raviadi12 / diffusion-testing
Testing
- Public
- 129 runs
-
L40S
- SDXL fine-tune
Prediction
raviadi12/diffusion-testing:2bccf2b55b92722cc8f6aa12b49af6da4557607b3ca9d3492a211cbd0697a15cID87btrhm4m1rgp0cfjk19g3sftwStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- a photo of TOK
- refine
- no_refiner
- scheduler
- K_EULER
- lora_scale
- 0.6
- num_outputs
- 1
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "image": "https://www.static-src.com/wcsstore/Indraprastha/images/catalog/full//catalog-image/111/MTA-131896587/no-brand_no-brand_full01.jpg", "width": 1024, "height": 1024, "prompt": "a photo of TOK", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run raviadi12/diffusion-testing using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "raviadi12/diffusion-testing:2bccf2b55b92722cc8f6aa12b49af6da4557607b3ca9d3492a211cbd0697a15c", { input: { image: "https://www.static-src.com/wcsstore/Indraprastha/images/catalog/full//catalog-image/111/MTA-131896587/no-brand_no-brand_full01.jpg", width: 1024, height: 1024, prompt: "a photo of TOK", refine: "no_refiner", scheduler: "K_EULER", lora_scale: 0.6, num_outputs: 1, guidance_scale: 7.5, apply_watermark: true, high_noise_frac: 0.8, negative_prompt: "", 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 replicate
Import the client:import replicate
Run raviadi12/diffusion-testing using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "raviadi12/diffusion-testing:2bccf2b55b92722cc8f6aa12b49af6da4557607b3ca9d3492a211cbd0697a15c", input={ "image": "https://www.static-src.com/wcsstore/Indraprastha/images/catalog/full//catalog-image/111/MTA-131896587/no-brand_no-brand_full01.jpg", "width": 1024, "height": 1024, "prompt": "a photo of TOK", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": True, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run raviadi12/diffusion-testing 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": "raviadi12/diffusion-testing:2bccf2b55b92722cc8f6aa12b49af6da4557607b3ca9d3492a211cbd0697a15c", "input": { "image": "https://www.static-src.com/wcsstore/Indraprastha/images/catalog/full//catalog-image/111/MTA-131896587/no-brand_no-brand_full01.jpg", "width": 1024, "height": 1024, "prompt": "a photo of TOK", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-05-20T06:48:58.515264Z", "created_at": "2024-05-20T06:48:47.008000Z", "data_removed": false, "error": null, "id": "87btrhm4m1rgp0cfjk19g3sftw", "input": { "image": "https://www.static-src.com/wcsstore/Indraprastha/images/catalog/full//catalog-image/111/MTA-131896587/no-brand_no-brand_full01.jpg", "width": 1024, "height": 1024, "prompt": "a photo of TOK", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 58631\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: a photo of <s0><s1>\nimg2img mode\n 0%| | 0/40 [00:00<?, ?it/s]\n 2%|▎ | 1/40 [00:00<00:06, 5.82it/s]\n 5%|▌ | 2/40 [00:00<00:06, 5.81it/s]\n 8%|▊ | 3/40 [00:00<00:06, 5.81it/s]\n 10%|█ | 4/40 [00:00<00:06, 5.82it/s]\n 12%|█▎ | 5/40 [00:00<00:06, 5.83it/s]\n 15%|█▌ | 6/40 [00:01<00:05, 5.83it/s]\n 18%|█▊ | 7/40 [00:01<00:05, 5.83it/s]\n 20%|██ | 8/40 [00:01<00:05, 5.83it/s]\n 22%|██▎ | 9/40 [00:01<00:05, 5.83it/s]\n 25%|██▌ | 10/40 [00:01<00:05, 5.83it/s]\n 28%|██▊ | 11/40 [00:01<00:04, 5.83it/s]\n 