandt, royal, noble, baroque art, trending on artstation"' \ -i 'scheduler="DDIM"' \ -i 'num_outputs=1' \ -i 'guidance_scale=7.5' \ -i 'negative_prompt="cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark"' \ -i 'prompt_strength=0.8' \ -i 'num_inference_steps=50'To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 512, "height": 512, "prompt": "a portrait of a qdg dog in a scenic environment by mary beale and rembrandt, royal, noble, baroque art, trending on artstation", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-06-18T20:39:54.476876Z", "created_at": "2023-06-18T20:39:42.814547Z", "data_removed": false, "error": null, "id": "anbsoerbpug7rzmfckh4awqc7u", "input": { "width": 512, "height": 512, "prompt": "a portrait of a qdg dog in a scenic environment by mary beale and rembrandt, royal, noble, baroque art, trending on artstation", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 40519\nusing txt2img\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:13, 3.69it/s]\n 4%|▍ | 2/50 [00:00<00:11, 4.36it/s]\n 6%|▌ | 3/50 [00:00<00:10, 4.59it/s]\n 8%|▊ | 4/50 [00:00<00:09, 4.69it/s]\n 10%|█ | 5/50 [00:01<00:09, 4.72it/s]\n 12%|█▏ | 6/50 [00:01<00:09, 4.58it/s]\n 14%|█▍ | 7/50 [00:01<00:09, 4.65it/s]\n 16%|█▌ | 8/50 [00:01<00:08, 4.73it/s]\n 18%|█▊ | 9/50 [00:01<00:08, 4.79it/s]\n 20%|██ | 10/50 [00:02<00:08, 4.76it/s]\n 22%|██▏ | 11/50 [00:02<00:08, 4.71it/s]\n 24%|██▍ | 12/50 [00:02<00:08, 4.73it/s]\n 26%|██▌ | 13/50 [00:02<00:07, 4.74it/s]\n 28%|██▊ | 14/50 [00:02<00:07, 4.78it/s]\n 30%|███ | 15/50 [00:03<00:07, 4.74it/s]\n 32%|███▏ | 16/50 [00:03<00:07, 4.71it/s]\n 34%|███▍ | 17/50 [00:03<00:06, 4.78it/s]\n 36%|███▌ | 18/50 [00:03<00:06, 4.83it/s]\n 38%|███▊ | 19/50 [00:04<00:06, 4.87it/s]\n 40%|████ | 20/50 [00:04<00:06, 4.80it/s]\n 42%|████▏ | 21/50 [00:04<00:06, 4.77it/s]\n 44%|████▍ | 22/50 [00:04<00:05, 4.75it/s]\n 46%|████▌ | 23/50 [00:04<00:05, 4.78it/s]\n 48%|████▊ | 24/50 [00:05<00:05, 4.80it/s]\n 50%|█████ | 25/50 [00:05<00:05, 4.74it/s]\n 52%|█████▏ | 26/50 [00:05<00:05, 4.77it/s]\n 54%|█████▍ | 27/50 [00:05<00:04, 4.82it/s]\n 56%|█████▌ | 28/50 [00:05<00:04, 4.83it/s]\n 58%|█████▊ | 29/50 [00:06<00:04, 4.81it/s]\n 60%|██████ | 30/50 [00:06<00:04, 4.76it/s]\n 62%|██████▏ | 31/50 [00:06<00:04, 4.71it/s]\n 64%|██████▍ | 32/50 [00:06<00:03, 4.76it/s]\n 66%|██████▌ | 33/50 [00:06<00:03, 4.80it/s]\n 68%|██████▊ | 34/50 [00:07<00:03, 4.79it/s]\n 70%|███████ | 35/50 [00:07<00:03, 4.76it/s]\n 72%|███████▏ | 36/50 [00:07<00:02, 4.70it/s]\n 74%|███████▍ | 37/50 [00:07<00:02, 4.75it/s]\n 76%|███████▌ | 38/50 [00:08<00:02, 4.79it/s]\n 78%|███████▊ | 39/50 [00:08<00:02, 4.75it/s]\n 80%|████████ | 40/50 [00:08<00:02, 4.75it/s]\n 82%|████████▏ | 41/50 [00:08<00:01, 4.70it/s]\n 84%|████████▍ | 42/50 [00:08<00:01, 4.74it/s]\n 86%|████████▌ | 43/50 [00:09<00:01, 4.77it/s]\n 88%|████████▊ | 44/50 [00:09<00:01, 4.71it/s]\n 90%|█████████ | 45/50 [00:09<00:01, 4.67it/s]\n 92%|█████████▏| 46/50 [00:09<00:00, 4.70it/s]\n 94%|█████████▍| 47/50 [00:09<00:00, 4.67it/s]\n 96%|█████████▌| 48/50 [00:10<00:00, 4.70it/s]\n 98%|█████████▊| 49/50 [00:10<00:00, 4.67it/s]\n100%|██████████| 50/50 [00:10<00:00, 4.64it/s]\n100%|██████████| 50/50 [00:10<00:00, 4.72it/s]", "metrics": { "predict_time": 11.694345, "total_time": 11.662329 }, "output": [ "https://replicate.delivery/pbxt/xNF6twavFrY8JJWuIFuUWZPSfoWbwJeerfzexFH76rdOzO6IC/out-0.png" ], "started_at": "2023-06-18T20:39:42.782531Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/anbsoerbpug7rzmfckh4awqc7u", "cancel": "https://api.replicate.com/v1/predictions/anbsoerbpug7rzmfckh4awqc7u/cancel" }, "version": "e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8" }Generated inUsing seed: 40519 using txt2img 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:13, 3.69it/s] 4%|▍ | 2/50 [00:00<00:11, 4.36it/s] 6%|▌ | 3/50 [00:00<00:10, 4.59it/s] 8%|▊ | 4/50 [00:00<00:09, 4.69it/s] 10%|█ | 5/50 [00:01<00:09, 4.72it/s] 12%|█▏ | 6/50 [00:01<00:09, 4.58it/s] 14%|█▍ | 7/50 [00:01<00:09, 4.65it/s] 16%|█▌ | 8/50 [00:01<00:08, 4.73it/s] 18%|█▊ | 9/50 [00:01<00:08, 4.79it/s] 20%|██ | 10/50 [00:02<00:08, 4.76it/s] 22%|██▏ | 11/50 [00:02<00:08, 4.71it/s] 24%|██▍ | 12/50 [00:02<00:08, 4.73it/s] 26%|██▌ | 13/50 [00:02<00:07, 4.74it/s] 28%|██▊ | 14/50 [00:02<00:07, 4.78it/s] 30%|███ | 15/50 [00:03<00:07, 4.74it/s] 32%|███▏ | 16/50 [00:03<00:07, 4.71it/s] 34%|███▍ | 17/50 [00:03<00:06, 4.78it/s] 36%|███▌ | 18/50 [00:03<00:06, 4.83it/s] 38%|███▊ | 19/50 [00:04<00:06, 4.87it/s] 40%|████ | 20/50 [00:04<00:06, 4.80it/s] 42%|████▏ | 21/50 [00:04<00:06, 4.77it/s] 44%|████▍ | 22/50 [00:04<00:05, 4.75it/s] 46%|████▌ | 23/50 [00:04<00:05, 4.78it/s] 48%|████▊ | 24/50 [00:05<00:05, 4.80it/s] 50%|█████ | 25/50 [00:05<00:05, 4.74it/s] 52%|█████▏ | 26/50 [00:05<00:05, 4.77it/s] 54%|█████▍ | 27/50 [00:05<00:04, 4.82it/s] 56%|█████▌ | 28/50 [00:05<00:04, 4.83it/s] 58%|█████▊ | 29/50 [00:06<00:04, 4.81it/s] 60%|██████ | 30/50 [00:06<00:04, 4.76it/s] 62%|██████▏ | 31/50 [00:06<00:04, 4.71it/s] 64%|██████▍ | 32/50 [00:06<00:03, 4.76it/s] 66%|██████▌ | 33/50 [00:06<00:03, 4.80it/s] 68%|██████▊ | 34/50 [00:07<00:03, 4.79it/s] 70%|███████ | 35/50 [00:07<00:03, 4.76it/s] 72%|███████▏ | 36/50 [00:07<00:02, 4.70it/s] 74%|███████▍ | 37/50 [00:07<00:02, 4.75it/s] 76%|███████▌ | 38/50 [00:08<00:02, 4.79it/s] 78%|███████▊ | 39/50 [00:08<00:02, 4.75it/s] 80%|████████ | 40/50 [00:08<00:02, 4.75it/s] 82%|████████▏ | 41/50 [00:08<00:01, 4.70it/s] 84%|████████▍ | 42/50 [00:08<00:01, 4.74it/s] 86%|████████▌ | 43/50 [00:09<00:01, 4.77it/s] 88%|████████▊ | 44/50 [00:09<00:01, 4.71it/s] 90%|█████████ | 45/50 [00:09<00:01, 4.67it/s] 92%|█████████▏| 46/50 [00:09<00:00, 4.70it/s] 94%|█████████▍| 47/50 [00:09<00:00, 4.67it/s] 96%|█████████▌| 48/50 [00:10<00:00, 4.70it/s] 98%|█████████▊| 49/50 [00:10<00:00, 4.67it/s] 100%|██████████| 50/50 [00:10<00:00, 4.64it/s] 100%|██████████| 50/50 [00:10<00:00, 4.72it/s]Prediction
cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8ID56krg4jbcjncp6vyvzekedpe2qStatusSucceededSourceWebHardwareT4Total durationCreatedInput
- width
- 512
- height
- 512
- prompt
- a portrait of a qdg dog in a scenic environment by mary beale and rembrandt, royal, noble, baroque art, trending on artstation
- scheduler
- DDIM
- num_outputs
- 1
- guidance_scale
- 7.5
- negative_prompt
- cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 512, "height": 512, "prompt": "a portrait of a qdg dog in a scenic environment by mary beale and rembrandt, royal, noble, baroque art, trending on artstation", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", { input: { width: 512, height: 512, prompt: "a portrait of a qdg dog in a scenic environment by mary beale and rembrandt, royal, noble, baroque art, trending on artstation", scheduler: "DDIM", num_outputs: 1, guidance_scale: 7.5, negative_prompt: "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", prompt_strength: 0.8, num_inference_steps: 50 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", input={ "width": 512, "height": 512, "prompt": "a portrait of a qdg dog in a scenic environment by mary beale and rembrandt, royal, noble, baroque art, trending on artstation", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } ) # To access the file URL: print(output[0].url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output[0].read())To learn more, take a look at the guide on getting started with Python.
Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", "input": { "width": 512, "height": 512, "prompt": "a portrait of a qdg dog in a scenic environment by mary beale and rembrandt, royal, noble, baroque art, trending on artstation", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8 \ -i 'width=512' \ -i 'height=512' \ -i 'prompt="a portrait of a qdg dog in a scenic environment by mary beale and rembrandt, royal, noble, baroque art, trending on artstation"' \ -i 'scheduler="DDIM"' \ -i 'num_outputs=1' \ -i 'guidance_scale=7.5' \ -i 'negative_prompt="cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark"' \ -i 'prompt_strength=0.8' \ -i 'num_inference_steps=50'To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 512, "height": 512, "prompt": "a portrait of a qdg dog in a scenic environment by mary beale and rembrandt, royal, noble, baroque art, trending on artstation", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-06-18T20:40:36.229569Z", "created_at": "2023-06-18T20:40:24.004528Z", "data_removed": false, "error": null, "id": "56krg4jbcjncp6vyvzekedpe2q", "input": { "width": 512, "height": 512, "prompt": "a portrait of a qdg dog in a scenic environment by mary beale and rembrandt, royal, noble, baroque art, trending on artstation", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 14736\nusing txt2img\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:13, 3.74it/s]\n 4%|▍ | 2/50 [00:00<00:11, 4.24it/s]\n 6%|▌ | 3/50 [00:00<00:10, 4.51it/s]\n 8%|▊ | 4/50 [00:00<00:09, 4.65it/s]\n 10%|█ | 5/50 [00:01<00:09, 4.56it/s]\n 12%|█▏ | 6/50 [00:01<00:09, 4.45it/s]\n 14%|█▍ | 7/50 [00:01<00:09, 4.53it/s]\n 16%|█▌ | 8/50 [00:01<00:09, 4.58it/s]\n 18%|█▊ | 9/50 [00:01<00:08, 4.59it/s]\n 20%|██ | 10/50 [00:02<00:08, 4.49it/s]\n 22%|██▏ | 11/50 [00:02<00:08, 4.44it/s]\n 24%|██▍ | 12/50 [00:02<00:08, 4.53it/s]\n 26%|██▌ | 13/50 [00:02<00:08, 4.55it/s]\n 28%|██▊ | 14/50 [00:03<00:08, 4.50it/s]\n 30%|███ | 15/50 [00:03<00:07, 4.43it/s]\n 32%|███▏ | 16/50 [00:03<00:07, 4.47it/s]\n 34%|███▍ | 17/50 [00:03<00:07, 4.54it/s]\n 36%|███▌ | 18/50 [00:04<00:07, 4.55it/s]\n 38%|███▊ | 19/50 [00:04<00:06, 4.49it/s]\n 40%|████ | 20/50 [00:04<00:06, 4.47it/s]\n 42%|████▏ | 21/50 [00:04<00:06, 4.49it/s]\n 44%|████▍ | 22/50 [00:04<00:06, 4.49it/s]\n 46%|████▌ | 23/50 [00:05<00:06, 4.44it/s]\n 48%|████▊ | 24/50 [00:05<00:05, 4.41it/s]\n 50%|█████ | 25/50 [00:05<00:05, 4.44it/s]\n 52%|█████▏ | 26/50 [00:05<00:05, 4.47it/s]\n 54%|█████▍ | 27/50 [00:06<00:05, 4.47it/s]\n 56%|█████▌ | 28/50 [00:06<00:04, 4.45it/s]\n 58%|█████▊ | 29/50 [00:06<00:04, 4.44it/s]\n 60%|██████ | 30/50 [00:06<00:04, 4.42it/s]\n 62%|██████▏ | 31/50 [00:06<00:04, 4.46it/s]\n 64%|██████▍ | 32/50 [00:07<00:04, 4.44it/s]\n 66%|██████▌ | 33/50 [00:07<00:03, 4.42it/s]\n 68%|██████▊ | 34/50 [00:07<00:03, 4.41it/s]\n 70%|███████ | 35/50 [00:07<00:03, 4.40it/s]\n 72%|███████▏ | 36/50 [00:08<00:03, 4.44it/s]\n 74%|███████▍ | 37/50 [00:08<00:02, 4.41it/s]\n 76%|███████▌ | 38/50 [00:08<00:02, 4.44it/s]\n 78%|███████▊ | 39/50 [00:08<00:02, 4.48it/s]\n 80%|████████ | 40/50 [00:08<00:02, 4.47it/s]\n 82%|████████▏ | 41/50 [00:09<00:02, 4.46it/s]\n 84%|████████▍ | 42/50 [00:09<00:01, 4.47it/s]\n 86%|████████▌ | 43/50 [00:09<00:01, 4.48it/s]\n 88%|████████▊ | 44/50 [00:09<00:01, 4.52it/s]\n 90%|█████████ | 45/50 [00:10<00:01, 4.47it/s]\n 92%|█████████▏| 46/50 [00:10<00:00, 4.46it/s]\n 94%|█████████▍| 47/50 [00:10<00:00, 4.47it/s]\n 96%|█████████▌| 48/50 [00:10<00:00, 4.49it/s]\n 98%|█████████▊| 49/50 [00:10<00:00, 4.48it/s]\n100%|██████████| 50/50 [00:11<00:00, 4.48it/s]\n100%|██████████| 50/50 [00:11<00:00, 4.47it/s]", "metrics": { "predict_time": 12.325575, "total_time": 12.225041 }, "output": [ "https://replicate.delivery/pbxt/vuN84Gq1VC49GBfATedtj6YNwiVqQVRtXZfxQLU7c8lGujOiA/out-0.png" ], "started_at": "2023-06-18T20:40:23.903994Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/56krg4jbcjncp6vyvzekedpe2q", "cancel": "https://api.replicate.com/v1/predictions/56krg4jbcjncp6vyvzekedpe2q/cancel" }, "version": "e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8" }Generated inUsing seed: 14736 using txt2img 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:13, 3.74it/s] 4%|▍ | 2/50 [00:00<00:11, 4.24it/s] 6%|▌ | 3/50 [00:00<00:10, 4.51it/s] 8%|▊ | 4/50 [00:00<00:09, 4.65it/s] 10%|█ | 5/50 [00:01<00:09, 4.56it/s] 12%|█▏ | 6/50 [00:01<00:09, 4.45it/s] 14%|█▍ | 7/50 [00:01<00:09, 4.53it/s] 16%|█▌ | 8/50 [00:01<00:09, 4.58it/s] 18%|█▊ | 9/50 [00:01<00:08, 4.59it/s] 20%|██ | 10/50 [00:02<00:08, 4.49it/s] 22%|██▏ | 11/50 [00:02<00:08, 4.44it/s] 24%|██▍ | 12/50 [00:02<00:08, 4.53it/s] 26%|██▌ | 13/50 [00:02<00:08, 4.55it/s] 28%|██▊ | 14/50 [00:03<00:08, 4.50it/s] 30%|███ | 15/50 [00:03<00:07, 4.43it/s] 32%|███▏ | 16/50 [00:03<00:07, 4.47it/s] 34%|███▍ | 17/50 [00:03<00:07, 4.54it/s] 36%|███▌ | 18/50 [00:04<00:07, 4.55it/s] 38%|███▊ | 19/50 [00:04<00:06, 4.49it/s] 40%|████ | 20/50 [00:04<00:06, 4.47it/s] 42%|████▏ | 21/50 [00:04<00:06, 4.49it/s] 44%|████▍ | 22/50 [00:04<00:06, 4.49it/s] 46%|████▌ | 23/50 [00:05<00:06, 4.44it/s] 48%|████▊ | 24/50 [00:05<00:05, 4.41it/s] 50%|█████ | 25/50 [00:05<00:05, 4.44it/s] 52%|█████▏ | 26/50 [00:05<00:05, 4.47it/s] 54%|█████▍ | 27/50 [00:06<00:05, 4.47it/s] 56%|█████▌ | 28/50 [00:06<00:04, 4.45it/s] 58%|█████▊ | 29/50 [00:06<00:04, 4.44it/s] 60%|██████ | 30/50 [00:06<00:04, 4.42it/s] 62%|██████▏ | 31/50 [00:06<00:04, 4.46it/s] 64%|██████▍ | 32/50 [00:07<00:04, 4.44it/s] 66%|██████▌ | 33/50 [00:07<00:03, 4.42it/s] 68%|██████▊ | 34/50 [00:07<00:03, 4.41it/s] 70%|███████ | 35/50 [00:07<00:03, 4.40it/s] 72%|███████▏ | 36/50 [00:08<00:03, 4.44it/s] 74%|███████▍ | 37/50 [00:08<00:02, 4.41it/s] 76%|███████▌ | 38/50 [00:08<00:02, 4.44it/s] 78%|███████▊ | 39/50 [00:08<00:02, 4.48it/s] 80%|████████ | 40/50 [00:08<00:02, 4.47it/s] 82%|████████▏ | 41/50 [00:09<00:02, 4.46it/s] 84%|████████▍ | 42/50 [00:09<00:01, 4.47it/s] 86%|████████▌ | 43/50 [00:09<00:01, 4.48it/s] 88%|████████▊ | 44/50 [00:09<00:01, 4.52it/s] 90%|█████████ | 45/50 [00:10<00:01, 4.47it/s] 92%|█████████▏| 46/50 [00:10<00:00, 4.46it/s] 94%|█████████▍| 47/50 [00:10<00:00, 4.47it/s] 96%|█████████▌| 48/50 [00:10<00:00, 4.49it/s] 98%|█████████▊| 49/50 [00:10<00:00, 4.48it/s] 100%|██████████| 50/50 [00:11<00:00, 4.48it/s] 100%|██████████| 50/50 [00:11<00:00, 4.47it/s]Prediction
cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8IDn5mmdzrbqokttkq5r6dsoml5vuStatusSucceededSourceWebHardwareT4Total durationCreatedInput
- width
- 512
- height
- 512
- prompt
- a portrait of a qdg dog in a scenic environment by mary beale and rembrandt, royal, noble, baroque art, trending on artstation
- scheduler
- DDIM
- num_outputs
- 1
- guidance_scale
- 7.5
- negative_prompt
- cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 512, "height": 512, "prompt": "a portrait of a qdg dog in a scenic environment by mary beale and rembrandt, royal, noble, baroque art, trending on artstation", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", { input: { width: 512, height: 512, prompt: "a portrait of a qdg dog in a scenic environment by mary beale and rembrandt, royal, noble, baroque art, trending on artstation", scheduler: "DDIM", num_outputs: 1, guidance_scale: 7.5, negative_prompt: "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", prompt_strength: 0.8, num_inference_steps: 50 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", input={ "width": 512, "height": 512, "prompt": "a portrait of a qdg dog in a scenic environment by mary beale and rembrandt, royal, noble, baroque art, trending on artstation", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } ) # To access the file URL: print(output[0].url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output[0].read())To learn more, take a look at the guide on getting started with Python.
Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", "input": { "width": 512, "height": 512, "prompt": "a portrait of a qdg dog in a scenic environment by mary beale and rembrandt, royal, noble, baroque art, trending on artstation", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8 \ -i 'width=512' \ -i 'height=512' \ -i 'prompt="a portrait of a qdg dog in a scenic environment by mary beale and rembrandt, royal, noble, baroque art, trending on artstation"' \ -i 'scheduler="DDIM"' \ -i 'num_outputs=1' \ -i 'guidance_scale=7.5' \ -i 'negative_prompt="cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark"' \ -i 'prompt_strength=0.8' \ -i 'num_inference_steps=50'To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 512, "height": 512, "prompt": "a portrait of a qdg dog in a scenic environment by mary beale and rembrandt, royal, noble, baroque art, trending on artstation", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-06-18T20:42:01.708585Z", "created_at": "2023-06-18T20:41:50.046235Z", "data_removed": false, "error": null, "id": "n5mmdzrbqokttkq5r6dsoml5vu", "input": { "width": 512, "height": 512, "prompt": "a portrait of a qdg dog in a scenic environment by mary beale and rembrandt, royal, noble, baroque art, trending on artstation", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 23524\nusing txt2img\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:12, 4.06it/s]\n 4%|▍ | 2/50 [00:00<00:10, 4.59it/s]\n 6%|▌ | 3/50 [00:00<00:09, 4.71it/s]\n 8%|▊ | 4/50 [00:00<00:09, 4.80it/s]\n 10%|█ | 5/50 [00:01<00:09, 4.74it/s]\n 12%|█▏ | 6/50 [00:01<00:09, 4.67it/s]\n 14%|█▍ | 7/50 [00:01<00:09, 4.75it/s]\n 16%|█▌ | 8/50 [00:01<00:08, 4.81it/s]\n 18%|█▊ | 9/50 [00:01<00:08, 4.83it/s]\n 20%|██ | 10/50 [00:02<00:08, 4.71it/s]\n 22%|██▏ | 11/50 [00:02<00:08, 4.70it/s]\n 24%|██▍ | 12/50 [00:02<00:07, 4.79it/s]\n 26%|██▌ | 13/50 [00:02<00:07, 4.85it/s]\n 28%|██▊ | 14/50 [00:02<00:07, 4.86it/s]\n 30%|███ | 15/50 [00:03<00:07, 4.82it/s]\n 32%|███▏ | 16/50 [00:03<00:07, 4.77it/s]\n 34%|███▍ | 17/50 [00:03<00:06, 4.81it/s]\n 36%|███▌ | 18/50 [00:03<00:06, 4.87it/s]\n 38%|███▊ | 19/50 [00:03<00:06, 4.86it/s]\n 40%|████ | 20/50 [00:04<00:06, 4.80it/s]\n 42%|████▏ | 21/50 [00:04<00:06, 4.76it/s]\n 44%|████▍ | 22/50 [00:04<00:05, 4.76it/s]\n 46%|████▌ | 23/50 [00:04<00:05, 4.76it/s]\n 48%|████▊ | 24/50 [00:05<00:05, 4.79it/s]\n 50%|█████ | 25/50 [00:05<00:05, 4.76it/s]\n 52%|█████▏ | 26/50 [00:05<00:05, 4.75it/s]\n 54%|█████▍ | 27/50 [00:05<00:04, 4.81it/s]\n 56%|█████▌ | 28/50 [00:05<00:04, 4.83it/s]\n 58%|█████▊ | 29/50 [00:06<00:04, 4.77it/s]\n 60%|██████ | 30/50 [00:06<00:04, 4.77it/s]\n 62%|██████▏ | 31/50 [00:06<00:04, 4.72it/s]\n 64%|██████▍ | 32/50 [00:06<00:03, 4.77it/s]\n 66%|██████▌ | 33/50 [00:06<00:03, 4.82it/s]\n 68%|██████▊ | 34/50 [00:07<00:03, 4.77it/s]\n 70%|███████ | 35/50 [00:07<00:03, 4.75it/s]\n 72%|███████▏ | 36/50 [00:07<00:02, 4.73it/s]\n 74%|███████▍ | 37/50 [00:07<00:02, 4.74it/s]\n 76%|███████▌ | 38/50 [00:07<00:02, 4.74it/s]\n 78%|███████▊ | 39/50 [00:08<00:02, 4.70it/s]\n 80%|████████ | 40/50 [00:08<00:02, 4.66it/s]\n 82%|████████▏ | 41/50 [00:08<00:01, 4.70it/s]\n 84%|████████▍ | 42/50 [00:08<00:01, 4.67it/s]\n 86%|████████▌ | 43/50 [00:09<00:01, 4.70it/s]\n 88%|████████▊ | 44/50 [00:09<00:01, 4.65it/s]\n 90%|█████████ | 45/50 [00:09<00:01, 4.62it/s]\n 92%|█████████▏| 46/50 [00:09<00:00, 4.70it/s]\n 94%|█████████▍| 47/50 [00:09<00:00, 4.66it/s]\n 96%|█████████▌| 48/50 [00:10<00:00, 4.68it/s]\n 98%|█████████▊| 49/50 [00:10<00:00, 4.63it/s]\n100%|██████████| 50/50 [00:10<00:00, 4.63it/s]\n100%|██████████| 50/50 [00:10<00:00, 4.74it/s]", "metrics": { "predict_time": 11.699999, "total_time": 11.66235 }, "output": [ "https://replicate.delivery/pbxt/fEfRAU8uIUnIkkhPe5rN9HZfzvQ0N5IkPJS60Q8taejMDP6IC/out-0.png" ], "started_at": "2023-06-18T20:41:50.008586Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/n5mmdzrbqokttkq5r6dsoml5vu", "cancel": "https://api.replicate.com/v1/predictions/n5mmdzrbqokttkq5r6dsoml5vu/cancel" }, "version": "e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8" }Generated inUsing seed: 23524 using txt2img 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:12, 4.06it/s] 4%|▍ | 2/50 [00:00<00:10, 4.59it/s] 6%|▌ | 3/50 [00:00<00:09, 4.71it/s] 8%|▊ | 4/50 [00:00<00:09, 4.80it/s] 10%|█ | 5/50 [00:01<00:09, 4.74it/s] 12%|█▏ | 6/50 [00:01<00:09, 4.67it/s] 14%|█▍ | 7/50 [00:01<00:09, 4.75it/s] 16%|█▌ | 8/50 [00:01<00:08, 4.81it/s] 18%|█▊ | 9/50 [00:01<00:08, 4.83it/s] 20%|██ | 10/50 [00:02<00:08, 4.71it/s] 22%|██▏ | 11/50 [00:02<00:08, 4.70it/s] 24%|██▍ | 12/50 [00:02<00:07, 4.79it/s] 26%|██▌ | 13/50 [00:02<00:07, 4.85it/s] 28%|██▊ | 14/50 [00:02<00:07, 4.86it/s] 30%|███ | 15/50 [00:03<00:07, 4.82it/s] 32%|███▏ | 16/50 [00:03<00:07, 4.77it/s] 34%|███▍ | 17/50 [00:03<00:06, 4.81it/s] 36%|███▌ | 18/50 [00:03<00:06, 4.87it/s] 38%|███▊ | 19/50 [00:03<00:06, 4.86it/s] 40%|████ | 20/50 [00:04<00:06, 4.80it/s] 42%|████▏ | 21/50 [00:04<00:06, 4.76it/s] 44%|████▍ | 22/50 [00:04<00:05, 4.76it/s] 46%|████▌ | 23/50 [00:04<00:05, 4.76it/s] 48%|████▊ | 24/50 [00:05<00:05, 4.79it/s] 50%|█████ | 25/50 [00:05<00:05, 4.76it/s] 52%|█████▏ | 26/50 [00:05<00:05, 4.75it/s] 54%|█████▍ | 27/50 [00:05<00:04, 4.81it/s] 56%|█████▌ | 28/50 [00:05<00:04, 4.83it/s] 58%|█████▊ | 29/50 [00:06<00:04, 4.77it/s] 60%|██████ | 30/50 [00:06<00:04, 4.77it/s] 62%|██████▏ | 31/50 [00:06<00:04, 4.72it/s] 64%|██████▍ | 32/50 [00:06<00:03, 4.77it/s] 66%|██████▌ | 33/50 [00:06<00:03, 4.82it/s] 68%|██████▊ | 34/50 [00:07<00:03, 4.77it/s] 70%|███████ | 35/50 [00:07<00:03, 4.75it/s] 72%|███████▏ | 36/50 [00:07<00:02, 4.73it/s] 74%|███████▍ | 37/50 [00:07<00:02, 4.74it/s] 76%|███████▌ | 38/50 [00:07<00:02, 4.74it/s] 78%|███████▊ | 39/50 [00:08<00:02, 4.70it/s] 80%|████████ | 40/50 [00:08<00:02, 4.66it/s] 82%|████████▏ | 41/50 [00:08<00:01, 4.70it/s] 84%|████████▍ | 42/50 [00:08<00:01, 4.67it/s] 86%|████████▌ | 43/50 [00:09<00:01, 4.70it/s] 88%|████████▊ | 44/50 [00:09<00:01, 4.65it/s] 90%|█████████ | 45/50 [00:09<00:01, 4.62it/s] 92%|█████████▏| 46/50 [00:09<00:00, 4.70it/s] 94%|█████████▍| 47/50 [00:09<00:00, 4.66it/s] 96%|█████████▌| 48/50 [00:10<00:00, 4.68it/s] 98%|█████████▊| 49/50 [00:10<00:00, 4.63it/s] 100%|██████████| 50/50 [00:10<00:00, 4.63it/s] 100%|██████████| 50/50 [00:10<00:00, 4.74it/s]Prediction
cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8IDy6a4aczbyuqvbxoh7wkhwcjvmaStatusSucceededSourceWebHardwareT4Total durationCreatedInput
- width
- 512
- height
- 512
- prompt
- a painted portrait of a qdg dog with brown fur, no white fur, wearing a sea captain's uniform and hat, sea in background, oil painting by thomas gainsborough, elegant, highly detailed, anthro, anthropomorphic dog, epic fantasy art, trending on artstation, photorealistic, photoshop, behance winner
- scheduler
- DDIM
- num_outputs
- 1
- guidance_scale
- 7.5
- negative_prompt
- cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 512, "height": 512, "prompt": "a painted portrait of a qdg dog with brown fur, no white fur, wearing a sea captain's uniform and hat, sea in background, oil painting by thomas gainsborough, elegant, highly detailed, anthro, anthropomorphic dog, epic fantasy art, trending on artstation, photorealistic, photoshop, behance winner", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", { input: { width: 512, height: 512, prompt: "a painted portrait of a qdg dog with brown fur, no white fur, wearing a sea captain's uniform and hat, sea in background, oil painting by thomas gainsborough, elegant, highly detailed, anthro, anthropomorphic dog, epic fantasy art, trending on artstation, photorealistic, photoshop, behance winner", scheduler: "DDIM", num_outputs: 1, guidance_scale: 7.5, negative_prompt: "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", prompt_strength: 0.8, num_inference_steps: 50 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", input={ "width": 512, "height": 512, "prompt": "a painted portrait of a qdg dog with brown fur, no white fur, wearing a sea captain's uniform and hat, sea in background, oil painting by thomas gainsborough, elegant, highly detailed, anthro, anthropomorphic dog, epic fantasy art, trending on artstation, photorealistic, photoshop, behance winner", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } ) # To access the file URL: print(output[0].url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output[0].read())To learn more, take a look at the guide on getting started with Python.
Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", "input": { "width": 512, "height": 512, "prompt": "a painted portrait of a qdg dog with brown fur, no white fur, wearing a sea captain\'s uniform and hat, sea in background, oil painting by thomas gainsborough, elegant, highly detailed, anthro, anthropomorphic dog, epic fantasy art, trending on artstation, photorealistic, photoshop, behance winner", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8 \ -i 'width=512' \ -i 'height=512' \ -i $'prompt="a painted portrait of a qdg dog with brown fur, no white fur, wearing a sea captain\'s uniform and hat, sea in background, oil painting by thomas gainsborough, elegant, highly detailed, anthro, anthropomorphic dog, epic fantasy art, trending on artstation, photorealistic, photoshop, behance winner"' \ -i 'scheduler="DDIM"' \ -i 'num_outputs=1' \ -i 'guidance_scale=7.5' \ -i 'negative_prompt="cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark"' \ -i 'prompt_strength=0.8' \ -i 'num_inference_steps=50'To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 512, "height": 512, "prompt": "a painted portrait of a qdg dog with brown fur, no white fur, wearing a sea captain\'s uniform and hat, sea in background, oil painting by thomas gainsborough, elegant, highly detailed, anthro, anthropomorphic dog, epic fantasy art, trending on artstation, photorealistic, photoshop, behance winner", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-06-18T20:42:54.969556Z", "created_at": "2023-06-18T20:42:42.449939Z", "data_removed": false, "error": null, "id": "y6a4aczbyuqvbxoh7wkhwcjvma", "input": { "width": 512, "height": 512, "prompt": "a painted portrait of a qdg dog with brown fur, no white fur, wearing a sea captain's uniform and hat, sea in background, oil painting by thomas gainsborough, elegant, highly detailed, anthro, anthropomorphic dog, epic fantasy art, trending on artstation, photorealistic, photoshop, behance winner", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 44937\nusing txt2img\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:11, 4.15it/s]\n 4%|▍ | 2/50 [00:00<00:10, 4.39it/s]\n 6%|▌ | 3/50 [00:00<00:10, 4.48it/s]\n 8%|▊ | 4/50 [00:00<00:10, 4.50it/s]\n 10%|█ | 5/50 [00:01<00:10, 4.26it/s]\n 12%|█▏ | 6/50 [00:01<00:10, 4.31it/s]\n 14%|█▍ | 7/50 [00:01<00:09, 4.37it/s]\n 16%|█▌ | 8/50 [00:01<00:09, 4.40it/s]\n 18%|█▊ | 9/50 [00:02<00:09, 4.33it/s]\n 20%|██ | 10/50 [00:02<00:09, 4.34it/s]\n 22%|██▏ | 11/50 [00:02<00:08, 4.37it/s]\n 24%|██▍ | 12/50 [00:02<00:08, 4.39it/s]\n 26%|██▌ | 13/50 [00:02<00:08, 4.36it/s]\n 28%|██▊ | 14/50 [00:03<00:08, 4.31it/s]\n 30%|███ | 15/50 [00:03<00:08, 4.35it/s]\n 32%|███▏ | 16/50 [00:03<00:07, 4.38it/s]\n 34%|███▍ | 17/50 [00:03<00:07, 4.39it/s]\n 36%|███▌ | 18/50 [00:04<00:07, 4.31it/s]\n 38%|███▊ | 19/50 [00:04<00:07, 4.34it/s]\n 40%|████ | 20/50 [00:04<00:06, 4.36it/s]\n 42%|████▏ | 21/50 [00:04<00:06, 4.37it/s]\n 44%|████▍ | 22/50 [00:05<00:06, 4.35it/s]\n 46%|████▌ | 23/50 [00:05<00:06, 4.31it/s]\n 48%|████▊ | 24/50 [00:05<00:05, 4.36it/s]\n 50%|█████ | 25/50 [00:05<00:05, 4.39it/s]\n 52%|█████▏ | 26/50 [00:05<00:05, 4.39it/s]\n 54%|█████▍ | 27/50 [00:06<00:05, 4.33it/s]\n 56%|█████▌ | 28/50 [00:06<00:05, 4.36it/s]\n 58%|█████▊ | 29/50 [00:06<00:04, 4.39it/s]\n 60%|██████ | 30/50 [00:06<00:04, 4.39it/s]\n 62%|██████▏ | 31/50 [00:07<00:04, 4.36it/s]\n 64%|██████▍ | 32/50 [00:07<00:04, 4.33it/s]\n 66%|██████▌ | 33/50 [00:07<00:03, 4.37it/s]\n 68%|██████▊ | 34/50 [00:07<00:03, 4.39it/s]\n 70%|███████ | 35/50 [00:08<00:03, 4.40it/s]\n 72%|███████▏ | 36/50 [00:08<00:03, 4.40it/s]\n 74%|███████▍ | 37/50 [00:08<00:02, 4.41it/s]\n 76%|███████▌ | 38/50 [00:08<00:02, 4.40it/s]\n 78%|███████▊ | 39/50 [00:08<00:02, 4.41it/s]\n 80%|████████ | 40/50 [00:09<00:02, 4.42it/s]\n 82%|████████▏ | 41/50 [00:09<00:02, 4.45it/s]\n 84%|████████▍ | 42/50 [00:09<00:01, 4.47it/s]\n 86%|████████▌ | 43/50 [00:09<00:01, 4.48it/s]\n 88%|████████▊ | 44/50 [00:10<00:01, 4.46it/s]\n 90%|█████████ | 45/50 [00:10<00:01, 4.47it/s]\n 92%|█████████▏| 46/50 [00:10<00:00, 4.48it/s]\n 94%|█████████▍| 47/50 [00:10<00:00, 4.48it/s]\n 96%|█████████▌| 48/50 [00:10<00:00, 4.48it/s]\n 98%|█████████▊| 49/50 [00:11<00:00, 4.46it/s]\n100%|██████████| 50/50 [00:11<00:00, 4.46it/s]\n100%|██████████| 50/50 [00:11<00:00, 4.39it/s]", "metrics": { "predict_time": 12.554198, "total_time": 12.519617 }, "output": [ "https://replicate.delivery/pbxt/AFgSRd48rA6BGBBCAnMl2jf88Mhne0suPdgfbab6MQe5kHdEB/out-0.png" ], "started_at": "2023-06-18T20:42:42.415358Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/y6a4aczbyuqvbxoh7wkhwcjvma", "cancel": "https://api.replicate.com/v1/predictions/y6a4aczbyuqvbxoh7wkhwcjvma/cancel" }, "version": "e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8" }Generated inUsing seed: 44937 using txt2img 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:11, 4.15it/s] 4%|▍ | 2/50 [00:00<00:10, 4.39it/s] 6%|▌ | 3/50 [00:00<00:10, 4.48it/s] 8%|▊ | 4/50 [00:00<00:10, 4.50it/s] 10%|█ | 5/50 [00:01<00:10, 4.26it/s] 12%|█▏ | 6/50 [00:01<00:10, 4.31it/s] 14%|█▍ | 7/50 [00:01<00:09, 4.37it/s] 16%|█▌ | 8/50 [00:01<00:09, 4.40it/s] 18%|█▊ | 9/50 [00:02<00:09, 4.33it/s] 20%|██ | 10/50 [00:02<00:09, 4.34it/s] 22%|██▏ | 11/50 [00:02<00:08, 4.37it/s] 24%|██▍ | 12/50 [00:02<00:08, 4.39it/s] 26%|██▌ | 13/50 [00:02<00:08, 4.36it/s] 28%|██▊ | 14/50 [00:03<00:08, 4.31it/s] 30%|███ | 15/50 [00:03<00:08, 4.35it/s] 32%|███▏ | 16/50 [00:03<00:07, 4.38it/s] 34%|███▍ | 17/50 [00:03<00:07, 4.39it/s] 36%|███▌ | 18/50 [00:04<00:07, 4.31it/s] 38%|███▊ | 19/50 [00:04<00:07, 4.34it/s] 40%|████ | 20/50 [00:04<00:06, 4.36it/s] 42%|████▏ | 21/50 [00:04<00:06, 4.37it/s] 44%|████▍ | 22/50 [00:05<00:06, 4.35it/s] 46%|████▌ | 23/50 [00:05<00:06, 4.31it/s] 48%|████▊ | 24/50 [00:05<00:05, 4.36it/s] 50%|█████ | 25/50 [00:05<00:05, 4.39it/s] 52%|█████▏ | 26/50 [00:05<00:05, 4.39it/s] 54%|█████▍ | 27/50 [00:06<00:05, 4.33it/s] 56%|█████▌ | 28/50 [00:06<00:05, 4.36it/s] 58%|█████▊ | 29/50 [00:06<00:04, 4.39it/s] 60%|██████ | 30/50 [00:06<00:04, 4.39it/s] 62%|██████▏ | 31/50 [00:07<00:04, 4.36it/s] 64%|██████▍ | 32/50 [00:07<00:04, 4.33it/s] 66%|██████▌ | 33/50 [00:07<00:03, 4.37it/s] 68%|██████▊ | 34/50 [00:07<00:03, 4.39it/s] 70%|███████ | 35/50 [00:08<00:03, 4.40it/s] 72%|███████▏ | 36/50 [00:08<00:03, 4.40it/s] 74%|███████▍ | 37/50 [00:08<00:02, 4.41it/s] 76%|███████▌ | 38/50 [00:08<00:02, 4.40it/s] 78%|███████▊ | 39/50 [00:08<00:02, 4.41it/s] 80%|████████ | 40/50 [00:09<00:02, 4.42it/s] 82%|████████▏ | 41/50 [00:09<00:02, 4.45it/s] 84%|████████▍ | 42/50 [00:09<00:01, 4.47it/s] 86%|████████▌ | 43/50 [00:09<00:01, 4.48it/s] 88%|████████▊ | 44/50 [00:10<00:01, 4.46it/s] 90%|█████████ | 45/50 [00:10<00:01, 4.47it/s] 92%|█████████▏| 46/50 [00:10<00:00, 4.48it/s] 94%|█████████▍| 47/50 [00:10<00:00, 4.48it/s] 96%|█████████▌| 48/50 [00:10<00:00, 4.48it/s] 98%|█████████▊| 49/50 [00:11<00:00, 4.46it/s] 100%|██████████| 50/50 [00:11<00:00, 4.46it/s] 100%|██████████| 50/50 [00:11<00:00, 4.39it/s]Prediction
cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8IDn26opbjbhmaj6hpdbprpg556suStatusSucceededSourceWebHardwareT4Total durationCreatedInput
- width
- 512
- height
- 512
- prompt
- a painted portrait of a qdg dog with brown fur, no white fur, wearing a sea captain's uniform and hat, sea in background, oil painting by thomas gainsborough, elegant, highly detailed, anthro, anthropomorphic dog, epic fantasy art, trending on artstation, photorealistic, photoshop, behance winner
- scheduler
- DDIM
- num_outputs
- 1
- guidance_scale
- 7.5
- negative_prompt
- cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 512, "height": 512, "prompt": "a painted portrait of a qdg dog with brown fur, no white fur, wearing a sea captain's uniform and hat, sea in background, oil painting by thomas gainsborough, elegant, highly detailed, anthro, anthropomorphic dog, epic fantasy art, trending on artstation, photorealistic, photoshop, behance winner", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", { input: { width: 512, height: 512, prompt: "a painted portrait of a qdg dog with brown fur, no white fur, wearing a sea captain's uniform and hat, sea in background, oil painting by thomas gainsborough, elegant, highly detailed, anthro, anthropomorphic dog, epic fantasy art, trending on artstation, photorealistic, photoshop, behance winner", scheduler: "DDIM", num_outputs: 1, guidance_scale: 7.5, negative_prompt: "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", prompt_strength: 0.8, num_inference_steps: 50 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", input={ "width": 512, "height": 512, "prompt": "a painted portrait of a qdg dog with brown fur, no white fur, wearing a sea captain's uniform and hat, sea in background, oil painting by thomas gainsborough, elegant, highly detailed, anthro, anthropomorphic dog, epic fantasy art, trending on artstation, photorealistic, photoshop, behance winner", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } ) # To access the file URL: print(output[0].url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output[0].read())To learn more, take a look at the guide on getting started with Python.
Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", "input": { "width": 512, "height": 512, "prompt": "a painted portrait of a qdg dog with brown fur, no white fur, wearing a sea captain\'s uniform and hat, sea in background, oil painting by thomas gainsborough, elegant, highly detailed, anthro, anthropomorphic dog, epic fantasy art, trending on artstation, photorealistic, photoshop, behance winner", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8 \ -i 'width=512' \ -i 'height=512' \ -i $'prompt="a painted portrait of a qdg dog with brown fur, no white fur, wearing a sea captain\'s uniform and hat, sea in background, oil painting by thomas gainsborough, elegant, highly detailed, anthro, anthropomorphic dog, epic fantasy art, trending on artstation, photorealistic, photoshop, behance winner"' \ -i 'scheduler="DDIM"' \ -i 'num_outputs=1' \ -i 'guidance_scale=7.5' \ -i 'negative_prompt="cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark"' \ -i 'prompt_strength=0.8' \ -i 'num_inference_steps=50'To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 512, "height": 512, "prompt": "a painted portrait of a qdg dog with brown fur, no white fur, wearing a sea captain\'s uniform and hat, sea in background, oil painting by thomas gainsborough, elegant, highly detailed, anthro, anthropomorphic dog, epic fantasy art, trending on artstation, photorealistic, photoshop, behance winner", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-06-18T20:43:34.292664Z", "created_at": "2023-06-18T20:43:22.512009Z", "data_removed": false, "error": null, "id": "n26opbjbhmaj6hpdbprpg556su", "input": { "width": 512, "height": 512, "prompt": "a painted portrait of a qdg dog with brown fur, no white fur, wearing a sea captain's uniform and hat, sea in background, oil painting by thomas gainsborough, elegant, highly detailed, anthro, anthropomorphic dog, epic fantasy art, trending on artstation, photorealistic, photoshop, behance winner", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 25920\nusing txt2img\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:12, 4.07it/s]\n 4%|▍ | 2/50 [00:00<00:10, 4.54it/s]\n 6%|▌ | 3/50 [00:00<00:09, 4.71it/s]\n 8%|▊ | 4/50 [00:00<00:09, 4.79it/s]\n 10%|█ | 5/50 [00:01<00:09, 4.75it/s]\n 12%|█▏ | 6/50 [00:01<00:09, 4.66it/s]\n 14%|█▍ | 7/50 [00:01<00:09, 4.68it/s]\n 16%|█▌ | 8/50 [00:01<00:08, 4.76it/s]\n 18%|█▊ | 9/50 [00:01<00:08, 4.80it/s]\n 20%|██ | 10/50 [00:02<00:08, 4.74it/s]\n 22%|██▏ | 11/50 [00:02<00:08, 4.74it/s]\n 24%|██▍ | 12/50 [00:02<00:07, 4.79it/s]\n 26%|██▌ | 13/50 [00:02<00:07, 4.81it/s]\n 28%|██▊ | 14/50 [00:02<00:07, 4.76it/s]\n 30%|███ | 15/50 [00:03<00:07, 4.69it/s]\n 32%|███▏ | 16/50 [00:03<00:07, 4.72it/s]\n 34%|███▍ | 17/50 [00:03<00:07, 4.69it/s]\n 36%|███▌ | 18/50 [00:03<00:06, 4.75it/s]\n 38%|███▊ | 19/50 [00:04<00:06, 4.76it/s]\n 40%|████ | 20/50 [00:04<00:06, 4.69it/s]\n 42%|████▏ | 21/50 [00:04<00:06, 4.65it/s]\n 44%|████▍ | 22/50 [00:04<00:05, 4.71it/s]\n 46%|████▌ | 23/50 [00:04<00:05, 4.68it/s]\n 48%|████▊ | 24/50 [00:05<00:05, 4.73it/s]\n 50%|█████ | 25/50 [00:05<00:05, 4.68it/s]\n 52%|█████▏ | 26/50 [00:05<00:05, 4.73it/s]\n 54%|█████▍ | 27/50 [00:05<00:04, 4.71it/s]\n 56%|█████▌ | 28/50 [00:05<00:04, 4.74it/s]\n 58%|█████▊ | 29/50 [00:06<00:04, 4.69it/s]\n 60%|██████ | 30/50 [00:06<00:04, 4.67it/s]\n 62%|██████▏ | 31/50 [00:06<00:04, 4.70it/s]\n 64%|██████▍ | 32/50 [00:06<00:03, 4.76it/s]\n 66%|██████▌ | 33/50 [00:06<00:03, 4.74it/s]\n 68%|██████▊ | 34/50 [00:07<00:03, 4.71it/s]\n 70%|███████ | 35/50 [00:07<00:03, 4.67it/s]\n 72%|███████▏ | 36/50 [00:07<00:02, 4.71it/s]\n 74%|███████▍ | 37/50 [00:07<00:02, 4.68it/s]\n 76%|███████▌ | 38/50 [00:08<00:02, 4.69it/s]\n 78%|███████▊ | 39/50 [00:08<00:02, 4.68it/s]\n 80%|████████ | 40/50 [00:08<00:02, 4.64it/s]\n 82%|████████▏ | 41/50 [00:08<00:01, 4.69it/s]\n 84%|████████▍ | 42/50 [00:08<00:01, 4.67it/s]\n 86%|████████▌ | 43/50 [00:09<00:01, 4.71it/s]\n 88%|████████▊ | 44/50 [00:09<00:01, 4.68it/s]\n 90%|█████████ | 45/50 [00:09<00:01, 4.66it/s]\n 92%|█████████▏| 46/50 [00:09<00:00, 4.66it/s]\n 94%|█████████▍| 47/50 [00:10<00:00, 4.63it/s]\n 96%|█████████▌| 48/50 [00:10<00:00, 4.65it/s]\n 98%|█████████▊| 49/50 [00:10<00:00, 4.59it/s]\n100%|██████████| 50/50 [00:10<00:00, 4.62it/s]\n100%|██████████| 50/50 [00:10<00:00, 4.69it/s]", "metrics": { "predict_time": 11.840546, "total_time": 11.780655 }, "output": [ "https://replicate.delivery/pbxt/QjLrEgHeHLSBNSLZxnazlLShrB1I3YW03vetMUSEq5Q15RHRA/out-0.png" ], "started_at": "2023-06-18T20:43:22.452118Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/n26opbjbhmaj6hpdbprpg556su", "cancel": "https://api.replicate.com/v1/predictions/n26opbjbhmaj6hpdbprpg556su/cancel" }, "version": "e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8" }Generated inUsing seed: 25920 using txt2img 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:12, 4.07it/s] 4%|▍ | 2/50 [00:00<00:10, 4.54it/s] 6%|▌ | 3/50 [00:00<00:09, 4.71it/s] 8%|▊ | 4/50 [00:00<00:09, 4.79it/s] 10%|█ | 5/50 [00:01<00:09, 4.75it/s] 12%|█▏ | 6/50 [00:01<00:09, 4.66it/s] 14%|█▍ | 7/50 [00:01<00:09, 4.68it/s] 16%|█▌ | 8/50 [00:01<00:08, 4.76it/s] 18%|█▊ | 9/50 [00:01<00:08, 4.80it/s] 20%|██ | 10/50 [00:02<00:08, 4.74it/s] 22%|██▏ | 11/50 [00:02<00:08, 4.74it/s] 24%|██▍ | 12/50 [00:02<00:07, 4.79it/s] 26%|██▌ | 13/50 [00:02<00:07, 4.81it/s] 28%|██▊ | 14/50 [00:02<00:07, 4.76it/s] 30%|███ | 15/50 [00:03<00:07, 4.69it/s] 32%|███▏ | 16/50 [00:03<00:07, 4.72it/s] 34%|███▍ | 17/50 [00:03<00:07, 4.69it/s] 36%|███▌ | 18/50 [00:03<00:06, 4.75it/s] 38%|███▊ | 19/50 [00:04<00:06, 4.76it/s] 40%|████ | 20/50 [00:04<00:06, 4.69it/s] 42%|████▏ | 21/50 [00:04<00:06, 4.65it/s] 44%|████▍ | 22/50 [00:04<00:05, 4.71it/s] 46%|████▌ | 23/50 [00:04<00:05, 4.68it/s] 48%|████▊ | 24/50 [00:05<00:05, 4.73it/s] 50%|█████ | 25/50 [00:05<00:05, 4.68it/s] 52%|█████▏ | 26/50 [00:05<00:05, 4.73it/s] 54%|█████▍ | 27/50 [00:05<00:04, 4.71it/s] 56%|█████▌ | 28/50 [00:05<00:04, 4.74it/s] 58%|█████▊ | 29/50 [00:06<00:04, 4.69it/s] 60%|██████ | 30/50 [00:06<00:04, 4.67it/s] 62%|██████▏ | 31/50 [00:06<00:04, 4.70it/s] 64%|██████▍ | 32/50 [00:06<00:03, 4.76it/s] 66%|██████▌ | 33/50 [00:06<00:03, 4.74it/s] 68%|██████▊ | 34/50 [00:07<00:03, 4.71it/s] 70%|███████ | 35/50 [00:07<00:03, 4.67it/s] 72%|███████▏ | 36/50 [00:07<00:02, 4.71it/s] 74%|███████▍ | 37/50 [00:07<00:02, 4.68it/s] 76%|███████▌ | 38/50 [00:08<00:02, 4.69it/s] 78%|███████▊ | 39/50 [00:08<00:02, 4.68it/s] 80%|████████ | 40/50 [00:08<00:02, 4.64it/s] 82%|████████▏ | 41/50 [00:08<00:01, 4.69it/s] 84%|████████▍ | 42/50 [00:08<00:01, 4.67it/s] 86%|████████▌ | 43/50 [00:09<00:01, 4.71it/s] 88%|████████▊ | 44/50 [00:09<00:01, 4.68it/s] 90%|█████████ | 45/50 [00:09<00:01, 4.66it/s] 92%|█████████▏| 46/50 [00:09<00:00, 4.66it/s] 94%|█████████▍| 47/50 [00:10<00:00, 4.63it/s] 96%|█████████▌| 48/50 [00:10<00:00, 4.65it/s] 98%|█████████▊| 49/50 [00:10<00:00, 4.59it/s] 100%|██████████| 50/50 [00:10<00:00, 4.62it/s] 100%|██████████| 50/50 [00:10<00:00, 4.69it/s]Prediction
cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8ID24bzinzblpe4goh7nc32dudyh4StatusSucceededSourceWebHardwareT4Total durationCreatedInput
- width
- 512
- height
- 512
- prompt
- qdg dog guarding her home, dramatic sunset lighting, mat painting, highly detailed
- scheduler
- DDIM
- num_outputs
- 1
- guidance_scale
- 7.5
- negative_prompt
- cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 512, "height": 512, "prompt": "qdg dog guarding her home, dramatic sunset lighting, mat painting, highly detailed", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", { input: { width: 512, height: 512, prompt: "qdg dog guarding her home, dramatic sunset lighting, mat painting, highly detailed", scheduler: "DDIM", num_outputs: 1, guidance_scale: 7.5, negative_prompt: "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", prompt_strength: 0.8, num_inference_steps: 50 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", input={ "width": 512, "height": 512, "prompt": "qdg dog guarding her home, dramatic sunset lighting, mat painting, highly detailed", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } ) # To access the file URL: print(output[0].url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output[0].read())To learn more, take a look at the guide on getting started with Python.
Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", "input": { "width": 512, "height": 512, "prompt": "qdg dog guarding her home, dramatic sunset lighting, mat painting, highly detailed", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8 \ -i 'width=512' \ -i 'height=512' \ -i 'prompt="qdg dog guarding her home, dramatic sunset lighting, mat painting, highly detailed"' \ -i 'scheduler="DDIM"' \ -i 'num_outputs=1' \ -i 'guidance_scale=7.5' \ -i 'negative_prompt="cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark"' \ -i 'prompt_strength=0.8' \ -i 'num_inference_steps=50'To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 512, "height": 512, "prompt": "qdg dog guarding her home, dramatic sunset lighting, mat painting, highly detailed", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-06-18T20:44:02.658680Z", "created_at": "2023-06-18T20:43:50.818614Z", "data_removed": false, "error": null, "id": "24bzinzblpe4goh7nc32dudyh4", "input": { "width": 512, "height": 512, "prompt": "qdg dog guarding her home, dramatic sunset lighting, mat painting, highly detailed", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 63742\nusing txt2img\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:12, 3.90it/s]\n 4%|▍ | 2/50 [00:00<00:10, 4.48it/s]\n 6%|▌ | 3/50 [00:00<00:10, 4.70it/s]\n 8%|▊ | 4/50 [00:00<00:09, 4.81it/s]\n 10%|█ | 5/50 [00:01<00:09, 4.80it/s]\n 12%|█▏ | 6/50 [00:01<00:09, 4.64it/s]\n 14%|█▍ | 7/50 [00:01<00:09, 4.68it/s]\n 16%|█▌ | 8/50 [00:01<00:08, 4.75it/s]\n 18%|█▊ | 9/50 [00:01<00:08, 4.82it/s]\n 20%|██ | 10/50 [00:02<00:08, 4.78it/s]\n 22%|██▏ | 11/50 [00:02<00:08, 4.71it/s]\n 24%|██▍ | 12/50 [00:02<00:08, 4.71it/s]\n 26%|██▌ | 13/50 [00:02<00:07, 4.75it/s]\n 28%|██▊ | 14/50 [00:02<00:07, 4.79it/s]\n 30%|███ | 15/50 [00:03<00:07, 4.73it/s]\n 32%|███▏ | 16/50 [00:03<00:07, 4.70it/s]\n 34%|███▍ | 17/50 [00:03<00:07, 4.69it/s]\n 36%|███▌ | 18/50 [00:03<00:06, 4.77it/s]\n 38%|███▊ | 19/50 [00:04<00:06, 4.79it/s]\n 40%|████ | 20/50 [00:04<00:06, 4.69it/s]\n 42%|████▏ | 21/50 [00:04<00:06, 4.66it/s]\n 44%|████▍ | 22/50 [00:04<00:05, 4.70it/s]\n 46%|████▌ | 23/50 [00:04<00:05, 4.68it/s]\n 48%|████▊ | 24/50 [00:05<00:05, 4.72it/s]\n 50%|█████ | 25/50 [00:05<00:05, 4.66it/s]\n 52%|█████▏ | 26/50 [00:05<00:05, 4.63it/s]\n 54%|█████▍ | 27/50 [00:05<00:04, 4.71it/s]\n 56%|█████▌ | 28/50 [00:05<00:04, 4.74it/s]\n 58%|█████▊ | 29/50 [00:06<00:04, 4.67it/s]\n 60%|██████ | 30/50 [00:06<00:04, 4.62it/s]\n 62%|██████▏ | 31/50 [00:06<00:04, 4.62it/s]\n 64%|██████▍ | 32/50 [00:06<00:03, 4.69it/s]\n 66%|██████▌ | 33/50 [00:07<00:03, 4.66it/s]\n 68%|██████▊ | 34/50 [00:07<00:03, 4.66it/s]\n 70%|███████ | 35/50 [00:07<00:03, 4.63it/s]\n 72%|███████▏ | 36/50 [00:07<00:03, 4.59it/s]\n 74%|███████▍ | 37/50 [00:07<00:02, 4.60it/s]\n 76%|███████▌ | 38/50 [00:08<00:02, 4.61it/s]\n 78%|███████▊ | 39/50 [00:08<00:02, 4.63it/s]\n 80%|████████ | 40/50 [00:08<00:02, 4.59it/s]\n 82%|████████▏ | 41/50 [00:08<00:01, 4.59it/s]\n 84%|████████▍ | 42/50 [00:08<00:01, 4.64it/s]\n 86%|████████▌ | 43/50 [00:09<00:01, 4.61it/s]\n 88%|████████▊ | 44/50 [00:09<00:01, 4.58it/s]\n 90%|█████████ | 45/50 [00:09<00:01, 4.56it/s]\n 92%|█████████▏| 46/50 [00:09<00:00, 4.56it/s]\n 94%|█████████▍| 47/50 [00:10<00:00, 4.61it/s]\n 96%|█████████▌| 48/50 [00:10<00:00, 4.60it/s]\n 98%|█████████▊| 49/50 [00:10<00:00, 4.57it/s]\n100%|██████████| 50/50 [00:10<00:00, 4.55it/s]\n100%|██████████| 50/50 [00:10<00:00, 4.66it/s]", "metrics": { "predict_time": 11.884929, "total_time": 11.840066 }, "output": [ "https://replicate.delivery/pbxt/hFhtuD8kogq4AZclCYS2CKhoksrvzuMauJFwecPaHkvI9ojIA/out-0.png" ], "started_at": "2023-06-18T20:43:50.773751Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/24bzinzblpe4goh7nc32dudyh4", "cancel": "https://api.replicate.com/v1/predictions/24bzinzblpe4goh7nc32dudyh4/cancel" }, "version": "e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8" }Generated inUsing seed: 63742 using txt2img 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:12, 3.90it/s] 4%|▍ | 2/50 [00:00<00:10, 4.48it/s] 6%|▌ | 3/50 [00:00<00:10, 4.70it/s] 8%|▊ | 4/50 [00:00<00:09, 4.81it/s] 10%|█ | 5/50 [00:01<00:09, 4.80it/s] 12%|█▏ | 6/50 [00:01<00:09, 4.64it/s] 14%|█▍ | 7/50 [00:01<00:09, 4.68it/s] 16%|█▌ | 8/50 [00:01<00:08, 4.75it/s] 18%|█▊ | 9/50 [00:01<00:08, 4.82it/s] 20%|██ | 10/50 [00:02<00:08, 4.78it/s] 22%|██▏ | 11/50 [00:02<00:08, 4.71it/s] 24%|██▍ | 12/50 [00:02<00:08, 4.71it/s] 26%|██▌ | 13/50 [00:02<00:07, 4.75it/s] 28%|██▊ | 14/50 [00:02<00:07, 4.79it/s] 30%|███ | 15/50 [00:03<00:07, 4.73it/s] 32%|███▏ | 16/50 [00:03<00:07, 4.70it/s] 34%|███▍ | 17/50 [00:03<00:07, 4.69it/s] 36%|███▌ | 18/50 [00:03<00:06, 4.77it/s] 38%|███▊ | 19/50 [00:04<00:06, 4.79it/s] 40%|████ | 20/50 [00:04<00:06, 4.69it/s] 42%|████▏ | 21/50 [00:04<00:06, 4.66it/s] 44%|████▍ | 22/50 [00:04<00:05, 4.70it/s] 46%|████▌ | 23/50 [00:04<00:05, 4.68it/s] 48%|████▊ | 24/50 [00:05<00:05, 4.72it/s] 50%|█████ | 25/50 [00:05<00:05, 4.66it/s] 52%|█████▏ | 26/50 [00:05<00:05, 4.63it/s] 54%|█████▍ | 27/50 [00:05<00:04, 4.71it/s] 56%|█████▌ | 28/50 [00:05<00:04, 4.74it/s] 58%|█████▊ | 29/50 [00:06<00:04, 4.67it/s] 60%|██████ | 30/50 [00:06<00:04, 4.62it/s] 62%|██████▏ | 31/50 [00:06<00:04, 4.62it/s] 64%|██████▍ | 32/50 [00:06<00:03, 4.69it/s] 66%|██████▌ | 33/50 [00:07<00:03, 4.66it/s] 68%|██████▊ | 34/50 [00:07<00:03, 4.66it/s] 70%|███████ | 35/50 [00:07<00:03, 4.63it/s] 72%|███████▏ | 36/50 [00:07<00:03, 4.59it/s] 74%|███████▍ | 37/50 [00:07<00:02, 4.60it/s] 76%|███████▌ | 38/50 [00:08<00:02, 4.61it/s] 78%|███████▊ | 39/50 [00:08<00:02, 4.63it/s] 80%|████████ | 40/50 [00:08<00:02, 4.59it/s] 82%|████████▏ | 41/50 [00:08<00:01, 4.59it/s] 84%|████████▍ | 42/50 [00:08<00:01, 4.64it/s] 86%|████████▌ | 43/50 [00:09<00:01, 4.61it/s] 88%|████████▊ | 44/50 [00:09<00:01, 4.58it/s] 90%|█████████ | 45/50 [00:09<00:01, 4.56it/s] 92%|█████████▏| 46/50 [00:09<00:00, 4.56it/s] 94%|█████████▍| 47/50 [00:10<00:00, 4.61it/s] 96%|█████████▌| 48/50 [00:10<00:00, 4.60it/s] 98%|█████████▊| 49/50 [00:10<00:00, 4.57it/s] 100%|██████████| 50/50 [00:10<00:00, 4.55it/s] 100%|██████████| 50/50 [00:10<00:00, 4.66it/s]Prediction
cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8IDbkg7asbbwnmt46ey35och3i4peStatusSucceededSourceWebHardwareT4Total durationCreatedInput
- width
- 512
- height
- 512
- prompt
- qdg dog guarding her home, dramatic sunset lighting, mat painting, highly detailed
- scheduler
- DDIM
- num_outputs
- 1
- guidance_scale
- 7.5
- negative_prompt
- cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 512, "height": 512, "prompt": "qdg dog guarding her home, dramatic sunset lighting, mat painting, highly detailed", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", { input: { width: 512, height: 512, prompt: "qdg dog guarding her home, dramatic sunset lighting, mat painting, highly detailed", scheduler: "DDIM", num_outputs: 1, guidance_scale: 7.5, negative_prompt: "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", prompt_strength: 0.8, num_inference_steps: 50 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", input={ "width": 512, "height": 512, "prompt": "qdg dog guarding her home, dramatic sunset lighting, mat painting, highly detailed", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } ) # To access the file URL: print(output[0].url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output[0].read())To learn more, take a look at the guide on getting started with Python.
Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", "input": { "width": 512, "height": 512, "prompt": "qdg dog guarding her home, dramatic sunset lighting, mat painting, highly detailed", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8 \ -i 'width=512' \ -i 'height=512' \ -i 'prompt="qdg dog guarding her home, dramatic sunset lighting, mat painting, highly detailed"' \ -i 'scheduler="DDIM"' \ -i 'num_outputs=1' \ -i 'guidance_scale=7.5' \ -i 'negative_prompt="cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark"' \ -i 'prompt_strength=0.8' \ -i 'num_inference_steps=50'To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 512, "height": 512, "prompt": "qdg dog guarding her home, dramatic sunset lighting, mat painting, highly detailed", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-06-18T20:44:39.513826Z", "created_at": "2023-06-18T20:44:27.591551Z", "data_removed": false, "error": null, "id": "bkg7asbbwnmt46ey35och3i4pe", "input": { "width": 512, "height": 512, "prompt": "qdg dog guarding her home, dramatic sunset lighting, mat painting, highly detailed", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 23876\nusing txt2img\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:11, 4.23it/s]\n 4%|▍ | 2/50 [00:00<00:10, 4.60it/s]\n 6%|▌ | 3/50 [00:00<00:09, 4.74it/s]\n 8%|▊ | 4/50 [00:00<00:09, 4.81it/s]\n 10%|█ | 5/50 [00:01<00:09, 4.61it/s]\n 12%|█▏ | 6/50 [00:01<00:09, 4.64it/s]\n 14%|█▍ | 7/50 [00:01<00:09, 4.72it/s]\n 16%|█▌ | 8/50 [00:01<00:08, 4.75it/s]\n 18%|█▊ | 9/50 [00:01<00:08, 4.69it/s]\n 20%|██ | 10/50 [00:02<00:08, 4.53it/s]\n 22%|██▏ | 11/50 [00:02<00:08, 4.57it/s]\n 24%|██▍ | 12/50 [00:02<00:08, 4.62it/s]\n 26%|██▌ | 13/50 [00:02<00:07, 4.70it/s]\n 28%|██▊ | 14/50 [00:03<00:07, 4.66it/s]\n 30%|███ | 15/50 [00:03<00:07, 4.60it/s]\n 32%|███▏ | 16/50 [00:03<00:07, 4.59it/s]\n 34%|███▍ | 17/50 [00:03<00:07, 4.66it/s]\n 36%|███▌ | 18/50 [00:03<00:06, 4.70it/s]\n 38%|███▊ | 19/50 [00:04<00:06, 4.58it/s]\n 40%|████ | 20/50 [00:04<00:06, 4.55it/s]\n 42%|████▏ | 21/50 [00:04<00:06, 4.62it/s]\n 44%|████▍ | 22/50 [00:04<00:06, 4.62it/s]\n 46%|████▌ | 23/50 [00:04<00:05, 4.67it/s]\n 48%|████▊ | 24/50 [00:05<00:05, 4.57it/s]\n 50%|█████ | 25/50 [00:05<00:05, 4.58it/s]\n 52%|█████▏ | 26/50 [00:05<00:05, 4.59it/s]\n 54%|█████▍ | 27/50 [00:05<00:04, 4.63it/s]\n 56%|█████▌ | 28/50 [00:06<00:04, 4.60it/s]\n 58%|█████▊ | 29/50 [00:06<00:04, 4.57it/s]\n 60%|██████ | 30/50 [00:06<00:04, 4.57it/s]\n 62%|██████▏ | 31/50 [00:06<00:04, 4.60it/s]\n 64%|██████▍ | 32/50 [00:06<00:03, 4.63it/s]\n 66%|██████▌ | 33/50 [00:07<00:03, 4.59it/s]\n 68%|██████▊ | 34/50 [00:07<00:03, 4.57it/s]\n 70%|███████ | 35/50 [00:07<00:03, 4.57it/s]\n 72%|███████▏ | 36/50 [00:07<00:03, 4.61it/s]\n 74%|███████▍ | 37/50 [00:08<00:02, 4.60it/s]\n 76%|███████▌ | 38/50 [00:08<00:02, 4.58it/s]\n 78%|███████▊ | 39/50 [00:08<00:02, 4.58it/s]\n 80%|████████ | 40/50 [00:08<00:02, 4.62it/s]\n 82%|████████▏ | 41/50 [00:08<00:01, 4.63it/s]\n 84%|████████▍ | 42/50 [00:09<00:01, 4.60it/s]\n 86%|████████▌ | 43/50 [00:09<00:01, 4.60it/s]\n 88%|████████▊ | 44/50 [00:09<00:01, 4.61it/s]\n 90%|█████████ | 45/50 [00:09<00:01, 4.61it/s]\n 92%|█████████▏| 46/50 [00:09<00:00, 4.63it/s]\n 94%|█████████▍| 47/50 [00:10<00:00, 4.63it/s]\n 96%|█████████▌| 48/50 [00:10<00:00, 4.60it/s]\n 98%|█████████▊| 49/50 [00:10<00:00, 4.57it/s]\n100%|██████████| 50/50 [00:10<00:00, 4.58it/s]\n100%|██████████| 50/50 [00:10<00:00, 4.61it/s]", "metrics": { "predict_time": 11.951757, "total_time": 11.922275 }, "output": [ "https://replicate.delivery/pbxt/fNtfO97EDCqGDkHPOTwb3OIBmf65mKygrKB0aSe9ZAKZrHdEB/out-0.png" ], "started_at": "2023-06-18T20:44:27.562069Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/bkg7asbbwnmt46ey35och3i4pe", "cancel": "https://api.replicate.com/v1/predictions/bkg7asbbwnmt46ey35och3i4pe/cancel" }, "version": "e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8" }Generated inUsing seed: 23876 using txt2img 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:11, 4.23it/s] 4%|▍ | 2/50 [00:00<00:10, 4.60it/s] 6%|▌ | 3/50 [00:00<00:09, 4.74it/s] 8%|▊ | 4/50 [00:00<00:09, 4.81it/s] 10%|█ | 5/50 [00:01<00:09, 4.61it/s] 12%|█▏ | 6/50 [00:01<00:09, 4.64it/s] 14%|█▍ | 7/50 [00:01<00:09, 4.72it/s] 16%|█▌ | 8/50 [00:01<00:08, 4.75it/s] 18%|█▊ | 9/50 [00:01<00:08, 4.69it/s] 20%|██ | 10/50 [00:02<00:08, 4.53it/s] 22%|██▏ | 11/50 [00:02<00:08, 4.57it/s] 24%|██▍ | 12/50 [00:02<00:08, 4.62it/s] 26%|██▌ | 13/50 [00:02<00:07, 4.70it/s] 28%|██▊ | 14/50 [00:03<00:07, 4.66it/s] 30%|███ | 15/50 [00:03<00:07, 4.60it/s] 32%|███▏ | 16/50 [00:03<00:07, 4.59it/s] 34%|███▍ | 17/50 [00:03<00:07, 4.66it/s] 36%|███▌ | 18/50 [00:03<00:06, 4.70it/s] 38%|███▊ | 19/50 [00:04<00:06, 4.58it/s] 40%|████ | 20/50 [00:04<00:06, 4.55it/s] 42%|████▏ | 21/50 [00:04<00:06, 4.62it/s] 44%|████▍ | 22/50 [00:04<00:06, 4.62it/s] 46%|████▌ | 23/50 [00:04<00:05, 4.67it/s] 48%|████▊ | 24/50 [00:05<00:05, 4.57it/s] 50%|█████ | 25/50 [00:05<00:05, 4.58it/s] 52%|█████▏ | 26/50 [00:05<00:05, 4.59it/s] 54%|█████▍ | 27/50 [00:05<00:04, 4.63it/s] 56%|█████▌ | 28/50 [00:06<00:04, 4.60it/s] 58%|█████▊ | 29/50 [00:06<00:04, 4.57it/s] 60%|██████ | 30/50 [00:06<00:04, 4.57it/s] 62%|██████▏ | 31/50 [00:06<00:04, 4.60it/s] 64%|██████▍ | 32/50 [00:06<00:03, 4.63it/s] 66%|██████▌ | 33/50 [00:07<00:03, 4.59it/s] 68%|██████▊ | 34/50 [00:07<00:03, 4.57it/s] 70%|███████ | 35/50 [00:07<00:03, 4.57it/s] 72%|███████▏ | 36/50 [00:07<00:03, 4.61it/s] 74%|███████▍ | 37/50 [00:08<00:02, 4.60it/s] 76%|███████▌ | 38/50 [00:08<00:02, 4.58it/s] 78%|███████▊ | 39/50 [00:08<00:02, 4.58it/s] 80%|████████ | 40/50 [00:08<00:02, 4.62it/s] 82%|████████▏ | 41/50 [00:08<00:01, 4.63it/s] 84%|████████▍ | 42/50 [00:09<00:01, 4.60it/s] 86%|████████▌ | 43/50 [00:09<00:01, 4.60it/s] 88%|████████▊ | 44/50 [00:09<00:01, 4.61it/s] 90%|█████████ | 45/50 [00:09<00:01, 4.61it/s] 92%|█████████▏| 46/50 [00:09<00:00, 4.63it/s] 94%|█████████▍| 47/50 [00:10<00:00, 4.63it/s] 96%|█████████▌| 48/50 [00:10<00:00, 4.60it/s] 98%|█████████▊| 49/50 [00:10<00:00, 4.57it/s] 100%|██████████| 50/50 [00:10<00:00, 4.58it/s] 100%|██████████| 50/50 [00:10<00:00, 4.61it/s]Prediction
cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8IDuorij7rb6qrpis5r3bgyijgaeaStatusSucceededSourceWebHardwareT4Total durationCreatedInput
- width
- 512
- height
- 512
- prompt
- qdg dog guarding her home, dramatic sunset lighting, mat painting, highly detailed
- scheduler
- DDIM
- num_outputs
- 1
- guidance_scale
- 7.5
- negative_prompt
- cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 512, "height": 512, "prompt": "qdg dog guarding her home, dramatic sunset lighting, mat painting, highly detailed", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", { input: { width: 512, height: 512, prompt: "qdg dog guarding her home, dramatic sunset lighting, mat painting, highly detailed", scheduler: "DDIM", num_outputs: 1, guidance_scale: 7.5, negative_prompt: "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", prompt_strength: 0.8, num_inference_steps: 50 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", input={ "width": 512, "height": 512, "prompt": "qdg dog guarding her home, dramatic sunset lighting, mat painting, highly detailed", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } ) # To access the file URL: print(output[0].url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output[0].read())To learn more, take a look at the guide on getting started with Python.
Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", "input": { "width": 512, "height": 512, "prompt": "qdg dog guarding her home, dramatic sunset lighting, mat painting, highly detailed", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8 \ -i 'width=512' \ -i 'height=512' \ -i 'prompt="qdg dog guarding her home, dramatic sunset lighting, mat painting, highly detailed"' \ -i 'scheduler="DDIM"' \ -i 'num_outputs=1' \ -i 'guidance_scale=7.5' \ -i 'negative_prompt="cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark"' \ -i 'prompt_strength=0.8' \ -i 'num_inference_steps=50'To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 512, "height": 512, "prompt": "qdg dog guarding her home, dramatic sunset lighting, mat painting, highly detailed", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-06-18T20:45:17.285758Z", "created_at": "2023-06-18T20:45:05.265612Z", "data_removed": false, "error": null, "id": "uorij7rb6qrpis5r3bgyijgaea", "input": { "width": 512, "height": 512, "prompt": "qdg dog guarding her home, dramatic sunset lighting, mat painting, highly detailed", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 46393\nusing txt2img\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:12, 4.06it/s]\n 4%|▍ | 2/50 [00:00<00:10, 4.40it/s]\n 6%|▌ | 3/50 [00:00<00:10, 4.62it/s]\n 8%|▊ | 4/50 [00:00<00:09, 4.75it/s]\n 10%|█ | 5/50 [00:01<00:09, 4.61it/s]\n 12%|█▏ | 6/50 [00:01<00:09, 4.59it/s]\n 14%|█▍ | 7/50 [00:01<00:09, 4.67it/s]\n 16%|█▌ | 8/50 [00:01<00:09, 4.66it/s]\n 18%|█▊ | 9/50 [00:01<00:08, 4.73it/s]\n 20%|██ | 10/50 [00:02<00:08, 4.63it/s]\n 22%|██▏ | 11/50 [00:02<00:08, 4.61it/s]\n 24%|██▍ | 12/50 [00:02<00:08, 4.70it/s]\n 26%|██▌ | 13/50 [00:02<00:07, 4.68it/s]\n 28%|██▊ | 14/50 [00:03<00:07, 4.67it/s]\n 30%|███ | 15/50 [00:03<00:07, 4.53it/s]\n 32%|███▏ | 16/50 [00:03<00:07, 4.55it/s]\n 34%|███▍ | 17/50 [00:03<00:07, 4.61it/s]\n 36%|███▌ | 18/50 [00:03<00:06, 4.67it/s]\n 38%|███▊ | 19/50 [00:04<00:06, 4.58it/s]\n 40%|████ | 20/50 [00:04<00:06, 4.52it/s]\n 42%|████▏ | 21/50 [00:04<00:06, 4.60it/s]\n 44%|████▍ | 22/50 [00:04<00:06, 4.61it/s]\n 46%|████▌ | 23/50 [00:04<00:05, 4.65it/s]\n 48%|████▊ | 24/50 [00:05<00:05, 4.57it/s]\n 50%|█████ | 25/50 [00:05<00:05, 4.56it/s]\n 52%|█████▏ | 26/50 [00:05<00:05, 4.57it/s]\n 54%|█████▍ | 27/50 [00:05<00:04, 4.60it/s]\n 56%|█████▌ | 28/50 [00:06<00:04, 4.57it/s]\n 58%|█████▊ | 29/50 [00:06<00:04, 4.55it/s]\n 60%|██████ | 30/50 [00:06<00:04, 4.56it/s]\n 62%|██████▏ | 31/50 [00:06<00:04, 4.59it/s]\n 64%|██████▍ | 32/50 [00:06<00:03, 4.61it/s]\n 66%|██████▌ | 33/50 [00:07<00:03, 4.58it/s]\n 68%|██████▊ | 34/50 [00:07<00:03, 4.52it/s]\n 70%|███████ | 35/50 [00:07<00:03, 4.56it/s]\n 72%|███████▏ | 36/50 [00:07<00:03, 4.59it/s]\n 74%|███████▍ | 37/50 [00:08<00:02, 4.57it/s]\n 76%|███████▌ | 38/50 [00:08<00:02, 4.54it/s]\n 78%|███████▊ | 39/50 [00:08<00:02, 4.54it/s]\n 80%|████████ | 40/50 [00:08<00:02, 4.59it/s]\n 82%|████████▏ | 41/50 [00:08<00:01, 4.59it/s]\n 84%|████████▍ | 42/50 [00:09<00:01, 4.56it/s]\n 86%|████████▌ | 43/50 [00:09<00:01, 4.51it/s]\n 88%|████████▊ | 44/50 [00:09<00:01, 4.53it/s]\n 90%|█████████ | 45/50 [00:09<00:01, 4.55it/s]\n 92%|█████████▏| 46/50 [00:10<00:00, 4.56it/s]\n 94%|█████████▍| 47/50 [00:10<00:00, 4.53it/s]\n 96%|█████████▌| 48/50 [00:10<00:00, 4.49it/s]\n 98%|█████████▊| 49/50 [00:10<00:00, 4.55it/s]\n100%|██████████| 50/50 [00:10<00:00, 4.55it/s]\n100%|██████████| 50/50 [00:10<00:00, 4.58it/s]", "metrics": { "predict_time": 12.091939, "total_time": 12.020146 }, "output": [ "https://replicate.delivery/pbxt/HDKYiZHeSwU1PCbfSly4kuLhSctC1ROJXAjVDYIabke42jOiA/out-0.png" ], "started_at": "2023-06-18T20:45:05.193819Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/uorij7rb6qrpis5r3bgyijgaea", "cancel": "https://api.replicate.com/v1/predictions/uorij7rb6qrpis5r3bgyijgaea/cancel" }, "version": "e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8" }Generated inUsing seed: 46393 using txt2img 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:12, 4.06it/s] 4%|▍ | 2/50 [00:00<00:10, 4.40it/s] 6%|▌ | 3/50 [00:00<00:10, 4.62it/s] 8%|▊ | 4/50 [00:00<00:09, 4.75it/s] 10%|█ | 5/50 [00:01<00:09, 4.61it/s] 12%|█▏ | 6/50 [00:01<00:09, 4.59it/s] 14%|█▍ | 7/50 [00:01<00:09, 4.67it/s] 16%|█▌ | 8/50 [00:01<00:09, 4.66it/s] 18%|█▊ | 9/50 [00:01<00:08, 4.73it/s] 20%|██ | 10/50 [00:02<00:08, 4.63it/s] 22%|██▏ | 11/50 [00:02<00:08, 4.61it/s] 24%|██▍ | 12/50 [00:02<00:08, 4.70it/s] 26%|██▌ | 13/50 [00:02<00:07, 4.68it/s] 28%|██▊ | 14/50 [00:03<00:07, 4.67it/s] 30%|███ | 15/50 [00:03<00:07, 4.53it/s] 32%|███▏ | 16/50 [00:03<00:07, 4.55it/s] 34%|███▍ | 17/50 [00:03<00:07, 4.61it/s] 36%|███▌ | 18/50 [00:03<00:06, 4.67it/s] 38%|███▊ | 19/50 [00:04<00:06, 4.58it/s] 40%|████ | 20/50 [00:04<00:06, 4.52it/s] 42%|████▏ | 21/50 [00:04<00:06, 4.60it/s] 44%|████▍ | 22/50 [00:04<00:06, 4.61it/s] 46%|████▌ | 23/50 [00:04<00:05, 4.65it/s] 48%|████▊ | 24/50 [00:05<00:05, 4.57it/s] 50%|█████ | 25/50 [00:05<00:05, 4.56it/s] 52%|█████▏ | 26/50 [00:05<00:05, 4.57it/s] 54%|█████▍ | 27/50 [00:05<00:04, 4.60it/s] 56%|█████▌ | 28/50 [00:06<00:04, 4.57it/s] 58%|█████▊ | 29/50 [00:06<00:04, 4.55it/s] 60%|██████ | 30/50 [00:06<00:04, 4.56it/s] 62%|██████▏ | 31/50 [00:06<00:04, 4.59it/s] 64%|██████▍ | 32/50 [00:06<00:03, 4.61it/s] 66%|██████▌ | 33/50 [00:07<00:03, 4.58it/s] 68%|██████▊ | 34/50 [00:07<00:03, 4.52it/s] 70%|███████ | 35/50 [00:07<00:03, 4.56it/s] 72%|███████▏ | 36/50 [00:07<00:03, 4.59it/s] 74%|███████▍ | 37/50 [00:08<00:02, 4.57it/s] 76%|███████▌ | 38/50 [00:08<00:02, 4.54it/s] 78%|███████▊ | 39/50 [00:08<00:02, 4.54it/s] 80%|████████ | 40/50 [00:08<00:02, 4.59it/s] 82%|████████▏ | 41/50 [00:08<00:01, 4.59it/s] 84%|████████▍ | 42/50 [00:09<00:01, 4.56it/s] 86%|████████▌ | 43/50 [00:09<00:01, 4.51it/s] 88%|████████▊ | 44/50 [00:09<00:01, 4.53it/s] 90%|█████████ | 45/50 [00:09<00:01, 4.55it/s] 92%|█████████▏| 46/50 [00:10<00:00, 4.56it/s] 94%|█████████▍| 47/50 [00:10<00:00, 4.53it/s] 96%|█████████▌| 48/50 [00:10<00:00, 4.49it/s] 98%|█████████▊| 49/50 [00:10<00:00, 4.55it/s] 100%|██████████| 50/50 [00:10<00:00, 4.55it/s] 100%|██████████| 50/50 [00:10<00:00, 4.58it/s]Prediction
cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8IDa4alaqzbyopnow3kigat73pj4uStatusSucceededSourceWebHardwareT4Total durationCreatedInput
- width
- 512
- height
- 512
- prompt
- qdg dog, realistic shaded lighting poster by ilya kuvshinov katsuhiro otomo, magali villeneuve, artgerm, jeremy lipkin and michael garmash and rob rey
- scheduler
- DDIM
- num_outputs
- 1
- guidance_scale
- 7.5
- negative_prompt
- cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 512, "height": 512, "prompt": "qdg dog, realistic shaded lighting poster by ilya kuvshinov katsuhiro otomo, magali villeneuve, artgerm, jeremy lipkin and michael garmash and rob rey", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", { input: { width: 512, height: 512, prompt: "qdg dog, realistic shaded lighting poster by ilya kuvshinov katsuhiro otomo, magali villeneuve, artgerm, jeremy lipkin and michael garmash and rob rey", scheduler: "DDIM", num_outputs: 1, guidance_scale: 7.5, negative_prompt: "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", prompt_strength: 0.8, num_inference_steps: 50 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", input={ "width": 512, "height": 512, "prompt": "qdg dog, realistic shaded lighting poster by ilya kuvshinov katsuhiro otomo, magali villeneuve, artgerm, jeremy lipkin and michael garmash and rob rey", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } ) # To access the file URL: print(output[0].url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output[0].read())To learn more, take a look at the guide on getting started with Python.
Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", "input": { "width": 512, "height": 512, "prompt": "qdg dog, realistic shaded lighting poster by ilya kuvshinov katsuhiro otomo, magali villeneuve, artgerm, jeremy lipkin and michael garmash and rob rey", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8 \ -i 'width=512' \ -i 'height=512' \ -i 'prompt="qdg dog, realistic shaded lighting poster by ilya kuvshinov katsuhiro otomo, magali villeneuve, artgerm, jeremy lipkin and michael garmash and rob rey"' \ -i 'scheduler="DDIM"' \ -i 'num_outputs=1' \ -i 'guidance_scale=7.5' \ -i 'negative_prompt="cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark"' \ -i 'prompt_strength=0.8' \ -i 'num_inference_steps=50'To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 512, "height": 512, "prompt": "qdg dog, realistic shaded lighting poster by ilya kuvshinov katsuhiro otomo, magali villeneuve, artgerm, jeremy lipkin and michael garmash and rob rey", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-06-18T20:46:29.273260Z", "created_at": "2023-06-18T20:46:17.671039Z", "data_removed": false, "error": null, "id": "a4alaqzbyopnow3kigat73pj4u", "input": { "width": 512, "height": 512, "prompt": "qdg dog, realistic shaded lighting poster by ilya kuvshinov katsuhiro otomo, magali villeneuve, artgerm, jeremy lipkin and michael garmash and rob rey", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 37010\nusing txt2img\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:11, 4.17it/s]\n 4%|▍ | 2/50 [00:00<00:10, 4.60it/s]\n 6%|▌ | 3/50 [00:00<00:09, 4.80it/s]\n 8%|▊ | 4/50 [00:00<00:09, 4.88it/s]\n 10%|█ | 5/50 [00:01<00:09, 4.81it/s]\n 12%|█▏ | 6/50 [00:01<00:09, 4.72it/s]\n 14%|█▍ | 7/50 [00:01<00:09, 4.75it/s]\n 16%|█▌ | 8/50 [00:01<00:08, 4.75it/s]\n 18%|█▊ | 9/50 [00:01<00:08, 4.81it/s]\n 20%|██ | 10/50 [00:02<00:08, 4.78it/s]\n 22%|██▏ | 11/50 [00:02<00:08, 4.72it/s]\n 24%|██▍ | 12/50 [00:02<00:07, 4.79it/s]\n 26%|██▌ | 13/50 [00:02<00:07, 4.86it/s]\n 28%|██▊ | 14/50 [00:02<00:07, 4.87it/s]\n 30%|███ | 15/50 [00:03<00:07, 4.80it/s]\n 32%|███▏ | 16/50 [00:03<00:07, 4.78it/s]\n 34%|███▍ | 17/50 [00:03<00:06, 4.84it/s]\n 36%|███▌ | 18/50 [00:03<00:06, 4.87it/s]\n 38%|███▊ | 19/50 [00:03<00:06, 4.88it/s]\n 40%|████ | 20/50 [00:04<00:06, 4.85it/s]\n 42%|████▏ | 21/50 [00:04<00:06, 4.78it/s]\n 44%|████▍ | 22/50 [00:04<00:05, 4.81it/s]\n 46%|████▌ | 23/50 [00:04<00:05, 4.82it/s]\n 48%|████▊ | 24/50 [00:05<00:05, 4.76it/s]\n 50%|█████ | 25/50 [00:05<00:05, 4.78it/s]\n 52%|█████▏ | 26/50 [00:05<00:05, 4.71it/s]\n 54%|█████▍ | 27/50 [00:05<00:04, 4.79it/s]\n 56%|█████▌ | 28/50 [00:05<00:04, 4.83it/s]\n 58%|█████▊ | 29/50 [00:06<00:04, 4.82it/s]\n 60%|██████ | 30/50 [00:06<00:04, 4.72it/s]\n 62%|██████▏ | 31/50 [00:06<00:04, 4.68it/s]\n 64%|██████▍ | 32/50 [00:06<00:03, 4.77it/s]\n 66%|██████▌ | 33/50 [00:06<00:03, 4.80it/s]\n 68%|██████▊ | 34/50 [00:07<00:03, 4.80it/s]\n 70%|███████ | 35/50 [00:07<00:03, 4.70it/s]\n 72%|███████▏ | 36/50 [00:07<00:03, 4.66it/s]\n 74%|███████▍ | 37/50 [00:07<00:02, 4.72it/s]\n 76%|███████▌ | 38/50 [00:07<00:02, 4.70it/s]\n 78%|███████▊ | 39/50 [00:08<00:02, 4.72it/s]\n 80%|████████ | 40/50 [00:08<00:02, 4.66it/s]\n 82%|████████▏ | 41/50 [00:08<00:01, 4.67it/s]\n 84%|████████▍ | 42/50 [00:08<00:01, 4.70it/s]\n 86%|████████▌ | 43/50 [00:09<00:01, 4.73it/s]\n 88%|████████▊ | 44/50 [00:09<00:01, 4.68it/s]\n 90%|█████████ | 45/50 [00:09<00:01, 4.63it/s]\n 92%|█████████▏| 46/50 [00:09<00:00, 4.72it/s]\n 94%|█████████▍| 47/50 [00:09<00:00, 4.76it/s]\n 96%|█████████▌| 48/50 [00:10<00:00, 4.80it/s]\n 98%|█████████▊| 49/50 [00:10<00:00, 4.71it/s]\n100%|██████████| 50/50 [00:10<00:00, 4.65it/s]\n100%|██████████| 50/50 [00:10<00:00, 4.75it/s]", "metrics": { "predict_time": 11.653259, "total_time": 11.602221 }, "output": [ "https://replicate.delivery/pbxt/Dfpz9sCAf0ulOksuaJmjllY9GamjrDxA5eGKWbnsU3RJ5jOiA/out-0.png" ], "started_at": "2023-06-18T20:46:17.620001Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/a4alaqzbyopnow3kigat73pj4u", "cancel": "https://api.replicate.com/v1/predictions/a4alaqzbyopnow3kigat73pj4u/cancel" }, "version": "e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8" }Generated inUsing seed: 37010 using txt2img 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:11, 4.17it/s] 4%|▍ | 2/50 [00:00<00:10, 4.60it/s] 6%|▌ | 3/50 [00:00<00:09, 4.80it/s] 8%|▊ | 4/50 [00:00<00:09, 4.88it/s] 10%|█ | 5/50 [00:01<00:09, 4.81it/s] 12%|█▏ | 6/50 [00:01<00:09, 4.72it/s] 14%|█▍ | 7/50 [00:01<00:09, 4.75it/s] 16%|█▌ | 8/50 [00:01<00:08, 4.75it/s] 18%|█▊ | 9/50 [00:01<00:08, 4.81it/s] 20%|██ | 10/50 [00:02<00:08, 4.78it/s] 22%|██▏ | 11/50 [00:02<00:08, 4.72it/s] 24%|██▍ | 12/50 [00:02<00:07, 4.79it/s] 26%|██▌ | 13/50 [00:02<00:07, 4.86it/s] 28%|██▊ | 14/50 [00:02<00:07, 4.87it/s] 30%|███ | 15/50 [00:03<00:07, 4.80it/s] 32%|███▏ | 16/50 [00:03<00:07, 4.78it/s] 34%|███▍ | 17/50 [00:03<00:06, 4.84it/s] 36%|███▌ | 18/50 [00:03<00:06, 4.87it/s] 38%|███▊ | 19/50 [00:03<00:06, 4.88it/s] 40%|████ | 20/50 [00:04<00:06, 4.85it/s] 42%|████▏ | 21/50 [00:04<00:06, 4.78it/s] 44%|████▍ | 22/50 [00:04<00:05, 4.81it/s] 46%|████▌ | 23/50 [00:04<00:05, 4.82it/s] 48%|████▊ | 24/50 [00:05<00:05, 4.76it/s] 50%|█████ | 25/50 [00:05<00:05, 4.78it/s] 52%|█████▏ | 26/50 [00:05<00:05, 4.71it/s] 54%|█████▍ | 27/50 [00:05<00:04, 4.79it/s] 56%|█████▌ | 28/50 [00:05<00:04, 4.83it/s] 58%|█████▊ | 29/50 [00:06<00:04, 4.82it/s] 60%|██████ | 30/50 [00:06<00:04, 4.72it/s] 62%|██████▏ | 31/50 [00:06<00:04, 4.68it/s] 64%|██████▍ | 32/50 [00:06<00:03, 4.77it/s] 66%|██████▌ | 33/50 [00:06<00:03, 4.80it/s] 68%|██████▊ | 34/50 [00:07<00:03, 4.80it/s] 70%|███████ | 35/50 [00:07<00:03, 4.70it/s] 72%|███████▏ | 36/50 [00:07<00:03, 4.66it/s] 74%|███████▍ | 37/50 [00:07<00:02, 4.72it/s] 76%|███████▌ | 38/50 [00:07<00:02, 4.70it/s] 78%|███████▊ | 39/50 [00:08<00:02, 4.72it/s] 80%|████████ | 40/50 [00:08<00:02, 4.66it/s] 82%|████████▏ | 41/50 [00:08<00:01, 4.67it/s] 84%|████████▍ | 42/50 [00:08<00:01, 4.70it/s] 86%|████████▌ | 43/50 [00:09<00:01, 4.73it/s] 88%|████████▊ | 44/50 [00:09<00:01, 4.68it/s] 90%|█████████ | 45/50 [00:09<00:01, 4.63it/s] 92%|█████████▏| 46/50 [00:09<00:00, 4.72it/s] 94%|█████████▍| 47/50 [00:09<00:00, 4.76it/s] 96%|█████████▌| 48/50 [00:10<00:00, 4.80it/s] 98%|█████████▊| 49/50 [00:10<00:00, 4.71it/s] 100%|██████████| 50/50 [00:10<00:00, 4.65it/s] 100%|██████████| 50/50 [00:10<00:00, 4.75it/s]Prediction
cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8IDirhijrjbwvyyrrzixoeg6pgpnqStatusSucceededSourceWebHardwareT4Total durationCreatedInput
- width
- 512
- height
- 512
- prompt
- qdg dog, realistic shaded lighting poster by ilya kuvshinov katsuhiro otomo, magali villeneuve, artgerm, jeremy lipkin and michael garmash and rob rey
- scheduler
- DDIM
- num_outputs
- 1
- guidance_scale
- 7.5
- negative_prompt
- cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 512, "height": 512, "prompt": "qdg dog, realistic shaded lighting poster by ilya kuvshinov katsuhiro otomo, magali villeneuve, artgerm, jeremy lipkin and michael garmash and rob rey", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", { input: { width: 512, height: 512, prompt: "qdg dog, realistic shaded lighting poster by ilya kuvshinov katsuhiro otomo, magali villeneuve, artgerm, jeremy lipkin and michael garmash and rob rey", scheduler: "DDIM", num_outputs: 1, guidance_scale: 7.5, negative_prompt: "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", prompt_strength: 0.8, num_inference_steps: 50 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", input={ "width": 512, "height": 512, "prompt": "qdg dog, realistic shaded lighting poster by ilya kuvshinov katsuhiro otomo, magali villeneuve, artgerm, jeremy lipkin and michael garmash and rob rey", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } ) # To access the file URL: print(output[0].url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output[0].read())To learn more, take a look at the guide on getting started with Python.
Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", "input": { "width": 512, "height": 512, "prompt": "qdg dog, realistic shaded lighting poster by ilya kuvshinov katsuhiro otomo, magali villeneuve, artgerm, jeremy lipkin and michael garmash and rob rey", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8 \ -i 'width=512' \ -i 'height=512' \ -i 'prompt="qdg dog, realistic shaded lighting poster by ilya kuvshinov katsuhiro otomo, magali villeneuve, artgerm, jeremy lipkin and michael garmash and rob rey"' \ -i 'scheduler="DDIM"' \ -i 'num_outputs=1' \ -i 'guidance_scale=7.5' \ -i 'negative_prompt="cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark"' \ -i 'prompt_strength=0.8' \ -i 'num_inference_steps=50'To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 512, "height": 512, "prompt": "qdg dog, realistic shaded lighting poster by ilya kuvshinov katsuhiro otomo, magali villeneuve, artgerm, jeremy lipkin and michael garmash and rob rey", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-06-18T20:47:05.059531Z", "created_at": "2023-06-18T20:46:53.126426Z", "data_removed": false, "error": null, "id": "irhijrjbwvyyrrzixoeg6pgpnq", "input": { "width": 512, "height": 512, "prompt": "qdg dog, realistic shaded lighting poster by ilya kuvshinov katsuhiro otomo, magali villeneuve, artgerm, jeremy lipkin and michael garmash and rob rey", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 57625\nusing txt2img\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:11, 4.11it/s]\n 4%|▍ | 2/50 [00:00<00:10, 4.49it/s]\n 6%|▌ | 3/50 [00:00<00:10, 4.61it/s]\n 8%|▊ | 4/50 [00:00<00:09, 4.71it/s]\n 10%|█ | 5/50 [00:01<00:09, 4.58it/s]\n 12%|█▏ | 6/50 [00:01<00:09, 4.57it/s]\n 14%|█▍ | 7/50 [00:01<00:09, 4.69it/s]\n 16%|█▌ | 8/50 [00:01<00:08, 4.72it/s]\n 18%|█▊ | 9/50 [00:01<00:08, 4.70it/s]\n 20%|██ | 10/50 [00:02<00:08, 4.60it/s]\n 22%|██▏ | 11/50 [00:02<00:08, 4.62it/s]\n 24%|██▍ | 12/50 [00:02<00:08, 4.69it/s]\n 26%|██▌ | 13/50 [00:02<00:07, 4.75it/s]\n 28%|██▊ | 14/50 [00:03<00:07, 4.65it/s]\n 30%|███ | 15/50 [00:03<00:07, 4.58it/s]\n 32%|███▏ | 16/50 [00:03<00:07, 4.62it/s]\n 34%|███▍ | 17/50 [00:03<00:07, 4.71it/s]\n 36%|███▌ | 18/50 [00:03<00:06, 4.70it/s]\n 38%|███▊ | 19/50 [00:04<00:06, 4.65it/s]\n 40%|████ | 20/50 [00:04<00:06, 4.59it/s]\n 42%|████▏ | 21/50 [00:04<00:06, 4.63it/s]\n 44%|████▍ | 22/50 [00:04<00:05, 4.69it/s]\n 46%|████▌ | 23/50 [00:04<00:05, 4.62it/s]\n 48%|████▊ | 24/50 [00:05<00:05, 4.59it/s]\n 50%|█████ | 25/50 [00:05<00:05, 4.58it/s]\n 52%|█████▏ | 26/50 [00:05<00:05, 4.61it/s]\n 54%|█████▍ | 27/50 [00:05<00:04, 4.63it/s]\n 56%|█████▌ | 28/50 [00:06<00:04, 4.60it/s]\n 58%|█████▊ | 29/50 [00:06<00:04, 4.59it/s]\n 60%|██████ | 30/50 [00:06<00:04, 4.62it/s]\n 62%|██████▏ | 31/50 [00:06<00:04, 4.63it/s]\n 64%|██████▍ | 32/50 [00:06<00:03, 4.66it/s]\n 66%|██████▌ | 33/50 [00:07<00:03, 4.62it/s]\n 68%|██████▊ | 34/50 [00:07<00:03, 4.61it/s]\n 70%|███████ | 35/50 [00:07<00:03, 4.61it/s]\n 72%|███████▏ | 36/50 [00:07<00:03, 4.61it/s]\n 74%|███████▍ | 37/50 [00:07<00:02, 4.62it/s]\n 76%|███████▌ | 38/50 [00:08<00:02, 4.60it/s]\n 78%|███████▊ | 39/50 [00:08<00:02, 4.63it/s]\n 80%|████████ | 40/50 [00:08<00:02, 4.65it/s]\n 82%|████████▏ | 41/50 [00:08<00:01, 4.67it/s]\n 84%|████████▍ | 42/50 [00:09<00:01, 4.65it/s]\n 86%|████████▌ | 43/50 [00:09<00:01, 4.62it/s]\n 88%|████████▊ | 44/50 [00:09<00:01, 4.61it/s]\n 90%|█████████ | 45/50 [00:09<00:01, 4.65it/s]\n 92%|█████████▏| 46/50 [00:09<00:00, 4.62it/s]\n 94%|█████████▍| 47/50 [00:10<00:00, 4.58it/s]\n 96%|█████████▌| 48/50 [00:10<00:00, 4.59it/s]\n 98%|█████████▊| 49/50 [00:10<00:00, 4.64it/s]\n100%|██████████| 50/50 [00:10<00:00, 4.61it/s]\n100%|██████████| 50/50 [00:10<00:00, 4.63it/s]", "metrics": { "predict_time": 11.938173, "total_time": 11.933105 }, "output": [ "https://replicate.delivery/pbxt/40iAVNj4QdYtEF0a9SaCUBobGxreMs5jYRz2OEfO5WmI9RHRA/out-0.png" ], "started_at": "2023-06-18T20:46:53.121358Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/irhijrjbwvyyrrzixoeg6pgpnq", "cancel": "https://api.replicate.com/v1/predictions/irhijrjbwvyyrrzixoeg6pgpnq/cancel" }, "version": "e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8" }Generated inUsing seed: 57625 using txt2img 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:11, 4.11it/s] 4%|▍ | 2/50 [00:00<00:10, 4.49it/s] 6%|▌ | 3/50 [00:00<00:10, 4.61it/s] 8%|▊ | 4/50 [00:00<00:09, 4.71it/s] 10%|█ | 5/50 [00:01<00:09, 4.58it/s] 12%|█▏ | 6/50 [00:01<00:09, 4.57it/s] 14%|█▍ | 7/50 [00:01<00:09, 4.69it/s] 16%|█▌ | 8/50 [00:01<00:08, 4.72it/s] 18%|█▊ | 9/50 [00:01<00:08, 4.70it/s] 20%|██ | 10/50 [00:02<00:08, 4.60it/s] 22%|██▏ | 11/50 [00:02<00:08, 4.62it/s] 24%|██▍ | 12/50 [00:02<00:08, 4.69it/s] 26%|██▌ | 13/50 [00:02<00:07, 4.75it/s] 28%|██▊ | 14/50 [00:03<00:07, 4.65it/s] 30%|███ | 15/50 [00:03<00:07, 4.58it/s] 32%|███▏ | 16/50 [00:03<00:07, 4.62it/s] 34%|███▍ | 17/50 [00:03<00:07, 4.71it/s] 36%|███▌ | 18/50 [00:03<00:06, 4.70it/s] 38%|███▊ | 19/50 [00:04<00:06, 4.65it/s] 40%|████ | 20/50 [00:04<00:06, 4.59it/s] 42%|████▏ | 21/50 [00:04<00:06, 4.63it/s] 44%|████▍ | 22/50 [00:04<00:05, 4.69it/s] 46%|████▌ | 23/50 [00:04<00:05, 4.62it/s] 48%|████▊ | 24/50 [00:05<00:05, 4.59it/s] 50%|█████ | 25/50 [00:05<00:05, 4.58it/s] 52%|█████▏ | 26/50 [00:05<00:05, 4.61it/s] 54%|█████▍ | 27/50 [00:05<00:04, 4.63it/s] 56%|█████▌ | 28/50 [00:06<00:04, 4.60it/s] 58%|█████▊ | 29/50 [00:06<00:04, 4.59it/s] 60%|██████ | 30/50 [00:06<00:04, 4.62it/s] 62%|██████▏ | 31/50 [00:06<00:04, 4.63it/s] 64%|██████▍ | 32/50 [00:06<00:03, 4.66it/s] 66%|██████▌ | 33/50 [00:07<00:03, 4.62it/s] 68%|██████▊ | 34/50 [00:07<00:03, 4.61it/s] 70%|███████ | 35/50 [00:07<00:03, 4.61it/s] 72%|███████▏ | 36/50 [00:07<00:03, 4.61it/s] 74%|███████▍ | 37/50 [00:07<00:02, 4.62it/s] 76%|███████▌ | 38/50 [00:08<00:02, 4.60it/s] 78%|███████▊ | 39/50 [00:08<00:02, 4.63it/s] 80%|████████ | 40/50 [00:08<00:02, 4.65it/s] 82%|████████▏ | 41/50 [00:08<00:01, 4.67it/s] 84%|████████▍ | 42/50 [00:09<00:01, 4.65it/s] 86%|████████▌ | 43/50 [00:09<00:01, 4.62it/s] 88%|████████▊ | 44/50 [00:09<00:01, 4.61it/s] 90%|█████████ | 45/50 [00:09<00:01, 4.65it/s] 92%|█████████▏| 46/50 [00:09<00:00, 4.62it/s] 94%|█████████▍| 47/50 [00:10<00:00, 4.58it/s] 96%|█████████▌| 48/50 [00:10<00:00, 4.59it/s] 98%|█████████▊| 49/50 [00:10<00:00, 4.64it/s] 100%|██████████| 50/50 [00:10<00:00, 4.61it/s] 100%|██████████| 50/50 [00:10<00:00, 4.63it/s]Prediction
cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8IDxb5zz3jbpps5cpvt37g6emegsyStatusSucceededSourceWebHardwareT4Total durationCreatedInput
- width
- 512
- height
- 512
- prompt
- qdg dog, realistic shaded lighting poster by ilya kuvshinov katsuhiro otomo, magali villeneuve, artgerm, jeremy lipkin and michael garmash and rob rey
- scheduler
- DDIM
- num_outputs
- 1
- guidance_scale
- 7.5
- negative_prompt
- cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 512, "height": 512, "prompt": "qdg dog, realistic shaded lighting poster by ilya kuvshinov katsuhiro otomo, magali villeneuve, artgerm, jeremy lipkin and michael garmash and rob rey", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", { input: { width: 512, height: 512, prompt: "qdg dog, realistic shaded lighting poster by ilya kuvshinov katsuhiro otomo, magali villeneuve, artgerm, jeremy lipkin and michael garmash and rob rey", scheduler: "DDIM", num_outputs: 1, guidance_scale: 7.5, negative_prompt: "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", prompt_strength: 0.8, num_inference_steps: 50 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", input={ "width": 512, "height": 512, "prompt": "qdg dog, realistic shaded lighting poster by ilya kuvshinov katsuhiro otomo, magali villeneuve, artgerm, jeremy lipkin and michael garmash and rob rey", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } ) # To access the file URL: print(output[0].url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output[0].read())To learn more, take a look at the guide on getting started with Python.
Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", "input": { "width": 512, "height": 512, "prompt": "qdg dog, realistic shaded lighting poster by ilya kuvshinov katsuhiro otomo, magali villeneuve, artgerm, jeremy lipkin and michael garmash and rob rey", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8 \ -i 'width=512' \ -i 'height=512' \ -i 'prompt="qdg dog, realistic shaded lighting poster by ilya kuvshinov katsuhiro otomo, magali villeneuve, artgerm, jeremy lipkin and michael garmash and rob rey"' \ -i 'scheduler="DDIM"' \ -i 'num_outputs=1' \ -i 'guidance_scale=7.5' \ -i 'negative_prompt="cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark"' \ -i 'prompt_strength=0.8' \ -i 'num_inference_steps=50'To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 512, "height": 512, "prompt": "qdg dog, realistic shaded lighting poster by ilya kuvshinov katsuhiro otomo, magali villeneuve, artgerm, jeremy lipkin and michael garmash and rob rey", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-06-18T20:47:24.565105Z", "created_at": "2023-06-18T20:47:12.777914Z", "data_removed": false, "error": null, "id": "xb5zz3jbpps5cpvt37g6emegsy", "input": { "width": 512, "height": 512, "prompt": "qdg dog, realistic shaded lighting poster by ilya kuvshinov katsuhiro otomo, magali villeneuve, artgerm, jeremy lipkin and michael garmash and rob rey", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 42461\nusing txt2img\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:13, 3.74it/s]\n 4%|▍ | 2/50 [00:00<00:11, 4.33it/s]\n 6%|▌ | 3/50 [00:00<00:10, 4.60it/s]\n 8%|▊ | 4/50 [00:00<00:09, 4.73it/s]\n 10%|█ | 5/50 [00:01<00:09, 4.79it/s]\n 12%|█▏ | 6/50 [00:01<00:09, 4.64it/s]\n 14%|█▍ | 7/50 [00:01<00:09, 4.65it/s]\n 16%|█▌ | 8/50 [00:01<00:08, 4.74it/s]\n 18%|█▊ | 9/50 [00:01<00:08, 4.79it/s]\n 20%|██ | 10/50 [00:02<00:08, 4.75it/s]\n 22%|██▏ | 11/50 [00:02<00:08, 4.69it/s]\n 24%|██▍ | 12/50 [00:02<00:08, 4.68it/s]\n 26%|██▌ | 13/50 [00:02<00:07, 4.76it/s]\n 28%|██▊ | 14/50 [00:02<00:07, 4.81it/s]\n 30%|███ | 15/50 [00:03<00:07, 4.74it/s]\n 32%|███▏ | 16/50 [00:03<00:07, 4.71it/s]\n 34%|███▍ | 17/50 [00:03<00:07, 4.71it/s]\n 36%|███▌ | 18/50 [00:03<00:06, 4.76it/s]\n 38%|███▊ | 19/50 [00:04<00:06, 4.77it/s]\n 40%|████ | 20/50 [00:04<00:06, 4.70it/s]\n 42%|████▏ | 21/50 [00:04<00:06, 4.65it/s]\n 44%|████▍ | 22/50 [00:04<00:06, 4.66it/s]\n 46%|████▌ | 23/50 [00:04<00:05, 4.71it/s]\n 48%|████▊ | 24/50 [00:05<00:05, 4.74it/s]\n 50%|█████ | 25/50 [00:05<00:05, 4.67it/s]\n 52%|█████▏ | 26/50 [00:05<00:05, 4.72it/s]\n 54%|█████▍ | 27/50 [00:05<00:04, 4.69it/s]\n 56%|█████▌ | 28/50 [00:05<00:04, 4.74it/s]\n 58%|█████▊ | 29/50 [00:06<00:04, 4.69it/s]\n 60%|██████ | 30/50 [00:06<00:04, 4.63it/s]\n 62%|██████▏ | 31/50 [00:06<00:04, 4.67it/s]\n 64%|██████▍ | 32/50 [00:06<00:03, 4.65it/s]\n 66%|██████▌ | 33/50 [00:07<00:03, 4.72it/s]\n 68%|██████▊ | 34/50 [00:07<00:03, 4.66it/s]\n 70%|███████ | 35/50 [00:07<00:03, 4.68it/s]\n 72%|███████▏ | 36/50 [00:07<00:02, 4.69it/s]\n 74%|███████▍ | 37/50 [00:07<00:02, 4.74it/s]\n 76%|███████▌ | 38/50 [00:08<00:02, 4.71it/s]\n 78%|███████▊ | 39/50 [00:08<00:02, 4.67it/s]\n 80%|████████ | 40/50 [00:08<00:02, 4.70it/s]\n 82%|████████▏ | 41/50 [00:08<00:01, 4.71it/s]\n 84%|████████▍ | 42/50 [00:08<00:01, 4.71it/s]\n 86%|████████▌ | 43/50 [00:09<00:01, 4.73it/s]\n 88%|████████▊ | 44/50 [00:09<00:01, 4.67it/s]\n 90%|█████████ | 45/50 [00:09<00:01, 4.64it/s]\n 92%|█████████▏| 46/50 [00:09<00:00, 4.72it/s]\n 94%|█████████▍| 47/50 [00:10<00:00, 4.72it/s]\n 96%|█████████▌| 48/50 [00:10<00:00, 4.70it/s]\n 98%|█████████▊| 49/50 [00:10<00:00, 4.66it/s]\n100%|██████████| 50/50 [00:10<00:00, 4.69it/s]\n100%|██████████| 50/50 [00:10<00:00, 4.69it/s]", "metrics": { "predict_time": 11.816772, "total_time": 11.787191 }, "output": [ "https://replicate.delivery/pbxt/NUN0fDjbZ7TLbCYBI22PE0OJX584gum2RmbQ1fWkXpf26jOiA/out-0.png" ], "started_at": "2023-06-18T20:47:12.748333Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/xb5zz3jbpps5cpvt37g6emegsy", "cancel": "https://api.replicate.com/v1/predictions/xb5zz3jbpps5cpvt37g6emegsy/cancel" }, "version": "e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8" }Generated inUsing seed: 42461 using txt2img 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:13, 3.74it/s] 4%|▍ | 2/50 [00:00<00:11, 4.33it/s] 6%|▌ | 3/50 [00:00<00:10, 4.60it/s] 8%|▊ | 4/50 [00:00<00:09, 4.73it/s] 10%|█ | 5/50 [00:01<00:09, 4.79it/s] 12%|█▏ | 6/50 [00:01<00:09, 4.64it/s] 14%|█▍ | 7/50 [00:01<00:09, 4.65it/s] 16%|█▌ | 8/50 [00:01<00:08, 4.74it/s] 18%|█▊ | 9/50 [00:01<00:08, 4.79it/s] 20%|██ | 10/50 [00:02<00:08, 4.75it/s] 22%|██▏ | 11/50 [00:02<00:08, 4.69it/s] 24%|██▍ | 12/50 [00:02<00:08, 4.68it/s] 26%|██▌ | 13/50 [00:02<00:07, 4.76it/s] 28%|██▊ | 14/50 [00:02<00:07, 4.81it/s] 30%|███ | 15/50 [00:03<00:07, 4.74it/s] 32%|███▏ | 16/50 [00:03<00:07, 4.71it/s] 34%|███▍ | 17/50 [00:03<00:07, 4.71it/s] 36%|███▌ | 18/50 [00:03<00:06, 4.76it/s] 38%|███▊ | 19/50 [00:04<00:06, 4.77it/s] 40%|████ | 20/50 [00:04<00:06, 4.70it/s] 42%|████▏ | 21/50 [00:04<00:06, 4.65it/s] 44%|████▍ | 22/50 [00:04<00:06, 4.66it/s] 46%|████▌ | 23/50 [00:04<00:05, 4.71it/s] 48%|████▊ | 24/50 [00:05<00:05, 4.74it/s] 50%|█████ | 25/50 [00:05<00:05, 4.67it/s] 52%|█████▏ | 26/50 [00:05<00:05, 4.72it/s] 54%|█████▍ | 27/50 [00:05<00:04, 4.69it/s] 56%|█████▌ | 28/50 [00:05<00:04, 4.74it/s] 58%|█████▊ | 29/50 [00:06<00:04, 4.69it/s] 60%|██████ | 30/50 [00:06<00:04, 4.63it/s] 62%|██████▏ | 31/50 [00:06<00:04, 4.67it/s] 64%|██████▍ | 32/50 [00:06<00:03, 4.65it/s] 66%|██████▌ | 33/50 [00:07<00:03, 4.72it/s] 68%|██████▊ | 34/50 [00:07<00:03, 4.66it/s] 70%|███████ | 35/50 [00:07<00:03, 4.68it/s] 72%|███████▏ | 36/50 [00:07<00:02, 4.69it/s] 74%|███████▍ | 37/50 [00:07<00:02, 4.74it/s] 76%|███████▌ | 38/50 [00:08<00:02, 4.71it/s] 78%|███████▊ | 39/50 [00:08<00:02, 4.67it/s] 80%|████████ | 40/50 [00:08<00:02, 4.70it/s] 82%|████████▏ | 41/50 [00:08<00:01, 4.71it/s] 84%|████████▍ | 42/50 [00:08<00:01, 4.71it/s] 86%|████████▌ | 43/50 [00:09<00:01, 4.73it/s] 88%|████████▊ | 44/50 [00:09<00:01, 4.67it/s] 90%|█████████ | 45/50 [00:09<00:01, 4.64it/s] 92%|█████████▏| 46/50 [00:09<00:00, 4.72it/s] 94%|█████████▍| 47/50 [00:10<00:00, 4.72it/s] 96%|█████████▌| 48/50 [00:10<00:00, 4.70it/s] 98%|█████████▊| 49/50 [00:10<00:00, 4.66it/s] 100%|██████████| 50/50 [00:10<00:00, 4.69it/s] 100%|██████████| 50/50 [00:10<00:00, 4.69it/s]Prediction
cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8ID3lza2ebbus5q73o3j6lkwpwuj4StatusSucceededSourceWebHardwareT4Total durationCreatedInput
- width
- 512
- height
- 512
- prompt
- qdg dog, cyberpunk poster by katsuhiro otomo
- scheduler
- DDIM
- num_outputs
- 1
- guidance_scale
- 7.5
- negative_prompt
- cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 512, "height": 512, "prompt": "qdg dog, cyberpunk poster by katsuhiro otomo", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", { input: { width: 512, height: 512, prompt: "qdg dog, cyberpunk poster by katsuhiro otomo", scheduler: "DDIM", num_outputs: 1, guidance_scale: 7.5, negative_prompt: "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", prompt_strength: 0.8, num_inference_steps: 50 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", input={ "width": 512, "height": 512, "prompt": "qdg dog, cyberpunk poster by katsuhiro otomo", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } ) # To access the file URL: print(output[0].url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output[0].read())To learn more, take a look at the guide on getting started with Python.
Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", "input": { "width": 512, "height": 512, "prompt": "qdg dog, cyberpunk poster by katsuhiro otomo", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8 \ -i 'width=512' \ -i 'height=512' \ -i 'prompt="qdg dog, cyberpunk poster by katsuhiro otomo"' \ -i 'scheduler="DDIM"' \ -i 'num_outputs=1' \ -i 'guidance_scale=7.5' \ -i 'negative_prompt="cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark"' \ -i 'prompt_strength=0.8' \ -i 'num_inference_steps=50'To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 512, "height": 512, "prompt": "qdg dog, cyberpunk poster by katsuhiro otomo", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-06-18T20:51:26.290858Z", "created_at": "2023-06-18T20:51:13.918330Z", "data_removed": false, "error": null, "id": "3lza2ebbus5q73o3j6lkwpwuj4", "input": { "width": 512, "height": 512, "prompt": "qdg dog, cyberpunk poster by katsuhiro otomo", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 64615\nusing txt2img\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:12, 3.80it/s]\n 4%|▍ | 2/50 [00:00<00:11, 4.29it/s]\n 6%|▌ | 3/50 [00:00<00:10, 4.54it/s]\n 8%|▊ | 4/50 [00:00<00:09, 4.63it/s]\n 10%|█ | 5/50 [00:01<00:10, 4.47it/s]\n 12%|█▏ | 6/50 [00:01<00:09, 4.45it/s]\n 14%|█▍ | 7/50 [00:01<00:09, 4.50it/s]\n 16%|█▌ | 8/50 [00:01<00:09, 4.57it/s]\n 18%|█▊ | 9/50 [00:01<00:08, 4.60it/s]\n 20%|██ | 10/50 [00:02<00:09, 4.44it/s]\n 22%|██▏ | 11/50 [00:02<00:08, 4.46it/s]\n 24%|██▍ | 12/50 [00:02<00:08, 4.53it/s]\n 26%|██▌ | 13/50 [00:02<00:08, 4.58it/s]\n 28%|██▊ | 14/50 [00:03<00:07, 4.53it/s]\n 30%|███ | 15/50 [00:03<00:07, 4.47it/s]\n 32%|███▏ | 16/50 [00:03<00:07, 4.48it/s]\n 34%|███▍ | 17/50 [00:03<00:07, 4.54it/s]\n 36%|███▌ | 18/50 [00:04<00:07, 4.54it/s]\n 38%|███▊ | 19/50 [00:04<00:06, 4.48it/s]\n 40%|████ | 20/50 [00:04<00:06, 4.48it/s]\n 42%|████▏ | 21/50 [00:04<00:06, 4.50it/s]\n 44%|████▍ | 22/50 [00:04<00:06, 4.50it/s]\n 46%|████▌ | 23/50 [00:05<00:06, 4.44it/s]\n 48%|████▊ | 24/50 [00:05<00:05, 4.42it/s]\n 50%|█████ | 25/50 [00:05<00:05, 4.45it/s]\n 52%|█████▏ | 26/50 [00:05<00:05, 4.50it/s]\n 54%|█████▍ | 27/50 [00:06<00:05, 4.51it/s]\n 56%|█████▌ | 28/50 [00:06<00:04, 4.44it/s]\n 58%|█████▊ | 29/50 [00:06<00:04, 4.44it/s]\n 60%|██████ | 30/50 [00:06<00:04, 4.44it/s]\n 62%|██████▏ | 31/50 [00:06<00:04, 4.47it/s]\n 64%|██████▍ | 32/50 [00:07<00:04, 4.42it/s]\n 66%|██████▌ | 33/50 [00:07<00:03, 4.40it/s]\n 68%|██████▊ | 34/50 [00:07<00:03, 4.42it/s]\n 70%|███████ | 35/50 [00:07<00:03, 4.43it/s]\n 72%|███████▏ | 36/50 [00:08<00:03, 4.41it/s]\n 74%|███████▍ | 37/50 [00:08<00:02, 4.40it/s]\n 76%|███████▌ | 38/50 [00:08<00:02, 4.41it/s]\n 78%|███████▊ | 39/50 [00:08<00:02, 4.44it/s]\n 80%|████████ | 40/50 [00:08<00:02, 4.46it/s]\n 82%|████████▏ | 41/50 [00:09<00:02, 4.43it/s]\n 84%|████████▍ | 42/50 [00:09<00:01, 4.39it/s]\n 86%|████████▌ | 43/50 [00:09<00:01, 4.38it/s]\n 88%|████████▊ | 44/50 [00:09<00:01, 4.40it/s]\n 90%|█████████ | 45/50 [00:10<00:01, 4.36it/s]\n 92%|█████████▏| 46/50 [00:10<00:00, 4.39it/s]\n 94%|█████████▍| 47/50 [00:10<00:00, 4.40it/s]\n 96%|█████████▌| 48/50 [00:10<00:00, 4.42it/s]\n 98%|█████████▊| 49/50 [00:11<00:00, 4.41it/s]\n100%|██████████| 50/50 [00:11<00:00, 4.39it/s]\n100%|██████████| 50/50 [00:11<00:00, 4.45it/s]", "metrics": { "predict_time": 12.393889, "total_time": 12.372528 }, "output": [ "https://replicate.delivery/pbxt/oPe1eqIvP0qWoU5qacf5gni65MrIDrWTsYfiAyat4eHuJQ6IC/out-0.png" ], "started_at": "2023-06-18T20:51:13.896969Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/3lza2ebbus5q73o3j6lkwpwuj4", "cancel": "https://api.replicate.com/v1/predictions/3lza2ebbus5q73o3j6lkwpwuj4/cancel" }, "version": "e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8" }Generated inUsing seed: 64615 using txt2img 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:12, 3.80it/s] 4%|▍ | 2/50 [00:00<00:11, 4.29it/s] 6%|▌ | 3/50 [00:00<00:10, 4.54it/s] 8%|▊ | 4/50 [00:00<00:09, 4.63it/s] 10%|█ | 5/50 [00:01<00:10, 4.47it/s] 12%|█▏ | 6/50 [00:01<00:09, 4.45it/s] 14%|█▍ | 7/50 [00:01<00:09, 4.50it/s] 16%|█▌ | 8/50 [00:01<00:09, 4.57it/s] 18%|█▊ | 9/50 [00:01<00:08, 4.60it/s] 20%|██ | 10/50 [00:02<00:09, 4.44it/s] 22%|██▏ | 11/50 [00:02<00:08, 4.46it/s] 24%|██▍ | 12/50 [00:02<00:08, 4.53it/s] 26%|██▌ | 13/50 [00:02<00:08, 4.58it/s] 28%|██▊ | 14/50 [00:03<00:07, 4.53it/s] 30%|███ | 15/50 [00:03<00:07, 4.47it/s] 32%|███▏ | 16/50 [00:03<00:07, 4.48it/s] 34%|███▍ | 17/50 [00:03<00:07, 4.54it/s] 36%|███▌ | 18/50 [00:04<00:07, 4.54it/s] 38%|███▊ | 19/50 [00:04<00:06, 4.48it/s] 40%|████ | 20/50 [00:04<00:06, 4.48it/s] 42%|████▏ | 21/50 [00:04<00:06, 4.50it/s] 44%|████▍ | 22/50 [00:04<00:06, 4.50it/s] 46%|████▌ | 23/50 [00:05<00:06, 4.44it/s] 48%|████▊ | 24/50 [00:05<00:05, 4.42it/s] 50%|█████ | 25/50 [00:05<00:05, 4.45it/s] 52%|█████▏ | 26/50 [00:05<00:05, 4.50it/s] 54%|█████▍ | 27/50 [00:06<00:05, 4.51it/s] 56%|█████▌ | 28/50 [00:06<00:04, 4.44it/s] 58%|█████▊ | 29/50 [00:06<00:04, 4.44it/s] 60%|██████ | 30/50 [00:06<00:04, 4.44it/s] 62%|██████▏ | 31/50 [00:06<00:04, 4.47it/s] 64%|██████▍ | 32/50 [00:07<00:04, 4.42it/s] 66%|██████▌ | 33/50 [00:07<00:03, 4.40it/s] 68%|██████▊ | 34/50 [00:07<00:03, 4.42it/s] 70%|███████ | 35/50 [00:07<00:03, 4.43it/s] 72%|███████▏ | 36/50 [00:08<00:03, 4.41it/s] 74%|███████▍ | 37/50 [00:08<00:02, 4.40it/s] 76%|███████▌ | 38/50 [00:08<00:02, 4.41it/s] 78%|███████▊ | 39/50 [00:08<00:02, 4.44it/s] 80%|████████ | 40/50 [00:08<00:02, 4.46it/s] 82%|████████▏ | 41/50 [00:09<00:02, 4.43it/s] 84%|████████▍ | 42/50 [00:09<00:01, 4.39it/s] 86%|████████▌ | 43/50 [00:09<00:01, 4.38it/s] 88%|████████▊ | 44/50 [00:09<00:01, 4.40it/s] 90%|█████████ | 45/50 [00:10<00:01, 4.36it/s] 92%|█████████▏| 46/50 [00:10<00:00, 4.39it/s] 94%|█████████▍| 47/50 [00:10<00:00, 4.40it/s] 96%|█████████▌| 48/50 [00:10<00:00, 4.42it/s] 98%|█████████▊| 49/50 [00:11<00:00, 4.41it/s] 100%|██████████| 50/50 [00:11<00:00, 4.39it/s] 100%|██████████| 50/50 [00:11<00:00, 4.45it/s]Prediction
cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8IDb5ufuubbfkgaaivzkl2mrckrjuStatusSucceededSourceWebHardwareT4Total durationCreatedInput
- width
- 512
- height
- 512
- prompt
- qdg dog, cyberpunk poster by katsuhiro otomo
- scheduler
- DDIM
- num_outputs
- 1
- guidance_scale
- 7.5
- negative_prompt
- cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 512, "height": 512, "prompt": "qdg dog, cyberpunk poster by katsuhiro otomo", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", { input: { width: 512, height: 512, prompt: "qdg dog, cyberpunk poster by katsuhiro otomo", scheduler: "DDIM", num_outputs: 1, guidance_scale: 7.5, negative_prompt: "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", prompt_strength: 0.8, num_inference_steps: 50 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", input={ "width": 512, "height": 512, "prompt": "qdg dog, cyberpunk poster by katsuhiro otomo", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } ) # To access the file URL: print(output[0].url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output[0].read())To learn more, take a look at the guide on getting started with Python.
Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", "input": { "width": 512, "height": 512, "prompt": "qdg dog, cyberpunk poster by katsuhiro otomo", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8 \ -i 'width=512' \ -i 'height=512' \ -i 'prompt="qdg dog, cyberpunk poster by katsuhiro otomo"' \ -i 'scheduler="DDIM"' \ -i 'num_outputs=1' \ -i 'guidance_scale=7.5' \ -i 'negative_prompt="cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark"' \ -i 'prompt_strength=0.8' \ -i 'num_inference_steps=50'To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 512, "height": 512, "prompt": "qdg dog, cyberpunk poster by katsuhiro otomo", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-06-18T20:52:06.444747Z", "created_at": "2023-06-18T20:51:54.749047Z", "data_removed": false, "error": null, "id": "b5ufuubbfkgaaivzkl2mrckrju", "input": { "width": 512, "height": 512, "prompt": "qdg dog, cyberpunk poster by katsuhiro otomo", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 7492\nusing txt2img\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:13, 3.69it/s]\n 4%|▍ | 2/50 [00:00<00:10, 4.38it/s]\n 6%|▌ | 3/50 [00:00<00:10, 4.66it/s]\n 8%|▊ | 4/50 [00:00<00:09, 4.75it/s]\n 10%|█ | 5/50 [00:01<00:09, 4.79it/s]\n 12%|█▏ | 6/50 [00:01<00:09, 4.68it/s]\n 14%|█▍ | 7/50 [00:01<00:09, 4.75it/s]\n 16%|█▌ | 8/50 [00:01<00:08, 4.84it/s]\n 18%|█▊ | 9/50 [00:01<00:08, 4.89it/s]\n 20%|██ | 10/50 [00:02<00:08, 4.85it/s]\n 22%|██▏ | 11/50 [00:02<00:08, 4.74it/s]\n 24%|██▍ | 12/50 [00:02<00:07, 4.77it/s]\n 26%|██▌ | 13/50 [00:02<00:07, 4.75it/s]\n 28%|██▊ | 14/50 [00:02<00:07, 4.80it/s]\n 30%|███ | 15/50 [00:03<00:07, 4.78it/s]\n 32%|███▏ | 16/50 [00:03<00:07, 4.70it/s]\n 34%|███▍ | 17/50 [00:03<00:07, 4.68it/s]\n 36%|███▌ | 18/50 [00:03<00:06, 4.74it/s]\n 38%|███▊ | 19/50 [00:04<00:06, 4.79it/s]\n 40%|████ | 20/50 [00:04<00:06, 4.79it/s]\n 42%|████▏ | 21/50 [00:04<00:06, 4.73it/s]\n 44%|████▍ | 22/50 [00:04<00:05, 4.76it/s]\n 46%|████▌ | 23/50 [00:04<00:05, 4.77it/s]\n 48%|████▊ | 24/50 [00:05<00:05, 4.75it/s]\n 50%|█████ | 25/50 [00:05<00:05, 4.69it/s]\n 52%|█████▏ | 26/50 [00:05<00:05, 4.72it/s]\n 54%|█████▍ | 27/50 [00:05<00:04, 4.73it/s]\n 56%|█████▌ | 28/50 [00:05<00:04, 4.72it/s]\n 58%|█████▊ | 29/50 [00:06<00:04, 4.75it/s]\n 60%|██████ | 30/50 [00:06<00:04, 4.67it/s]\n 62%|██████▏ | 31/50 [00:06<00:04, 4.64it/s]\n 64%|██████▍ | 32/50 [00:06<00:03, 4.66it/s]\n 66%|██████▌ | 33/50 [00:06<00:03, 4.67it/s]\n 68%|██████▊ | 34/50 [00:07<00:03, 4.69it/s]\n 70%|███████ | 35/50 [00:07<00:03, 4.64it/s]\n 72%|███████▏ | 36/50 [00:07<00:03, 4.63it/s]\n 74%|███████▍ | 37/50 [00:07<00:02, 4.70it/s]\n 76%|███████▌ | 38/50 [00:08<00:02, 4.73it/s]\n 78%|███████▊ | 39/50 [00:08<00:02, 4.67it/s]\n 80%|████████ | 40/50 [00:08<00:02, 4.64it/s]\n 82%|████████▏ | 41/50 [00:08<00:01, 4.68it/s]\n 84%|████████▍ | 42/50 [00:08<00:01, 4.65it/s]\n 86%|████████▌ | 43/50 [00:09<00:01, 4.66it/s]\n 88%|████████▊ | 44/50 [00:09<00:01, 4.66it/s]\n 90%|█████████ | 45/50 [00:09<00:01, 4.61it/s]\n 92%|█████████▏| 46/50 [00:09<00:00, 4.60it/s]\n 94%|█████████▍| 47/50 [00:10<00:00, 4.63it/s]\n 96%|█████████▌| 48/50 [00:10<00:00, 4.60it/s]\n 98%|█████████▊| 49/50 [00:10<00:00, 4.56it/s]\n100%|██████████| 50/50 [00:10<00:00, 4.56it/s]\n100%|██████████| 50/50 [00:10<00:00, 4.69it/s]", "metrics": { "predict_time": 11.772665, "total_time": 11.6957 }, "output": [ "https://replicate.delivery/pbxt/7mAXVMz1eO3ADyGrrUpKyFQtdiA2P1VnhkZBa94gtQ16ApjIA/out-0.png" ], "started_at": "2023-06-18T20:51:54.672082Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/b5ufuubbfkgaaivzkl2mrckrju", "cancel": "https://api.replicate.com/v1/predictions/b5ufuubbfkgaaivzkl2mrckrju/cancel" }, "version": "e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8" }Generated inUsing seed: 7492 using txt2img 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:13, 3.69it/s] 4%|▍ | 2/50 [00:00<00:10, 4.38it/s] 6%|▌ | 3/50 [00:00<00:10, 4.66it/s] 8%|▊ | 4/50 [00:00<00:09, 4.75it/s] 10%|█ | 5/50 [00:01<00:09, 4.79it/s] 12%|█▏ | 6/50 [00:01<00:09, 4.68it/s] 14%|█▍ | 7/50 [00:01<00:09, 4.75it/s] 16%|█▌ | 8/50 [00:01<00:08, 4.84it/s] 18%|█▊ | 9/50 [00:01<00:08, 4.89it/s] 20%|██ | 10/50 [00:02<00:08, 4.85it/s] 22%|██▏ | 11/50 [00:02<00:08, 4.74it/s] 24%|██▍ | 12/50 [00:02<00:07, 4.77it/s] 26%|██▌ | 13/50 [00:02<00:07, 4.75it/s] 28%|██▊ | 14/50 [00:02<00:07, 4.80it/s] 30%|███ | 15/50 [00:03<00:07, 4.78it/s] 32%|███▏ | 16/50 [00:03<00:07, 4.70it/s] 34%|███▍ | 17/50 [00:03<00:07, 4.68it/s] 36%|███▌ | 18/50 [00:03<00:06, 4.74it/s] 38%|███▊ | 19/50 [00:04<00:06, 4.79it/s] 40%|████ | 20/50 [00:04<00:06, 4.79it/s] 42%|████▏ | 21/50 [00:04<00:06, 4.73it/s] 44%|████▍ | 22/50 [00:04<00:05, 4.76it/s] 46%|████▌ | 23/50 [00:04<00:05, 4.77it/s] 48%|████▊ | 24/50 [00:05<00:05, 4.75it/s] 50%|█████ | 25/50 [00:05<00:05, 4.69it/s] 52%|█████▏ | 26/50 [00:05<00:05, 4.72it/s] 54%|█████▍ | 27/50 [00:05<00:04, 4.73it/s] 56%|█████▌ | 28/50 [00:05<00:04, 4.72it/s] 58%|█████▊ | 29/50 [00:06<00:04, 4.75it/s] 60%|██████ | 30/50 [00:06<00:04, 4.67it/s] 62%|██████▏ | 31/50 [00:06<00:04, 4.64it/s] 64%|██████▍ | 32/50 [00:06<00:03, 4.66it/s] 66%|██████▌ | 33/50 [00:06<00:03, 4.67it/s] 68%|██████▊ | 34/50 [00:07<00:03, 4.69it/s] 70%|███████ | 35/50 [00:07<00:03, 4.64it/s] 72%|███████▏ | 36/50 [00:07<00:03, 4.63it/s] 74%|███████▍ | 37/50 [00:07<00:02, 4.70it/s] 76%|███████▌ | 38/50 [00:08<00:02, 4.73it/s] 78%|███████▊ | 39/50 [00:08<00:02, 4.67it/s] 80%|████████ | 40/50 [00:08<00:02, 4.64it/s] 82%|████████▏ | 41/50 [00:08<00:01, 4.68it/s] 84%|████████▍ | 42/50 [00:08<00:01, 4.65it/s] 86%|████████▌ | 43/50 [00:09<00:01, 4.66it/s] 88%|████████▊ | 44/50 [00:09<00:01, 4.66it/s] 90%|█████████ | 45/50 [00:09<00:01, 4.61it/s] 92%|█████████▏| 46/50 [00:09<00:00, 4.60it/s] 94%|█████████▍| 47/50 [00:10<00:00, 4.63it/s] 96%|█████████▌| 48/50 [00:10<00:00, 4.60it/s] 98%|█████████▊| 49/50 [00:10<00:00, 4.56it/s] 100%|██████████| 50/50 [00:10<00:00, 4.56it/s] 100%|██████████| 50/50 [00:10<00:00, 4.69it/s]Prediction
cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8IDyu6aqijbbdlraonvg5j2olwe2mStatusSucceededSourceWebHardwareT4Total durationCreatedInput
- width
- 512
- height
- 512
- prompt
- qdg dog, cyberpunk poster by katsuhiro otomo
- scheduler
- DDIM
- num_outputs
- 1
- guidance_scale
- 7.5
- negative_prompt
- cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 512, "height": 512, "prompt": "qdg dog, cyberpunk poster by katsuhiro otomo", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", { input: { width: 512, height: 512, prompt: "qdg dog, cyberpunk poster by katsuhiro otomo", scheduler: "DDIM", num_outputs: 1, guidance_scale: 7.5, negative_prompt: "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", prompt_strength: 0.8, num_inference_steps: 50 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", input={ "width": 512, "height": 512, "prompt": "qdg dog, cyberpunk poster by katsuhiro otomo", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } ) # To access the file URL: print(output[0].url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output[0].read())To learn more, take a look at the guide on getting started with Python.
Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", "input": { "width": 512, "height": 512, "prompt": "qdg dog, cyberpunk poster by katsuhiro otomo", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8 \ -i 'width=512' \ -i 'height=512' \ -i 'prompt="qdg dog, cyberpunk poster by katsuhiro otomo"' \ -i 'scheduler="DDIM"' \ -i 'num_outputs=1' \ -i 'guidance_scale=7.5' \ -i 'negative_prompt="cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark"' \ -i 'prompt_strength=0.8' \ -i 'num_inference_steps=50'To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 512, "height": 512, "prompt": "qdg dog, cyberpunk poster by katsuhiro otomo", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-06-18T20:52:42.083500Z", "created_at": "2023-06-18T20:52:29.660552Z", "data_removed": false, "error": null, "id": "yu6aqijbbdlraonvg5j2olwe2m", "input": { "width": 512, "height": 512, "prompt": "qdg dog, cyberpunk poster by katsuhiro otomo", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 25447\nusing txt2img\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:11, 4.30it/s]\n 4%|▍ | 2/50 [00:00<00:10, 4.64it/s]\n 6%|▌ | 3/50 [00:00<00:09, 4.76it/s]\n 8%|▊ | 4/50 [00:00<00:09, 4.83it/s]\n 10%|█ | 5/50 [00:01<00:09, 4.63it/s]\n 12%|█▏ | 6/50 [00:01<00:09, 4.58it/s]\n 14%|█▍ | 7/50 [00:01<00:09, 4.63it/s]\n 16%|█▌ | 8/50 [00:01<00:08, 4.67it/s]\n 18%|█▊ | 9/50 [00:01<00:08, 4.64it/s]\n 20%|██ | 10/50 [00:02<00:08, 4.51it/s]\n 22%|██▏ | 11/50 [00:02<00:08, 4.54it/s]\n 24%|██▍ | 12/50 [00:02<00:08, 4.58it/s]\n 26%|██▌ | 13/50 [00:02<00:08, 4.58it/s]\n 28%|██▊ | 14/50 [00:03<00:07, 4.53it/s]\n 30%|███ | 15/50 [00:03<00:07, 4.46it/s]\n 32%|███▏ | 16/50 [00:03<00:07, 4.49it/s]\n 34%|███▍ | 17/50 [00:03<00:07, 4.53it/s]\n 36%|███▌ | 18/50 [00:03<00:07, 4.51it/s]\n 38%|███▊ | 19/50 [00:04<00:06, 4.49it/s]\n 40%|████ | 20/50 [00:04<00:06, 4.47it/s]\n 42%|████▏ | 21/50 [00:04<00:06, 4.51it/s]\n 44%|████▍ | 22/50 [00:04<00:06, 4.52it/s]\n 46%|████▌ | 23/50 [00:05<00:06, 4.50it/s]\n 48%|████▊ | 24/50 [00:05<00:05, 4.48it/s]\n 50%|█████ | 25/50 [00:05<00:05, 4.45it/s]\n 52%|█████▏ | 26/50 [00:05<00:05, 4.48it/s]\n 54%|█████▍ | 27/50 [00:05<00:05, 4.47it/s]\n 56%|█████▌ | 28/50 [00:06<00:04, 4.45it/s]\n 58%|█████▊ | 29/50 [00:06<00:04, 4.48it/s]\n 60%|██████ | 30/50 [00:06<00:04, 4.49it/s]\n 62%|██████▏ | 31/50 [00:06<00:04, 4.45it/s]\n 64%|██████▍ | 32/50 [00:07<00:04, 4.43it/s]\n 66%|██████▌ | 33/50 [00:07<00:03, 4.44it/s]\n 68%|██████▊ | 34/50 [00:07<00:03, 4.47it/s]\n 70%|███████ | 35/50 [00:07<00:03, 4.47it/s]\n 72%|███████▏ | 36/50 [00:07<00:03, 4.47it/s]\n 74%|███████▍ | 37/50 [00:08<00:02, 4.45it/s]\n 76%|███████▌ | 38/50 [00:08<00:02, 4.43it/s]\n 78%|███████▊ | 39/50 [00:08<00:02, 4.43it/s]\n 80%|████████ | 40/50 [00:08<00:02, 4.45it/s]\n 82%|████████▏ | 41/50 [00:09<00:02, 4.43it/s]\n 84%|████████▍ | 42/50 [00:09<00:01, 4.43it/s]\n 86%|████████▌ | 43/50 [00:09<00:01, 4.42it/s]\n 88%|████████▊ | 44/50 [00:09<00:01, 4.42it/s]\n 90%|█████████ | 45/50 [00:10<00:01, 4.41it/s]\n 92%|█████████▏| 46/50 [00:10<00:00, 4.39it/s]\n 94%|█████████▍| 47/50 [00:10<00:00, 4.38it/s]\n 96%|█████████▌| 48/50 [00:10<00:00, 4.40it/s]\n 98%|█████████▊| 49/50 [00:10<00:00, 4.39it/s]\n100%|██████████| 50/50 [00:11<00:00, 4.39it/s]\n100%|██████████| 50/50 [00:11<00:00, 4.48it/s]", "metrics": { "predict_time": 12.480539, "total_time": 12.422948 }, "output": [ "https://replicate.delivery/pbxt/7k3PNFBC74ZlLVa0RXKg0L2qROnacvW90WZfafSeftsnJIdEB/out-0.png" ], "started_at": "2023-06-18T20:52:29.602961Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/yu6aqijbbdlraonvg5j2olwe2m", "cancel": "https://api.replicate.com/v1/predictions/yu6aqijbbdlraonvg5j2olwe2m/cancel" }, "version": "e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8" }Generated inUsing seed: 25447 using txt2img 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:11, 4.30it/s] 4%|▍ | 2/50 [00:00<00:10, 4.64it/s] 6%|▌ | 3/50 [00:00<00:09, 4.76it/s] 8%|▊ | 4/50 [00:00<00:09, 4.83it/s] 10%|█ | 5/50 [00:01<00:09, 4.63it/s] 12%|█▏ | 6/50 [00:01<00:09, 4.58it/s] 14%|█▍ | 7/50 [00:01<00:09, 4.63it/s] 16%|█▌ | 8/50 [00:01<00:08, 4.67it/s] 18%|█▊ | 9/50 [00:01<00:08, 4.64it/s] 20%|██ | 10/50 [00:02<00:08, 4.51it/s] 22%|██▏ | 11/50 [00:02<00:08, 4.54it/s] 24%|██▍ | 12/50 [00:02<00:08, 4.58it/s] 26%|██▌ | 13/50 [00:02<00:08, 4.58it/s] 28%|██▊ | 14/50 [00:03<00:07, 4.53it/s] 30%|███ | 15/50 [00:03<00:07, 4.46it/s] 32%|███▏ | 16/50 [00:03<00:07, 4.49it/s] 34%|███▍ | 17/50 [00:03<00:07, 4.53it/s] 36%|███▌ | 18/50 [00:03<00:07, 4.51it/s] 38%|███▊ | 19/50 [00:04<00:06, 4.49it/s] 40%|████ | 20/50 [00:04<00:06, 4.47it/s] 42%|████▏ | 21/50 [00:04<00:06, 4.51it/s] 44%|████▍ | 22/50 [00:04<00:06, 4.52it/s] 46%|████▌ | 23/50 [00:05<00:06, 4.50it/s] 48%|████▊ | 24/50 [00:05<00:05, 4.48it/s] 50%|█████ | 25/50 [00:05<00:05, 4.45it/s] 52%|█████▏ | 26/50 [00:05<00:05, 4.48it/s] 54%|█████▍ | 27/50 [00:05<00:05, 4.47it/s] 56%|█████▌ | 28/50 [00:06<00:04, 4.45it/s] 58%|█████▊ | 29/50 [00:06<00:04, 4.48it/s] 60%|██████ | 30/50 [00:06<00:04, 4.49it/s] 62%|██████▏ | 31/50 [00:06<00:04, 4.45it/s] 64%|██████▍ | 32/50 [00:07<00:04, 4.43it/s] 66%|██████▌ | 33/50 [00:07<00:03, 4.44it/s] 68%|██████▊ | 34/50 [00:07<00:03, 4.47it/s] 70%|███████ | 35/50 [00:07<00:03, 4.47it/s] 72%|███████▏ | 36/50 [00:07<00:03, 4.47it/s] 74%|███████▍ | 37/50 [00:08<00:02, 4.45it/s] 76%|███████▌ | 38/50 [00:08<00:02, 4.43it/s] 78%|███████▊ | 39/50 [00:08<00:02, 4.43it/s] 80%|████████ | 40/50 [00:08<00:02, 4.45it/s] 82%|████████▏ | 41/50 [00:09<00:02, 4.43it/s] 84%|████████▍ | 42/50 [00:09<00:01, 4.43it/s] 86%|████████▌ | 43/50 [00:09<00:01, 4.42it/s] 88%|████████▊ | 44/50 [00:09<00:01, 4.42it/s] 90%|█████████ | 45/50 [00:10<00:01, 4.41it/s] 92%|█████████▏| 46/50 [00:10<00:00, 4.39it/s] 94%|█████████▍| 47/50 [00:10<00:00, 4.38it/s] 96%|█████████▌| 48/50 [00:10<00:00, 4.40it/s] 98%|█████████▊| 49/50 [00:10<00:00, 4.39it/s] 100%|██████████| 50/50 [00:11<00:00, 4.39it/s] 100%|██████████| 50/50 [00:11<00:00, 4.48it/s]Prediction
cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8IDsfa5lqbb65dal2rigdbgxaglxeStatusSucceededSourceWebHardwareT4Total durationCreatedInput
- width
- 512
- height
- 512
- prompt
- qdg dog, cyberpunk poster by katsuhiro otomo
- scheduler
- DDIM
- num_outputs
- 1
- guidance_scale
- 7.5
- negative_prompt
- cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 512, "height": 512, "prompt": "qdg dog, cyberpunk poster by katsuhiro otomo", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", { input: { width: 512, height: 512, prompt: "qdg dog, cyberpunk poster by katsuhiro otomo", scheduler: "DDIM", num_outputs: 1, guidance_scale: 7.5, negative_prompt: "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", prompt_strength: 0.8, num_inference_steps: 50 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", input={ "width": 512, "height": 512, "prompt": "qdg dog, cyberpunk poster by katsuhiro otomo", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } ) # To access the file URL: print(output[0].url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output[0].read())To learn more, take a look at the guide on getting started with Python.
Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", "input": { "width": 512, "height": 512, "prompt": "qdg dog, cyberpunk poster by katsuhiro otomo", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8 \ -i 'width=512' \ -i 'height=512' \ -i 'prompt="qdg dog, cyberpunk poster by katsuhiro otomo"' \ -i 'scheduler="DDIM"' \ -i 'num_outputs=1' \ -i 'guidance_scale=7.5' \ -i 'negative_prompt="cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark"' \ -i 'prompt_strength=0.8' \ -i 'num_inference_steps=50'To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 512, "height": 512, "prompt": "qdg dog, cyberpunk poster by katsuhiro otomo", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-06-18T20:53:36.037031Z", "created_at": "2023-06-18T20:53:24.109484Z", "data_removed": false, "error": null, "id": "sfa5lqbb65dal2rigdbgxaglxe", "input": { "width": 512, "height": 512, "prompt": "qdg dog, cyberpunk poster by katsuhiro otomo", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 58327\nusing txt2img\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:11, 4.26it/s]\n 4%|▍ | 2/50 [00:00<00:10, 4.59it/s]\n 6%|▌ | 3/50 [00:00<00:10, 4.70it/s]\n 8%|▊ | 4/50 [00:00<00:09, 4.79it/s]\n 10%|█ | 5/50 [00:01<00:09, 4.66it/s]\n 12%|█▏ | 6/50 [00:01<00:09, 4.70it/s]\n 14%|█▍ | 7/50 [00:01<00:09, 4.69it/s]\n 16%|█▌ | 8/50 [00:01<00:08, 4.77it/s]\n 18%|█▊ | 9/50 [00:01<00:08, 4.78it/s]\n 20%|██ | 10/50 [00:02<00:08, 4.66it/s]\n 22%|██▏ | 11/50 [00:02<00:08, 4.65it/s]\n 24%|██▍ | 12/50 [00:02<00:08, 4.73it/s]\n 26%|██▌ | 13/50 [00:02<00:07, 4.79it/s]\n 28%|██▊ | 14/50 [00:02<00:07, 4.78it/s]\n 30%|███ | 15/50 [00:03<00:07, 4.70it/s]\n 32%|███▏ | 16/50 [00:03<00:07, 4.68it/s]\n 34%|███▍ | 17/50 [00:03<00:06, 4.73it/s]\n 36%|███▌ | 18/50 [00:03<00:06, 4.75it/s]\n 38%|███▊ | 19/50 [00:04<00:06, 4.68it/s]\n 40%|████ | 20/50 [00:04<00:06, 4.60it/s]\n 42%|████▏ | 21/50 [00:04<00:06, 4.63it/s]\n 44%|████▍ | 22/50 [00:04<00:06, 4.63it/s]\n 46%|████▌ | 23/50 [00:04<00:05, 4.69it/s]\n 48%|████▊ | 24/50 [00:05<00:05, 4.64it/s]\n 50%|█████ | 25/50 [00:05<00:05, 4.59it/s]\n 52%|█████▏ | 26/50 [00:05<00:05, 4.66it/s]\n 54%|█████▍ | 27/50 [00:05<00:04, 4.69it/s]\n 56%|█████▌ | 28/50 [00:05<00:04, 4.68it/s]\n 58%|█████▊ | 29/50 [00:06<00:04, 4.62it/s]\n 60%|██████ | 30/50 [00:06<00:04, 4.59it/s]\n 62%|██████▏ | 31/50 [00:06<00:04, 4.62it/s]\n 64%|██████▍ | 32/50 [00:06<00:03, 4.63it/s]\n 66%|██████▌ | 33/50 [00:07<00:03, 4.60it/s]\n 68%|██████▊ | 34/50 [00:07<00:03, 4.57it/s]\n 70%|███████ | 35/50 [00:07<00:03, 4.62it/s]\n 72%|███████▏ | 36/50 [00:07<00:03, 4.61it/s]\n 74%|███████▍ | 37/50 [00:07<00:02, 4.59it/s]\n 76%|███████▌ | 38/50 [00:08<00:02, 4.57it/s]\n 78%|███████▊ | 39/50 [00:08<00:02, 4.55it/s]\n 80%|████████ | 40/50 [00:08<00:02, 4.58it/s]\n 82%|████████▏ | 41/50 [00:08<00:01, 4.60it/s]\n 84%|████████▍ | 42/50 [00:09<00:01, 4.57it/s]\n 86%|████████▌ | 43/50 [00:09<00:01, 4.53it/s]\n 88%|████████▊ | 44/50 [00:09<00:01, 4.52it/s]\n 90%|█████████ | 45/50 [00:09<00:01, 4.53it/s]\n 92%|█████████▏| 46/50 [00:09<00:00, 4.55it/s]\n 94%|█████████▍| 47/50 [00:10<00:00, 4.51it/s]\n 96%|█████████▌| 48/50 [00:10<00:00, 4.51it/s]\n 98%|█████████▊| 49/50 [00:10<00:00, 4.52it/s]\n100%|██████████| 50/50 [00:10<00:00, 4.56it/s]\n100%|██████████| 50/50 [00:10<00:00, 4.63it/s]", "metrics": { "predict_time": 11.974142, "total_time": 11.927547 }, "output": [ "https://replicate.delivery/pbxt/OctUJ4tVJ05gF54K53lTMa5Euaie3n0vF6XtFqubLfmPDSHRA/out-0.png" ], "started_at": "2023-06-18T20:53:24.062889Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/sfa5lqbb65dal2rigdbgxaglxe", "cancel": "https://api.replicate.com/v1/predictions/sfa5lqbb65dal2rigdbgxaglxe/cancel" }, "version": "e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8" }Generated inUsing seed: 58327 using txt2img 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:11, 4.26it/s] 4%|▍ | 2/50 [00:00<00:10, 4.59it/s] 6%|▌ | 3/50 [00:00<00:10, 4.70it/s] 8%|▊ | 4/50 [00:00<00:09, 4.79it/s] 10%|█ | 5/50 [00:01<00:09, 4.66it/s] 12%|█▏ | 6/50 [00:01<00:09, 4.70it/s] 14%|█▍ | 7/50 [00:01<00:09, 4.69it/s] 16%|█▌ | 8/50 [00:01<00:08, 4.77it/s] 18%|█▊ | 9/50 [00:01<00:08, 4.78it/s] 20%|██ | 10/50 [00:02<00:08, 4.66it/s] 22%|██▏ | 11/50 [00:02<00:08, 4.65it/s] 24%|██▍ | 12/50 [00:02<00:08, 4.73it/s] 26%|██▌ | 13/50 [00:02<00:07, 4.79it/s] 28%|██▊ | 14/50 [00:02<00:07, 4.78it/s] 30%|███ | 15/50 [00:03<00:07, 4.70it/s] 32%|███▏ | 16/50 [00:03<00:07, 4.68it/s] 34%|███▍ | 17/50 [00:03<00:06, 4.73it/s] 36%|███▌ | 18/50 [00:03<00:06, 4.75it/s] 38%|███▊ | 19/50 [00:04<00:06, 4.68it/s] 40%|████ | 20/50 [00:04<00:06, 4.60it/s] 42%|████▏ | 21/50 [00:04<00:06, 4.63it/s] 44%|████▍ | 22/50 [00:04<00:06, 4.63it/s] 46%|████▌ | 23/50 [00:04<00:05, 4.69it/s] 48%|████▊ | 24/50 [00:05<00:05, 4.64it/s] 50%|█████ | 25/50 [00:05<00:05, 4.59it/s] 52%|█████▏ | 26/50 [00:05<00:05, 4.66it/s] 54%|█████▍ | 27/50 [00:05<00:04, 4.69it/s] 56%|█████▌ | 28/50 [00:05<00:04, 4.68it/s] 58%|█████▊ | 29/50 [00:06<00:04, 4.62it/s] 60%|██████ | 30/50 [00:06<00:04, 4.59it/s] 62%|██████▏ | 31/50 [00:06<00:04, 4.62it/s] 64%|██████▍ | 32/50 [00:06<00:03, 4.63it/s] 66%|██████▌ | 33/50 [00:07<00:03, 4.60it/s] 68%|██████▊ | 34/50 [00:07<00:03, 4.57it/s] 70%|███████ | 35/50 [00:07<00:03, 4.62it/s] 72%|███████▏ | 36/50 [00:07<00:03, 4.61it/s] 74%|███████▍ | 37/50 [00:07<00:02, 4.59it/s] 76%|███████▌ | 38/50 [00:08<00:02, 4.57it/s] 78%|███████▊ | 39/50 [00:08<00:02, 4.55it/s] 80%|████████ | 40/50 [00:08<00:02, 4.58it/s] 82%|████████▏ | 41/50 [00:08<00:01, 4.60it/s] 84%|████████▍ | 42/50 [00:09<00:01, 4.57it/s] 86%|████████▌ | 43/50 [00:09<00:01, 4.53it/s] 88%|████████▊ | 44/50 [00:09<00:01, 4.52it/s] 90%|█████████ | 45/50 [00:09<00:01, 4.53it/s] 92%|█████████▏| 46/50 [00:09<00:00, 4.55it/s] 94%|█████████▍| 47/50 [00:10<00:00, 4.51it/s] 96%|█████████▌| 48/50 [00:10<00:00, 4.51it/s] 98%|█████████▊| 49/50 [00:10<00:00, 4.52it/s] 100%|██████████| 50/50 [00:10<00:00, 4.56it/s] 100%|██████████| 50/50 [00:10<00:00, 4.63it/s]Prediction
cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8ID3bzzrpbbcwefmg7inzbzm3w6daStatusSucceededSourceWebHardwareT4Total durationCreatedInput
- width
- 512
- height
- 512
- prompt
- Adorably cute qdg dog portrait, artstation winner by Victo Ngai, Kilian Eng and by Jake Parker, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution
- scheduler
- DDIM
- num_outputs
- 1
- guidance_scale
- 7.5
- negative_prompt
- cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 512, "height": 512, "prompt": "Adorably cute qdg dog portrait, artstation winner by Victo Ngai, Kilian Eng and by Jake Parker, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", { input: { width: 512, height: 512, prompt: "Adorably cute qdg dog portrait, artstation winner by Victo Ngai, Kilian Eng and by Jake Parker, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution", scheduler: "DDIM", num_outputs: 1, guidance_scale: 7.5, negative_prompt: "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", prompt_strength: 0.8, num_inference_steps: 50 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", input={ "width": 512, "height": 512, "prompt": "Adorably cute qdg dog portrait, artstation winner by Victo Ngai, Kilian Eng and by Jake Parker, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } ) # To access the file URL: print(output[0].url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output[0].read())To learn more, take a look at the guide on getting started with Python.
Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", "input": { "width": 512, "height": 512, "prompt": "Adorably cute qdg dog portrait, artstation winner by Victo Ngai, Kilian Eng and by Jake Parker, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8 \ -i 'width=512' \ -i 'height=512' \ -i 'prompt="Adorably cute qdg dog portrait, artstation winner by Victo Ngai, Kilian Eng and by Jake Parker, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution"' \ -i 'scheduler="DDIM"' \ -i 'num_outputs=1' \ -i 'guidance_scale=7.5' \ -i 'negative_prompt="cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark"' \ -i 'prompt_strength=0.8' \ -i 'num_inference_steps=50'To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 512, "height": 512, "prompt": "Adorably cute qdg dog portrait, artstation winner by Victo Ngai, Kilian Eng and by Jake Parker, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-06-18T20:57:03.671160Z", "created_at": "2023-06-18T20:56:52.021684Z", "data_removed": false, "error": null, "id": "3bzzrpbbcwefmg7inzbzm3w6da", "input": { "width": 512, "height": 512, "prompt": "Adorably cute qdg dog portrait, artstation winner by Victo Ngai, Kilian Eng and by Jake Parker, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 4709\nusing txt2img\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:11, 4.21it/s]\n 4%|▍ | 2/50 [00:00<00:10, 4.54it/s]\n 6%|▌ | 3/50 [00:00<00:09, 4.70it/s]\n 8%|▊ | 4/50 [00:00<00:09, 4.79it/s]\n 10%|█ | 5/50 [00:01<00:09, 4.66it/s]\n 12%|█▏ | 6/50 [00:01<00:09, 4.67it/s]\n 14%|█▍ | 7/50 [00:01<00:09, 4.71it/s]\n 16%|█▌ | 8/50 [00:01<00:08, 4.77it/s]\n 18%|█▊ | 9/50 [00:01<00:08, 4.82it/s]\n 20%|██ | 10/50 [00:02<00:08, 4.70it/s]\n 22%|██▏ | 11/50 [00:02<00:08, 4.74it/s]\n 24%|██▍ | 12/50 [00:02<00:08, 4.72it/s]\n 26%|██▌ | 13/50 [00:02<00:07, 4.78it/s]\n 28%|██▊ | 14/50 [00:02<00:07, 4.79it/s]\n 30%|███ | 15/50 [00:03<00:07, 4.72it/s]\n 32%|███▏ | 16/50 [00:03<00:07, 4.78it/s]\n 34%|███▍ | 17/50 [00:03<00:06, 4.82it/s]\n 36%|███▌ | 18/50 [00:03<00:06, 4.86it/s]\n 38%|███▊ | 19/50 [00:03<00:06, 4.85it/s]\n 40%|████ | 20/50 [00:04<00:06, 4.76it/s]\n 42%|████▏ | 21/50 [00:04<00:06, 4.75it/s]\n 44%|████▍ | 22/50 [00:04<00:05, 4.75it/s]\n 46%|████▌ | 23/50 [00:04<00:05, 4.80it/s]\n 48%|████▊ | 24/50 [00:05<00:05, 4.80it/s]\n 50%|█████ | 25/50 [00:05<00:05, 4.76it/s]\n 52%|█████▏ | 26/50 [00:05<00:05, 4.77it/s]\n 54%|█████▍ | 27/50 [00:05<00:04, 4.71it/s]\n 56%|█████▌ | 28/50 [00:05<00:04, 4.78it/s]\n 58%|█████▊ | 29/50 [00:06<00:04, 4.77it/s]\n 60%|██████ | 30/50 [00:06<00:04, 4.73it/s]\n 62%|██████▏ | 31/50 [00:06<00:03, 4.77it/s]\n 64%|██████▍ | 32/50 [00:06<00:03, 4.72it/s]\n 66%|██████▌ | 33/50 [00:06<00:03, 4.78it/s]\n 68%|██████▊ | 34/50 [00:07<00:03, 4.80it/s]\n 70%|███████ | 35/50 [00:07<00:03, 4.78it/s]\n 72%|███████▏ | 36/50 [00:07<00:02, 4.76it/s]\n 74%|███████▍ | 37/50 [00:07<00:02, 4.78it/s]\n 76%|███████▌ | 38/50 [00:07<00:02, 4.74it/s]\n 78%|███████▊ | 39/50 [00:08<00:02, 4.76it/s]\n 80%|████████ | 40/50 [00:08<00:02, 4.72it/s]\n 82%|████████▏ | 41/50 [00:08<00:01, 4.77it/s]\n 84%|████████▍ | 42/50 [00:08<00:01, 4.78it/s]\n 86%|████████▌ | 43/50 [00:09<00:01, 4.73it/s]\n 88%|████████▊ | 44/50 [00:09<00:01, 4.74it/s]\n 90%|█████████ | 45/50 [00:09<00:01, 4.70it/s]\n 92%|█████████▏| 46/50 [00:09<00:00, 4.70it/s]\n 94%|█████████▍| 47/50 [00:09<00:00, 4.72it/s]\n 96%|█████████▌| 48/50 [00:10<00:00, 4.76it/s]\n 98%|█████████▊| 49/50 [00:10<00:00, 4.72it/s]\n100%|██████████| 50/50 [00:10<00:00, 4.75it/s]\n100%|██████████| 50/50 [00:10<00:00, 4.75it/s]", "metrics": { "predict_time": 11.674991, "total_time": 11.649476 }, "output": [ "https://replicate.delivery/pbxt/pIk5hO9YQp5IB1SZZgxRfxPk8WHNlQRKSjdL8rq5pZSPDpjIA/out-0.png" ], "started_at": "2023-06-18T20:56:51.996169Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/3bzzrpbbcwefmg7inzbzm3w6da", "cancel": "https://api.replicate.com/v1/predictions/3bzzrpbbcwefmg7inzbzm3w6da/cancel" }, "version": "e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8" }Generated inUsing seed: 4709 using txt2img 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:11, 4.21it/s] 4%|▍ | 2/50 [00:00<00:10, 4.54it/s] 6%|▌ | 3/50 [00:00<00:09, 4.70it/s] 8%|▊ | 4/50 [00:00<00:09, 4.79it/s] 10%|█ | 5/50 [00:01<00:09, 4.66it/s] 12%|█▏ | 6/50 [00:01<00:09, 4.67it/s] 14%|█▍ | 7/50 [00:01<00:09, 4.71it/s] 16%|█▌ | 8/50 [00:01<00:08, 4.77it/s] 18%|█▊ | 9/50 [00:01<00:08, 4.82it/s] 20%|██ | 10/50 [00:02<00:08, 4.70it/s] 22%|██▏ | 11/50 [00:02<00:08, 4.74it/s] 24%|██▍ | 12/50 [00:02<00:08, 4.72it/s] 26%|██▌ | 13/50 [00:02<00:07, 4.78it/s] 28%|██▊ | 14/50 [00:02<00:07, 4.79it/s] 30%|███ | 15/50 [00:03<00:07, 4.72it/s] 32%|███▏ | 16/50 [00:03<00:07, 4.78it/s] 34%|███▍ | 17/50 [00:03<00:06, 4.82it/s] 36%|███▌ | 18/50 [00:03<00:06, 4.86it/s] 38%|███▊ | 19/50 [00:03<00:06, 4.85it/s] 40%|████ | 20/50 [00:04<00:06, 4.76it/s] 42%|████▏ | 21/50 [00:04<00:06, 4.75it/s] 44%|████▍ | 22/50 [00:04<00:05, 4.75it/s] 46%|████▌ | 23/50 [00:04<00:05, 4.80it/s] 48%|████▊ | 24/50 [00:05<00:05, 4.80it/s] 50%|█████ | 25/50 [00:05<00:05, 4.76it/s] 52%|█████▏ | 26/50 [00:05<00:05, 4.77it/s] 54%|█████▍ | 27/50 [00:05<00:04, 4.71it/s] 56%|█████▌ | 28/50 [00:05<00:04, 4.78it/s] 58%|█████▊ | 29/50 [00:06<00:04, 4.77it/s] 60%|██████ | 30/50 [00:06<00:04, 4.73it/s] 62%|██████▏ | 31/50 [00:06<00:03, 4.77it/s] 64%|██████▍ | 32/50 [00:06<00:03, 4.72it/s] 66%|██████▌ | 33/50 [00:06<00:03, 4.78it/s] 68%|██████▊ | 34/50 [00:07<00:03, 4.80it/s] 70%|███████ | 35/50 [00:07<00:03, 4.78it/s] 72%|███████▏ | 36/50 [00:07<00:02, 4.76it/s] 74%|███████▍ | 37/50 [00:07<00:02, 4.78it/s] 76%|███████▌ | 38/50 [00:07<00:02, 4.74it/s] 78%|███████▊ | 39/50 [00:08<00:02, 4.76it/s] 80%|████████ | 40/50 [00:08<00:02, 4.72it/s] 82%|████████▏ | 41/50 [00:08<00:01, 4.77it/s] 84%|████████▍ | 42/50 [00:08<00:01, 4.78it/s] 86%|████████▌ | 43/50 [00:09<00:01, 4.73it/s] 88%|████████▊ | 44/50 [00:09<00:01, 4.74it/s] 90%|█████████ | 45/50 [00:09<00:01, 4.70it/s] 92%|█████████▏| 46/50 [00:09<00:00, 4.70it/s] 94%|█████████▍| 47/50 [00:09<00:00, 4.72it/s] 96%|█████████▌| 48/50 [00:10<00:00, 4.76it/s] 98%|█████████▊| 49/50 [00:10<00:00, 4.72it/s] 100%|██████████| 50/50 [00:10<00:00, 4.75it/s] 100%|██████████| 50/50 [00:10<00:00, 4.75it/s]Prediction
cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8IDfplbcvrbkh53eeabepmd6faazyStatusSucceededSourceWebHardwareT4Total durationCreatedInput
- width
- 512
- height
- 512
- prompt
- Adorably cute qdg dog portrait, artstation winner by Victo Ngai, Kilian Eng and by Jake Parker, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution
- scheduler
- DDIM
- num_outputs
- 1
- guidance_scale
- 7.5
- negative_prompt
- cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 512, "height": 512, "prompt": "Adorably cute qdg dog portrait, artstation winner by Victo Ngai, Kilian Eng and by Jake Parker, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", { input: { width: 512, height: 512, prompt: "Adorably cute qdg dog portrait, artstation winner by Victo Ngai, Kilian Eng and by Jake Parker, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution", scheduler: "DDIM", num_outputs: 1, guidance_scale: 7.5, negative_prompt: "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", prompt_strength: 0.8, num_inference_steps: 50 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", input={ "width": 512, "height": 512, "prompt": "Adorably cute qdg dog portrait, artstation winner by Victo Ngai, Kilian Eng and by Jake Parker, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } ) # To access the file URL: print(output[0].url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output[0].read())To learn more, take a look at the guide on getting started with Python.
Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", "input": { "width": 512, "height": 512, "prompt": "Adorably cute qdg dog portrait, artstation winner by Victo Ngai, Kilian Eng and by Jake Parker, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8 \ -i 'width=512' \ -i 'height=512' \ -i 'prompt="Adorably cute qdg dog portrait, artstation winner by Victo Ngai, Kilian Eng and by Jake Parker, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution"' \ -i 'scheduler="DDIM"' \ -i 'num_outputs=1' \ -i 'guidance_scale=7.5' \ -i 'negative_prompt="cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark"' \ -i 'prompt_strength=0.8' \ -i 'num_inference_steps=50'To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 512, "height": 512, "prompt": "Adorably cute qdg dog portrait, artstation winner by Victo Ngai, Kilian Eng and by Jake Parker, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-06-18T20:57:52.384605Z", "created_at": "2023-06-18T20:57:40.400276Z", "data_removed": false, "error": null, "id": "fplbcvrbkh53eeabepmd6faazy", "input": { "width": 512, "height": 512, "prompt": "Adorably cute qdg dog portrait, artstation winner by Victo Ngai, Kilian Eng and by Jake Parker, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 43812\nusing txt2img\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:12, 3.87it/s]\n 4%|▍ | 2/50 [00:00<00:10, 4.38it/s]\n 6%|▌ | 3/50 [00:00<00:10, 4.63it/s]\n 8%|▊ | 4/50 [00:00<00:09, 4.73it/s]\n 10%|█ | 5/50 [00:01<00:09, 4.63it/s]\n 12%|█▏ | 6/50 [00:01<00:09, 4.58it/s]\n 14%|█▍ | 7/50 [00:01<00:09, 4.62it/s]\n 16%|█▌ | 8/50 [00:01<00:09, 4.66it/s]\n 18%|█▊ | 9/50 [00:01<00:08, 4.72it/s]\n 20%|██ | 10/50 [00:02<00:08, 4.58it/s]\n 22%|██▏ | 11/50 [00:02<00:08, 4.60it/s]\n 24%|██▍ | 12/50 [00:02<00:08, 4.59it/s]\n 26%|██▌ | 13/50 [00:02<00:07, 4.63it/s]\n 28%|██▊ | 14/50 [00:03<00:07, 4.59it/s]\n 30%|███ | 15/50 [00:03<00:07, 4.53it/s]\n 32%|███▏ | 16/50 [00:03<00:07, 4.57it/s]\n 34%|███▍ | 17/50 [00:03<00:07, 4.58it/s]\n 36%|███▌ | 18/50 [00:03<00:06, 4.66it/s]\n 38%|███▊ | 19/50 [00:04<00:06, 4.59it/s]\n 40%|████ | 20/50 [00:04<00:06, 4.57it/s]\n 42%|████▏ | 21/50 [00:04<00:06, 4.57it/s]\n 44%|████▍ | 22/50 [00:04<00:06, 4.64it/s]\n 46%|████▌ | 23/50 [00:05<00:05, 4.59it/s]\n 48%|████▊ | 24/50 [00:05<00:05, 4.58it/s]\n 50%|█████ | 25/50 [00:05<00:05, 4.59it/s]\n 52%|█████▏ | 26/50 [00:05<00:05, 4.60it/s]\n 54%|█████▍ | 27/50 [00:05<00:04, 4.63it/s]\n 56%|█████▌ | 28/50 [00:06<00:04, 4.58it/s]\n 58%|█████▊ | 29/50 [00:06<00:04, 4.57it/s]\n 60%|██████ | 30/50 [00:06<00:04, 4.61it/s]\n 62%|██████▏ | 31/50 [00:06<00:04, 4.61it/s]\n 64%|██████▍ | 32/50 [00:06<00:03, 4.59it/s]\n 66%|██████▌ | 33/50 [00:07<00:03, 4.56it/s]\n 68%|██████▊ | 34/50 [00:07<00:03, 4.59it/s]\n 70%|███████ | 35/50 [00:07<00:03, 4.62it/s]\n 72%|███████▏ | 36/50 [00:07<00:03, 4.61it/s]\n 74%|███████▍ | 37/50 [00:08<00:02, 4.61it/s]\n 76%|███████▌ | 38/50 [00:08<00:02, 4.62it/s]\n 78%|███████▊ | 39/50 [00:08<00:02, 4.61it/s]\n 80%|████████ | 40/50 [00:08<00:02, 4.65it/s]\n 82%|████████▏ | 41/50 [00:08<00:01, 4.60it/s]\n 84%|████████▍ | 42/50 [00:09<00:01, 4.60it/s]\n 86%|████████▌ | 43/50 [00:09<00:01, 4.59it/s]\n 88%|████████▊ | 44/50 [00:09<00:01, 4.59it/s]\n 90%|█████████ | 45/50 [00:09<00:01, 4.63it/s]\n 92%|█████████▏| 46/50 [00:10<00:00, 4.59it/s]\n 94%|█████████▍| 47/50 [00:10<00:00, 4.58it/s]\n 96%|█████████▌| 48/50 [00:10<00:00, 4.58it/s]\n 98%|█████████▊| 49/50 [00:10<00:00, 4.62it/s]\n100%|██████████| 50/50 [00:10<00:00, 4.61it/s]\n100%|██████████| 50/50 [00:10<00:00, 4.60it/s]", "metrics": { "predict_time": 12.040473, "total_time": 11.984329 }, "output": [ "https://replicate.delivery/pbxt/wgOVwfz58u1FKCmBzcShfbU8Zyzmobpekn3sp9tbMzf9cIdEB/out-0.png" ], "started_at": "2023-06-18T20:57:40.344132Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/fplbcvrbkh53eeabepmd6faazy", "cancel": "https://api.replicate.com/v1/predictions/fplbcvrbkh53eeabepmd6faazy/cancel" }, "version": "e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8" }Generated inUsing seed: 43812 using txt2img 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:12, 3.87it/s] 4%|▍ | 2/50 [00:00<00:10, 4.38it/s] 6%|▌ | 3/50 [00:00<00:10, 4.63it/s] 8%|▊ | 4/50 [00:00<00:09, 4.73it/s] 10%|█ | 5/50 [00:01<00:09, 4.63it/s] 12%|█▏ | 6/50 [00:01<00:09, 4.58it/s] 14%|█▍ | 7/50 [00:01<00:09, 4.62it/s] 16%|█▌ | 8/50 [00:01<00:09, 4.66it/s] 18%|█▊ | 9/50 [00:01<00:08, 4.72it/s] 20%|██ | 10/50 [00:02<00:08, 4.58it/s] 22%|██▏ | 11/50 [00:02<00:08, 4.60it/s] 24%|██▍ | 12/50 [00:02<00:08, 4.59it/s] 26%|██▌ | 13/50 [00:02<00:07, 4.63it/s] 28%|██▊ | 14/50 [00:03<00:07, 4.59it/s] 30%|███ | 15/50 [00:03<00:07, 4.53it/s] 32%|███▏ | 16/50 [00:03<00:07, 4.57it/s] 34%|███▍ | 17/50 [00:03<00:07, 4.58it/s] 36%|███▌ | 18/50 [00:03<00:06, 4.66it/s] 38%|███▊ | 19/50 [00:04<00:06, 4.59it/s] 40%|████ | 20/50 [00:04<00:06, 4.57it/s] 42%|████▏ | 21/50 [00:04<00:06, 4.57it/s] 44%|████▍ | 22/50 [00:04<00:06, 4.64it/s] 46%|████▌ | 23/50 [00:05<00:05, 4.59it/s] 48%|████▊ | 24/50 [00:05<00:05, 4.58it/s] 50%|█████ | 25/50 [00:05<00:05, 4.59it/s] 52%|█████▏ | 26/50 [00:05<00:05, 4.60it/s] 54%|█████▍ | 27/50 [00:05<00:04, 4.63it/s] 56%|█████▌ | 28/50 [00:06<00:04, 4.58it/s] 58%|█████▊ | 29/50 [00:06<00:04, 4.57it/s] 60%|██████ | 30/50 [00:06<00:04, 4.61it/s] 62%|██████▏ | 31/50 [00:06<00:04, 4.61it/s] 64%|██████▍ | 32/50 [00:06<00:03, 4.59it/s] 66%|██████▌ | 33/50 [00:07<00:03, 4.56it/s] 68%|██████▊ | 34/50 [00:07<00:03, 4.59it/s] 70%|███████ | 35/50 [00:07<00:03, 4.62it/s] 72%|███████▏ | 36/50 [00:07<00:03, 4.61it/s] 74%|███████▍ | 37/50 [00:08<00:02, 4.61it/s] 76%|███████▌ | 38/50 [00:08<00:02, 4.62it/s] 78%|███████▊ | 39/50 [00:08<00:02, 4.61it/s] 80%|████████ | 40/50 [00:08<00:02, 4.65it/s] 82%|████████▏ | 41/50 [00:08<00:01, 4.60it/s] 84%|████████▍ | 42/50 [00:09<00:01, 4.60it/s] 86%|████████▌ | 43/50 [00:09<00:01, 4.59it/s] 88%|████████▊ | 44/50 [00:09<00:01, 4.59it/s] 90%|█████████ | 45/50 [00:09<00:01, 4.63it/s] 92%|█████████▏| 46/50 [00:10<00:00, 4.59it/s] 94%|█████████▍| 47/50 [00:10<00:00, 4.58it/s] 96%|█████████▌| 48/50 [00:10<00:00, 4.58it/s] 98%|█████████▊| 49/50 [00:10<00:00, 4.62it/s] 100%|██████████| 50/50 [00:10<00:00, 4.61it/s] 100%|██████████| 50/50 [00:10<00:00, 4.60it/s]Prediction
cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8ID5f3x3dbbbk3xejuihjliwfa5saStatusSucceededSourceWebHardwareT4Total durationCreatedInput
- width
- 512
- height
- 512
- prompt
- Adorably cute qdg dog portrait, artstation winner by Victo Ngai, Kilian Eng and by Jake Parker, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution
- scheduler
- DDIM
- num_outputs
- 1
- guidance_scale
- 7.5
- negative_prompt
- cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 512, "height": 512, "prompt": "Adorably cute qdg dog portrait, artstation winner by Victo Ngai, Kilian Eng and by Jake Parker, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", { input: { width: 512, height: 512, prompt: "Adorably cute qdg dog portrait, artstation winner by Victo Ngai, Kilian Eng and by Jake Parker, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution", scheduler: "DDIM", num_outputs: 1, guidance_scale: 7.5, negative_prompt: "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", prompt_strength: 0.8, num_inference_steps: 50 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", input={ "width": 512, "height": 512, "prompt": "Adorably cute qdg dog portrait, artstation winner by Victo Ngai, Kilian Eng and by Jake Parker, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } ) # To access the file URL: print(output[0].url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output[0].read())To learn more, take a look at the guide on getting started with Python.
Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", "input": { "width": 512, "height": 512, "prompt": "Adorably cute qdg dog portrait, artstation winner by Victo Ngai, Kilian Eng and by Jake Parker, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8 \ -i 'width=512' \ -i 'height=512' \ -i 'prompt="Adorably cute qdg dog portrait, artstation winner by Victo Ngai, Kilian Eng and by Jake Parker, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution"' \ -i 'scheduler="DDIM"' \ -i 'num_outputs=1' \ -i 'guidance_scale=7.5' \ -i 'negative_prompt="cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark"' \ -i 'prompt_strength=0.8' \ -i 'num_inference_steps=50'To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 512, "height": 512, "prompt": "Adorably cute qdg dog portrait, artstation winner by Victo Ngai, Kilian Eng and by Jake Parker, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-06-18T20:58:12.207684Z", "created_at": "2023-06-18T20:58:00.367973Z", "data_removed": false, "error": null, "id": "5f3x3dbbbk3xejuihjliwfa5sa", "input": { "width": 512, "height": 512, "prompt": "Adorably cute qdg dog portrait, artstation winner by Victo Ngai, Kilian Eng and by Jake Parker, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 44118\nusing txt2img\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:12, 4.01it/s]\n 4%|▍ | 2/50 [00:00<00:10, 4.53it/s]\n 6%|▌ | 3/50 [00:00<00:09, 4.74it/s]\n 8%|▊ | 4/50 [00:00<00:09, 4.84it/s]\n 10%|█ | 5/50 [00:01<00:09, 4.81it/s]\n 12%|█▏ | 6/50 [00:01<00:09, 4.67it/s]\n 14%|█▍ | 7/50 [00:01<00:09, 4.69it/s]\n 16%|█▌ | 8/50 [00:01<00:08, 4.77it/s]\n 18%|█▊ | 9/50 [00:01<00:08, 4.82it/s]\n 20%|██ | 10/50 [00:02<00:08, 4.74it/s]\n 22%|██▏ | 11/50 [00:02<00:08, 4.74it/s]\n 24%|██▍ | 12/50 [00:02<00:08, 4.74it/s]\n 26%|██▌ | 13/50 [00:02<00:07, 4.75it/s]\n 28%|██▊ | 14/50 [00:02<00:07, 4.79it/s]\n 30%|███ | 15/50 [00:03<00:07, 4.69it/s]\n 32%|███▏ | 16/50 [00:03<00:07, 4.69it/s]\n 34%|███▍ | 17/50 [00:03<00:07, 4.70it/s]\n 36%|███▌ | 18/50 [00:03<00:06, 4.77it/s]\n 38%|███▊ | 19/50 [00:04<00:06, 4.76it/s]\n 40%|████ | 20/50 [00:04<00:06, 4.73it/s]\n 42%|████▏ | 21/50 [00:04<00:06, 4.74it/s]\n 44%|████▍ | 22/50 [00:04<00:05, 4.72it/s]\n 46%|████▌ | 23/50 [00:04<00:05, 4.77it/s]\n 48%|████▊ | 24/50 [00:05<00:05, 4.76it/s]\n 50%|█████ | 25/50 [00:05<00:05, 4.73it/s]\n 52%|█████▏ | 26/50 [00:05<00:05, 4.71it/s]\n 54%|█████▍ | 27/50 [00:05<00:04, 4.74it/s]\n 56%|█████▌ | 28/50 [00:05<00:04, 4.78it/s]\n 58%|█████▊ | 29/50 [00:06<00:04, 4.72it/s]\n 60%|██████ | 30/50 [00:06<00:04, 4.75it/s]\n 62%|██████▏ | 31/50 [00:06<00:04, 4.72it/s]\n 64%|██████▍ | 32/50 [00:06<00:03, 4.75it/s]\n 66%|██████▌ | 33/50 [00:06<00:03, 4.77it/s]\n 68%|██████▊ | 34/50 [00:07<00:03, 4.70it/s]\n 70%|███████ | 35/50 [00:07<00:03, 4.66it/s]\n 72%|███████▏ | 36/50 [00:07<00:02, 4.71it/s]\n 74%|███████▍ | 37/50 [00:07<00:02, 4.70it/s]\n 76%|███████▌ | 38/50 [00:08<00:02, 4.71it/s]\n 78%|███████▊ | 39/50 [00:08<00:02, 4.69it/s]\n 80%|████████ | 40/50 [00:08<00:02, 4.67it/s]\n 82%|████████▏ | 41/50 [00:08<00:01, 4.67it/s]\n 84%|████████▍ | 42/50 [00:08<00:01, 4.70it/s]\n 86%|████████▌ | 43/50 [00:09<00:01, 4.68it/s]\n 88%|████████▊ | 44/50 [00:09<00:01, 4.68it/s]\n 90%|█████████ | 45/50 [00:09<00:01, 4.69it/s]\n 92%|█████████▏| 46/50 [00:09<00:00, 4.66it/s]\n 94%|█████████▍| 47/50 [00:09<00:00, 4.72it/s]\n 96%|█████████▌| 48/50 [00:10<00:00, 4.68it/s]\n 98%|█████████▊| 49/50 [00:10<00:00, 4.72it/s]\n100%|██████████| 50/50 [00:10<00:00, 4.72it/s]\n100%|██████████| 50/50 [00:10<00:00, 4.72it/s]", "metrics": { "predict_time": 11.878062, "total_time": 11.839711 }, "output": [ "https://replicate.delivery/pbxt/3TZGHlgLhBZ5FBRVW3KgtURf22ZzuD6yvseyApxMQtHjHSHRA/out-0.png" ], "started_at": "2023-06-18T20:58:00.329622Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/5f3x3dbbbk3xejuihjliwfa5sa", "cancel": "https://api.replicate.com/v1/predictions/5f3x3dbbbk3xejuihjliwfa5sa/cancel" }, "version": "e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8" }Generated inUsing seed: 44118 using txt2img 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:12, 4.01it/s] 4%|▍ | 2/50 [00:00<00:10, 4.53it/s] 6%|▌ | 3/50 [00:00<00:09, 4.74it/s] 8%|▊ | 4/50 [00:00<00:09, 4.84it/s] 10%|█ | 5/50 [00:01<00:09, 4.81it/s] 12%|█▏ | 6/50 [00:01<00:09, 4.67it/s] 14%|█▍ | 7/50 [00:01<00:09, 4.69it/s] 16%|█▌ | 8/50 [00:01<00:08, 4.77it/s] 18%|█▊ | 9/50 [00:01<00:08, 4.82it/s] 20%|██ | 10/50 [00:02<00:08, 4.74it/s] 22%|██▏ | 11/50 [00:02<00:08, 4.74it/s] 24%|██▍ | 12/50 [00:02<00:08, 4.74it/s] 26%|██▌ | 13/50 [00:02<00:07, 4.75it/s] 28%|██▊ | 14/50 [00:02<00:07, 4.79it/s] 30%|███ | 15/50 [00:03<00:07, 4.69it/s] 32%|███▏ | 16/50 [00:03<00:07, 4.69it/s] 34%|███▍ | 17/50 [00:03<00:07, 4.70it/s] 36%|███▌ | 18/50 [00:03<00:06, 4.77it/s] 38%|███▊ | 19/50 [00:04<00:06, 4.76it/s] 40%|████ | 20/50 [00:04<00:06, 4.73it/s] 42%|████▏ | 21/50 [00:04<00:06, 4.74it/s] 44%|████▍ | 22/50 [00:04<00:05, 4.72it/s] 46%|████▌ | 23/50 [00:04<00:05, 4.77it/s] 48%|████▊ | 24/50 [00:05<00:05, 4.76it/s] 50%|█████ | 25/50 [00:05<00:05, 4.73it/s] 52%|█████▏ | 26/50 [00:05<00:05, 4.71it/s] 54%|█████▍ | 27/50 [00:05<00:04, 4.74it/s] 56%|█████▌ | 28/50 [00:05<00:04, 4.78it/s] 58%|█████▊ | 29/50 [00:06<00:04, 4.72it/s] 60%|██████ | 30/50 [00:06<00:04, 4.75it/s] 62%|██████▏ | 31/50 [00:06<00:04, 4.72it/s] 64%|██████▍ | 32/50 [00:06<00:03, 4.75it/s] 66%|██████▌ | 33/50 [00:06<00:03, 4.77it/s] 68%|██████▊ | 34/50 [00:07<00:03, 4.70it/s] 70%|███████ | 35/50 [00:07<00:03, 4.66it/s] 72%|███████▏ | 36/50 [00:07<00:02, 4.71it/s] 74%|███████▍ | 37/50 [00:07<00:02, 4.70it/s] 76%|███████▌ | 38/50 [00:08<00:02, 4.71it/s] 78%|███████▊ | 39/50 [00:08<00:02, 4.69it/s] 80%|████████ | 40/50 [00:08<00:02, 4.67it/s] 82%|████████▏ | 41/50 [00:08<00:01, 4.67it/s] 84%|████████▍ | 42/50 [00:08<00:01, 4.70it/s] 86%|████████▌ | 43/50 [00:09<00:01, 4.68it/s] 88%|████████▊ | 44/50 [00:09<00:01, 4.68it/s] 90%|█████████ | 45/50 [00:09<00:01, 4.69it/s] 92%|█████████▏| 46/50 [00:09<00:00, 4.66it/s] 94%|█████████▍| 47/50 [00:09<00:00, 4.72it/s] 96%|█████████▌| 48/50 [00:10<00:00, 4.68it/s] 98%|█████████▊| 49/50 [00:10<00:00, 4.72it/s] 100%|██████████| 50/50 [00:10<00:00, 4.72it/s] 100%|██████████| 50/50 [00:10<00:00, 4.72it/s]Prediction
cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8IDkdi4pgrbchjmxb4kvzfq5tgm2aStatusSucceededSourceWebHardwareT4Total durationCreatedInput
- width
- 512
- height
- 512
- prompt
- Adorably cute qdg dog portrait, artstation winner by Victo Ngai, Kilian Eng and by Jake Parker, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution
- scheduler
- DDIM
- num_outputs
- 1
- guidance_scale
- 7.5
- negative_prompt
- cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 512, "height": 512, "prompt": "Adorably cute qdg dog portrait, artstation winner by Victo Ngai, Kilian Eng and by Jake Parker, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", { input: { width: 512, height: 512, prompt: "Adorably cute qdg dog portrait, artstation winner by Victo Ngai, Kilian Eng and by Jake Parker, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution", scheduler: "DDIM", num_outputs: 1, guidance_scale: 7.5, negative_prompt: "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", prompt_strength: 0.8, num_inference_steps: 50 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", input={ "width": 512, "height": 512, "prompt": "Adorably cute qdg dog portrait, artstation winner by Victo Ngai, Kilian Eng and by Jake Parker, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } ) # To access the file URL: print(output[0].url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output[0].read())To learn more, take a look at the guide on getting started with Python.
Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", "input": { "width": 512, "height": 512, "prompt": "Adorably cute qdg dog portrait, artstation winner by Victo Ngai, Kilian Eng and by Jake Parker, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8 \ -i 'width=512' \ -i 'height=512' \ -i 'prompt="Adorably cute qdg dog portrait, artstation winner by Victo Ngai, Kilian Eng and by Jake Parker, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution"' \ -i 'scheduler="DDIM"' \ -i 'num_outputs=1' \ -i 'guidance_scale=7.5' \ -i 'negative_prompt="cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark"' \ -i 'prompt_strength=0.8' \ -i 'num_inference_steps=50'To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 512, "height": 512, "prompt": "Adorably cute qdg dog portrait, artstation winner by Victo Ngai, Kilian Eng and by Jake Parker, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-06-18T20:58:34.072063Z", "created_at": "2023-06-18T20:58:22.700591Z", "data_removed": false, "error": null, "id": "kdi4pgrbchjmxb4kvzfq5tgm2a", "input": { "width": 512, "height": 512, "prompt": "Adorably cute qdg dog portrait, artstation winner by Victo Ngai, Kilian Eng and by Jake Parker, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 32928\nusing txt2img\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:12, 4.05it/s]\n 4%|▍ | 2/50 [00:00<00:10, 4.50it/s]\n 6%|▌ | 3/50 [00:00<00:09, 4.74it/s]\n 8%|▊ | 4/50 [00:00<00:09, 4.85it/s]\n 10%|█ | 5/50 [00:01<00:09, 4.84it/s]\n 12%|█▏ | 6/50 [00:01<00:09, 4.71it/s]\n 14%|█▍ | 7/50 [00:01<00:08, 4.79it/s]\n 16%|█▌ | 8/50 [00:01<00:08, 4.85it/s]\n 18%|█▊ | 9/50 [00:01<00:08, 4.90it/s]\n 20%|██ | 10/50 [00:02<00:08, 4.87it/s]\n 22%|██▏ | 11/50 [00:02<00:08, 4.76it/s]\n 24%|██▍ | 12/50 [00:02<00:07, 4.83it/s]\n 26%|██▌ | 13/50 [00:02<00:07, 4.87it/s]\n 28%|██▊ | 14/50 [00:02<00:07, 4.89it/s]\n 30%|███ | 15/50 [00:03<00:07, 4.87it/s]\n 32%|███▏ | 16/50 [00:03<00:07, 4.76it/s]\n 34%|███▍ | 17/50 [00:03<00:06, 4.80it/s]\n 36%|███▌ | 18/50 [00:03<00:06, 4.85it/s]\n 38%|███▊ | 19/50 [00:03<00:06, 4.87it/s]\n 40%|████ | 20/50 [00:04<00:06, 4.78it/s]\n 42%|████▏ | 21/50 [00:04<00:06, 4.77it/s]\n 44%|████▍ | 22/50 [00:04<00:05, 4.75it/s]\n 46%|████▌ | 23/50 [00:04<00:05, 4.80it/s]\n 48%|████▊ | 24/50 [00:05<00:05, 4.83it/s]\n 50%|█████ | 25/50 [00:05<00:05, 4.77it/s]\n 52%|█████▏ | 26/50 [00:05<00:05, 4.76it/s]\n 54%|█████▍ | 27/50 [00:05<00:04, 4.77it/s]\n 56%|█████▌ | 28/50 [00:05<00:04, 4.75it/s]\n 58%|█████▊ | 29/50 [00:06<00:04, 4.79it/s]\n 60%|██████ | 30/50 [00:06<00:04, 4.77it/s]\n 62%|██████▏ | 31/50 [00:06<00:03, 4.76it/s]\n 64%|██████▍ | 32/50 [00:06<00:03, 4.80it/s]\n 66%|██████▌ | 33/50 [00:06<00:03, 4.81it/s]\n 68%|██████▊ | 34/50 [00:07<00:03, 4.73it/s]\n 70%|███████ | 35/50 [00:07<00:03, 4.74it/s]\n 72%|███████▏ | 36/50 [00:07<00:02, 4.73it/s]\n 74%|███████▍ | 37/50 [00:07<00:02, 4.77it/s]\n 76%|███████▌ | 38/50 [00:07<00:02, 4.77it/s]\n 78%|███████▊ | 39/50 [00:08<00:02, 4.75it/s]\n 80%|████████ | 40/50 [00:08<00:02, 4.73it/s]\n 82%|████████▏ | 41/50 [00:08<00:01, 4.73it/s]\n 84%|████████▍ | 42/50 [00:08<00:01, 4.78it/s]\n 86%|████████▌ | 43/50 [00:09<00:01, 4.72it/s]\n 88%|████████▊ | 44/50 [00:09<00:01, 4.74it/s]\n 90%|█████████ | 45/50 [00:09<00:01, 4.68it/s]\n 92%|█████████▏| 46/50 [00:09<00:00, 4.65it/s]\n 94%|█████████▍| 47/50 [00:09<00:00, 4.71it/s]\n 96%|█████████▌| 48/50 [00:10<00:00, 4.68it/s]\n 98%|█████████▊| 49/50 [00:10<00:00, 4.70it/s]\n100%|██████████| 50/50 [00:10<00:00, 4.66it/s]\n100%|██████████| 50/50 [00:10<00:00, 4.76it/s]", "metrics": { "predict_time": 11.698467, "total_time": 11.371472 }, "output": [ "https://replicate.delivery/pbxt/DNMfMCNZad0wfE0oohZUpa1EiliDVa4T8Ukf0PYlhyTyPkOiA/out-0.png" ], "started_at": "2023-06-18T20:58:22.373596Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/kdi4pgrbchjmxb4kvzfq5tgm2a", "cancel": "https://api.replicate.com/v1/predictions/kdi4pgrbchjmxb4kvzfq5tgm2a/cancel" }, "version": "e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8" }Generated inUsing seed: 32928 using txt2img 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:12, 4.05it/s] 4%|▍ | 2/50 [00:00<00:10, 4.50it/s] 6%|▌ | 3/50 [00:00<00:09, 4.74it/s] 8%|▊ | 4/50 [00:00<00:09, 4.85it/s] 10%|█ | 5/50 [00:01<00:09, 4.84it/s] 12%|█▏ | 6/50 [00:01<00:09, 4.71it/s] 14%|█▍ | 7/50 [00:01<00:08, 4.79it/s] 16%|█▌ | 8/50 [00:01<00:08, 4.85it/s] 18%|█▊ | 9/50 [00:01<00:08, 4.90it/s] 20%|██ | 10/50 [00:02<00:08, 4.87it/s] 22%|██▏ | 11/50 [00:02<00:08, 4.76it/s] 24%|██▍ | 12/50 [00:02<00:07, 4.83it/s] 26%|██▌ | 13/50 [00:02<00:07, 4.87it/s] 28%|██▊ | 14/50 [00:02<00:07, 4.89it/s] 30%|███ | 15/50 [00:03<00:07, 4.87it/s] 32%|███▏ | 16/50 [00:03<00:07, 4.76it/s] 34%|███▍ | 17/50 [00:03<00:06, 4.80it/s] 36%|███▌ | 18/50 [00:03<00:06, 4.85it/s] 38%|███▊ | 19/50 [00:03<00:06, 4.87it/s] 40%|████ | 20/50 [00:04<00:06, 4.78it/s] 42%|████▏ | 21/50 [00:04<00:06, 4.77it/s] 44%|████▍ | 22/50 [00:04<00:05, 4.75it/s] 46%|████▌ | 23/50 [00:04<00:05, 4.80it/s] 48%|████▊ | 24/50 [00:05<00:05, 4.83it/s] 50%|█████ | 25/50 [00:05<00:05, 4.77it/s] 52%|█████▏ | 26/50 [00:05<00:05, 4.76it/s] 54%|█████▍ | 27/50 [00:05<00:04, 4.77it/s] 56%|█████▌ | 28/50 [00:05<00:04, 4.75it/s] 58%|█████▊ | 29/50 [00:06<00:04, 4.79it/s] 60%|██████ | 30/50 [00:06<00:04, 4.77it/s] 62%|██████▏ | 31/50 [00:06<00:03, 4.76it/s] 64%|██████▍ | 32/50 [00:06<00:03, 4.80it/s] 66%|██████▌ | 33/50 [00:06<00:03, 4.81it/s] 68%|██████▊ | 34/50 [00:07<00:03, 4.73it/s] 70%|███████ | 35/50 [00:07<00:03, 4.74it/s] 72%|███████▏ | 36/50 [00:07<00:02, 4.73it/s] 74%|███████▍ | 37/50 [00:07<00:02, 4.77it/s] 76%|███████▌ | 38/50 [00:07<00:02, 4.77it/s] 78%|███████▊ | 39/50 [00:08<00:02, 4.75it/s] 80%|████████ | 40/50 [00:08<00:02, 4.73it/s] 82%|████████▏ | 41/50 [00:08<00:01, 4.73it/s] 84%|████████▍ | 42/50 [00:08<00:01, 4.78it/s] 86%|████████▌ | 43/50 [00:09<00:01, 4.72it/s] 88%|████████▊ | 44/50 [00:09<00:01, 4.74it/s] 90%|█████████ | 45/50 [00:09<00:01, 4.68it/s] 92%|█████████▏| 46/50 [00:09<00:00, 4.65it/s] 94%|█████████▍| 47/50 [00:09<00:00, 4.71it/s] 96%|█████████▌| 48/50 [00:10<00:00, 4.68it/s] 98%|█████████▊| 49/50 [00:10<00:00, 4.70it/s] 100%|██████████| 50/50 [00:10<00:00, 4.66it/s] 100%|██████████| 50/50 [00:10<00:00, 4.76it/s]Prediction
cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8ID66dnmebb4pxjyiqeq6rpae2kiqStatusSucceededSourceWebHardwareT4Total durationCreatedInput
- width
- 512
- height
- 512
- prompt
- Adorably cute qdg dog portrait, artstation winner by Victo Ngai, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution
- scheduler
- DDIM
- num_outputs
- 1
- guidance_scale
- 7.5
- negative_prompt
- cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 512, "height": 512, "prompt": "Adorably cute qdg dog portrait, artstation winner by Victo Ngai, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", { input: { width: 512, height: 512, prompt: "Adorably cute qdg dog portrait, artstation winner by Victo Ngai, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution", scheduler: "DDIM", num_outputs: 1, guidance_scale: 7.5, negative_prompt: "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", prompt_strength: 0.8, num_inference_steps: 50 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", input={ "width": 512, "height": 512, "prompt": "Adorably cute qdg dog portrait, artstation winner by Victo Ngai, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } ) # To access the file URL: print(output[0].url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output[0].read())To learn more, take a look at the guide on getting started with Python.
Run cmenguy/toshiro-ai-1_5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "cmenguy/toshiro-ai-1_5:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8", "input": { "width": 512, "height": 512, "prompt": "Adorably cute qdg dog portrait, artstation winner by Victo Ngai, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8 \ -i 'width=512' \ -i 'height=512' \ -i 'prompt="Adorably cute qdg dog portrait, artstation winner by Victo Ngai, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution"' \ -i 'scheduler="DDIM"' \ -i 'num_outputs=1' \ -i 'guidance_scale=7.5' \ -i 'negative_prompt="cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark"' \ -i 'prompt_strength=0.8' \ -i 'num_inference_steps=50'To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/cmenguy/toshiro-ai-1_5@sha256:e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 512, "height": 512, "prompt": "Adorably cute qdg dog portrait, artstation winner by Victo Ngai, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-06-18T21:03:47.290381Z", "created_at": "2023-06-18T21:03:36.039038Z", "data_removed": false, "error": null, "id": "66dnmebb4pxjyiqeq6rpae2kiq", "input": { "width": 512, "height": 512, "prompt": "Adorably cute qdg dog portrait, artstation winner by Victo Ngai, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution", "scheduler": "DDIM", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 41889\nusing txt2img\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:12, 3.80it/s]\n 4%|▍ | 2/50 [00:00<00:11, 4.31it/s]\n 6%|▌ | 3/50 [00:00<00:10, 4.58it/s]\n 8%|▊ | 4/50 [00:00<00:09, 4.72it/s]\n 10%|█ | 5/50 [00:01<00:09, 4.76it/s]\n 12%|█▏ | 6/50 [00:01<00:09, 4.55it/s]\n 14%|█▍ | 7/50 [00:01<00:09, 4.65it/s]\n 16%|█▌ | 8/50 [00:01<00:08, 4.73it/s]\n 18%|█▊ | 9/50 [00:01<00:08, 4.75it/s]\n 20%|██ | 10/50 [00:02<00:08, 4.70it/s]\n 22%|██▏ | 11/50 [00:02<00:08, 4.57it/s]\n 24%|██▍ | 12/50 [00:02<00:08, 4.65it/s]\n 26%|██▌ | 13/50 [00:02<00:07, 4.72it/s]\n 28%|██▊ | 14/50 [00:03<00:07, 4.72it/s]\n 30%|███ | 15/50 [00:03<00:07, 4.67it/s]\n 32%|███▏ | 16/50 [00:03<00:07, 4.65it/s]\n 34%|███▍ | 17/50 [00:03<00:07, 4.63it/s]\n 36%|███▌ | 18/50 [00:03<00:06, 4.71it/s]\n 38%|███▊ | 19/50 [00:04<00:06, 4.74it/s]\n 40%|████ | 20/50 [00:04<00:06, 4.64it/s]\n 42%|████▏ | 21/50 [00:04<00:06, 4.63it/s]\n 44%|████▍ | 22/50 [00:04<00:06, 4.63it/s]\n 46%|████▌ | 23/50 [00:04<00:05, 4.71it/s]\n 48%|████▊ | 24/50 [00:05<00:05, 4.73it/s]\n 50%|█████ | 25/50 [00:05<00:05, 4.66it/s]\n 52%|█████▏ | 26/50 [00:05<00:05, 4.64it/s]\n 54%|█████▍ | 27/50 [00:05<00:04, 4.73it/s]\n 56%|█████▌ | 28/50 [00:05<00:04, 4.79it/s]\n 58%|█████▊ | 29/50 [00:06<00:04, 4.76it/s]\n 60%|██████ | 30/50 [00:06<00:04, 4.70it/s]\n 62%|██████▏ | 31/50 [00:06<00:04, 4.68it/s]\n 64%|██████▍ | 32/50 [00:06<00:03, 4.72it/s]\n 66%|██████▌ | 33/50 [00:07<00:03, 4.68it/s]\n 68%|██████▊ | 34/50 [00:07<00:03, 4.68it/s]\n 70%|███████ | 35/50 [00:07<00:03, 4.66it/s]\n 72%|███████▏ | 36/50 [00:07<00:03, 4.64it/s]\n 74%|███████▍ | 37/50 [00:07<00:02, 4.70it/s]\n 76%|███████▌ | 38/50 [00:08<00:02, 4.67it/s]\n 78%|███████▊ | 39/50 [00:08<00:02, 4.64it/s]\n 80%|████████ | 40/50 [00:08<00:02, 4.62it/s]\n 82%|████████▏ | 41/50 [00:08<00:01, 4.68it/s]\n 84%|████████▍ | 42/50 [00:08<00:01, 4.72it/s]\n 86%|████████▌ | 43/50 [00:09<00:01, 4.69it/s]\n 88%|████████▊ | 44/50 [00:09<00:01, 4.70it/s]\n 90%|█████████ | 45/50 [00:09<00:01, 4.66it/s]\n 92%|█████████▏| 46/50 [00:09<00:00, 4.64it/s]\n 94%|█████████▍| 47/50 [00:10<00:00, 4.70it/s]\n 96%|█████████▌| 48/50 [00:10<00:00, 4.65it/s]\n 98%|█████████▊| 49/50 [00:10<00:00, 4.63it/s]\n100%|██████████| 50/50 [00:10<00:00, 4.67it/s]\n100%|██████████| 50/50 [00:10<00:00, 4.67it/s]", "metrics": { "predict_time": 11.283343, "total_time": 11.251343 }, "output": [ "https://replicate.delivery/pbxt/zXusLqevnixgHKCeJofYofJ0THewK0JzvQpUSDBelsVxMj0RE/out-0.png" ], "started_at": "2023-06-18T21:03:36.007038Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/66dnmebb4pxjyiqeq6rpae2kiq", "cancel": "https://api.replicate.com/v1/predictions/66dnmebb4pxjyiqeq6rpae2kiq/cancel" }, "version": "e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8" }Generated inUsing seed: 41889 using txt2img 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:12, 3.80it/s] 4%|▍ | 2/50 [00:00<00:11, 4.31it/s] 6%|▌ | 3/50 [00:00<00:10, 4.58it/s] 8%|▊ | 4/50 [00:00<00:09, 4.72it/s] 10%|█ | 5/50 [00:01<00:09, 4.76it/s] 12%|█▏ | 6/50 [00:01<00:09, 4.55it/s] 14%|█▍ | 7/50 [00:01<00:09, 4.65it/s] 16%|█▌ | 8/50 [00:01<00:08, 4.73it/s] 18%|█▊ | 9/50 [00:01<00:08, 4.75it/s] 20%|██ | 10/50 [00:02<00:08, 4.70it/s] 22%|██▏ | 11/50 [00:02<00:08, 4.57it/s] 24%|██▍ | 12/50 [00:02<00:08, 4.65it/s] 26%|██▌ | 13/50 [00:02<00:07, 4.72it/s] 28%|██▊ | 14/50 [00:03<00:07, 4.72it/s] 30%|███ | 15/50 [00:03<00:07, 4.67it/s] 32%|███▏ | 16/50 [00:03<00:07, 4.65it/s] 34%|███▍ | 17/50 [00:03<00:07, 4.63it/s] 36%|███▌ | 18/50 [00:03<00:06, 4.71it/s] 38%|███▊ | 19/50 [00:04<00:06, 4.74it/s] 40%|████ | 20/50 [00:04<00:06, 4.64it/s] 42%|████▏ | 21/50 [00:04<00:06, 4.63it/s] 44%|████▍ | 22/50 [00:04<00:06, 4.63it/s] 46%|████▌ | 23/50 [00:04<00:05, 4.71it/s] 48%|████▊ | 24/50 [00:05<00:05, 4.73it/s] 50%|█████ | 25/50 [00:05<00:05, 4.66it/s] 52%|█████▏ | 26/50 [00:05<00:05, 4.64it/s] 54%|█████▍ | 27/50 [00:05<00:04, 4.73it/s] 56%|█████▌ | 28/50 [00:05<00:04, 4.79it/s] 58%|█████▊ | 29/50 [00:06<00:04, 4.76it/s] 60%|██████ | 30/50 [00:06<00:04, 4.70it/s] 62%|██████▏ | 31/50 [00:06<00:04, 4.68it/s] 64%|██████▍ | 32/50 [00:06<00:03, 4.72it/s] 66%|██████▌ | 33/50 [00:07<00:03, 4.68it/s] 68%|██████▊ | 34/50 [00:07<00:03, 4.68it/s] 70%|███████ | 35/50 [00:07<00:03, 4.66it/s] 72%|███████▏ | 36/50 [00:07<00:03, 4.64it/s] 74%|███████▍ | 37/50 [00:07<00:02, 4.70it/s] 76%|███████▌ | 38/50 [00:08<00:02, 4.67it/s] 78%|███████▊ | 39/50 [00:08<00:02, 4.64it/s] 80%|████████ | 40/50 [00:08<00:02, 4.62it/s] 82%|████████▏ | 41/50 [00:08<00:01, 4.68it/s] 84%|████████▍ | 42/50 [00:08<00:01, 4.72it/s] 86%|████████▌ | 43/50 [00:09<00:01, 4.69it/s] 88%|████████▊ | 44/50 [00:09<00:01, 4.70it/s] 90%|█████████ | 45/50 [00:09<00:01, 4.66it/s] 92%|█████████▏| 46/50 [00:09<00:00, 4.64it/s] 94%|█████████▍| 47/50 [00:10<00:00, 4.70it/s] 96%|█████████▌| 48/50 [00:10<00:00, 4.65it/s] 98%|█████████▊| 49/50 [00:10<00:00, 4.63it/s] 100%|██████████| 50/50 [00:10<00:00, 4.67it/s] 100%|██████████| 50/50 [00:10<00:00, 4.67it/s]
Want to make some of these yourself?
Run this model