30%|███ | 12/40 [00:02<00:04, 5.83it/s]\n 32%|███▎ | 13/40 [00:02<00:04, 5.83it/s]\n 35%|███▌ | 14/40 [00:02<00:04, 5.83it/s]\n 38%|███▊ | 15/40 [00:02<00:04, 5.82it/s]\n 40%|████ | 16/40 [00:02<00:04, 5.83it/s]\n 42%|████▎ | 17/40 [00:02<00:03, 5.83it/s]\n 45%|████▌ | 18/40 [00:03<00:03, 5.83it/s]\n 48%|████▊ | 19/40 [00:03<00:03, 5.82it/s]\n 50%|█████ | 20/40 [00:03<00:03, 5.83it/s]\n 52%|█████▎ | 21/40 [00:03<00:03, 5.83it/s]\n 55%|█████▌ | 22/40 [00:03<00:03, 5.83it/s]\n 57%|█████▊ | 23/40 [00:03<00:02, 5.83it/s]\n 60%|██████ | 24/40 [00:04<00:02, 5.82it/s]\n 62%|██████▎ | 25/40 [00:04<00:02, 5.83it/s]\n 65%|██████▌ | 26/40 [00:04<00:02, 5.83it/s]\n 68%|██████▊ | 27/40 [00:04<00:02, 5.82it/s]\n 70%|███████ | 28/40 [00:04<00:02, 5.83it/s]\n 72%|███████▎ | 29/40 [00:04<00:01, 5.83it/s]\n 75%|███████▌ | 30/40 [00:05<00:01, 5.83it/s]\n 78%|███████▊ | 31/40 [00:05<00:01, 5.82it/s]\n 80%|████████ | 32/40 [00:05<00:01, 5.82it/s]\n 82%|████████▎ | 33/40 [00:05<00:01, 5.82it/s]\n 85%|████████▌ | 34/40 [00:05<00:01, 5.82it/s]\n 88%|████████▊ | 35/40 [00:06<00:00, 5.82it/s]\n 90%|█████████ | 36/40 [00:06<00:00, 5.82it/s]\n 92%|█████████▎| 37/40 [00:06<00:00, 5.82it/s]\n 95%|█████████▌| 38/40 [00:06<00:00, 5.82it/s]\n 98%|█████████▊| 39/40 [00:06<00:00, 5.82it/s]\n100%|██████████| 40/40 [00:06<00:00, 5.81it/s]\n100%|██████████| 40/40 [00:06<00:00, 5.82it/s]", "metrics": { "predict_time": 8.767386, "total_time": 11.507264 }, "output": [ "https://replicate.delivery/pbxt/MLIEVA7fK3SCKaKfG5pv1Dp0ZBke5T8noSHI17ZlpU21iUslA/out-0.png" ], "started_at": "2024-05-20T06:48:49.747878Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/87btrhm4m1rgp0cfjk19g3sftw", "cancel": "https://api.replicate.com/v1/predictions/87btrhm4m1rgp0cfjk19g3sftw/cancel" }, "version": "2bccf2b55b92722cc8f6aa12b49af6da4557607b3ca9d3492a211cbd0697a15c" }
Generated inUsing seed: 58631 Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: a photo of <s0><s1> img2img mode 0%| | 0/40 [00:00<?, ?it/s] 2%|▎ | 1/40 [00:00<00:06, 5.82it/s] 5%|▌ | 2/40 [00:00<00:06, 5.81it/s] 8%|▊ | 3/40 [00:00<00:06, 5.81it/s] 10%|█ | 4/40 [00:00<00:06, 5.82it/s] 12%|█▎ | 5/40 [00:00<00:06, 5.83it/s] 15%|█▌ | 6/40 [00:01<00:05, 5.83it/s] 18%|█▊ | 7/40 [00:01<00:05, 5.83it/s] 20%|██ | 8/40 [00:01<00:05, 5.83it/s] 22%|██▎ | 9/40 [00:01<00:05, 5.83it/s] 25%|██▌ | 10/40 [00:01<00:05, 5.83it/s] 28%|██▊ | 11/40 [00:01<00:04, 5.83it/s] 30%|███ | 12/40 [00:02<00:04, 5.83it/s] 32%|███▎ | 13/40 [00:02<00:04, 5.83it/s] 35%|███▌ | 14/40 [00:02<00:04, 5.83it/s] 38%|███▊ | 15/40 [00:02<00:04, 5.82it/s] 40%|████ | 16/40 [00:02<00:04, 5.83it/s] 42%|████▎ | 17/40 [00:02<00:03, 5.83it/s] 45%|████▌ | 18/40 [00:03<00:03, 5.83it/s] 48%|████▊ | 19/40 [00:03<00:03, 5.82it/s] 50%|█████ | 20/40 [00:03<00:03, 5.83it/s] 52%|█████▎ | 21/40 [00:03<00:03, 5.83it/s] 55%|█████▌ | 22/40 [00:03<00:03, 5.83it/s] 57%|█████▊ | 23/40 [00:03<00:02, 5.83it/s] 60%|██████ | 24/40 [00:04<00:02, 5.82it/s] 62%|██████▎ | 25/40 [00:04<00:02, 5.83it/s] 65%|██████▌ | 26/40 [00:04<00:02, 5.83it/s] 68%|██████▊ | 27/40 [00:04<00:02, 5.82it/s] 70%|███████ | 28/40 [00:04<00:02, 5.83it/s] 72%|███████▎ | 29/40 [00:04<00:01, 5.83it/s] 75%|███████▌ | 30/40 [00:05<00:01, 5.83it/s] 78%|███████▊ | 31/40 [00:05<00:01, 5.82it/s] 80%|████████ | 32/40 [00:05<00:01, 5.82it/s] 82%|████████▎ | 33/40 [00:05<00:01, 5.82it/s] 85%|████████▌ | 34/40 [00:05<00:01, 5.82it/s] 88%|████████▊ | 35/40 [00:06<00:00, 5.82it/s] 90%|█████████ | 36/40 [00:06<00:00, 5.82it/s] 92%|█████████▎| 37/40 [00:06<00:00, 5.82it/s] 95%|█████████▌| 38/40 [00:06<00:00, 5.82it/s] 98%|█████████▊| 39/40 [00:06<00:00, 5.82it/s] 100%|██████████| 40/40 [00:06<00:00, 5.81it/s] 100%|██████████| 40/40 [00:06<00:00, 5.82it/s]
Prediction
raviadi12/diffusion-testing:2bccf2b55b92722cc8f6aa12b49af6da4557607b3ca9d3492a211cbd0697a15cIDr7pxe69fg9rgj0cfhdyag4mpx8StatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- a photo of TOK
- refine
- no_refiner
- scheduler
- K_EULER
- lora_scale
- 0.6
- num_outputs
- 1
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "image": "https://replicate.delivery/pbxt/KwLoUsaZVbACMqyxFdGkqhxUGUXbf4U5X25hAq2yYGhptBC6/mask.png", "width": 1024, "height": 1024, "prompt": "a photo of TOK", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run raviadi12/diffusion-testing using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "raviadi12/diffusion-testing:2bccf2b55b92722cc8f6aa12b49af6da4557607b3ca9d3492a211cbd0697a15c", { input: { image: "https://replicate.delivery/pbxt/KwLoUsaZVbACMqyxFdGkqhxUGUXbf4U5X25hAq2yYGhptBC6/mask.png", width: 1024, height: 1024, prompt: "a photo of TOK", refine: "no_refiner", scheduler: "K_EULER", lora_scale: 0.6, num_outputs: 1, guidance_scale: 7.5, apply_watermark: true, high_noise_frac: 0.8, negative_prompt: "", 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 replicate
Import the client:import replicate
Run raviadi12/diffusion-testing using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "raviadi12/diffusion-testing:2bccf2b55b92722cc8f6aa12b49af6da4557607b3ca9d3492a211cbd0697a15c", input={ "image": "https://replicate.delivery/pbxt/KwLoUsaZVbACMqyxFdGkqhxUGUXbf4U5X25hAq2yYGhptBC6/mask.png", "width": 1024, "height": 1024, "prompt": "a photo of TOK", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": True, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run raviadi12/diffusion-testing 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": "raviadi12/diffusion-testing:2bccf2b55b92722cc8f6aa12b49af6da4557607b3ca9d3492a211cbd0697a15c", "input": { "image": "https://replicate.delivery/pbxt/KwLoUsaZVbACMqyxFdGkqhxUGUXbf4U5X25hAq2yYGhptBC6/mask.png", "width": 1024, "height": 1024, "prompt": "a photo of TOK", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-05-18T11:35:32.201807Z", "created_at": "2024-05-18T11:35:22.754000Z", "data_removed": false, "error": null, "id": "r7pxe69fg9rgj0cfhdyag4mpx8", "input": { "image": "https://replicate.delivery/pbxt/KwLoUsaZVbACMqyxFdGkqhxUGUXbf4U5X25hAq2yYGhptBC6/mask.png", "width": 1024, "height": 1024, "prompt": "a photo of TOK", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 17714\nskipping loading .. weights already loaded\nPrompt: a photo of <s0><s1>\nimg2img mode\n 0%| | 0/40 [00:00<?, ?it/s]\n 2%|▎ | 1/40 [00:00<00:07, 4.93it/s]\n 5%|▌ | 2/40 [00:00<00:07, 4.91it/s]\n 8%|▊ | 3/40 [00:00<00:07, 4.91it/s]\n 10%|█ | 4/40 [00:00<00:07, 4.91it/s]\n 12%|█▎ | 5/40 [00:01<00:07, 4.90it/s]\n 15%|█▌ | 6/40 [00:01<00:06, 4.90it/s]\n 18%|█▊ | 7/40 [00:01<00:06, 4.89it/s]\n 20%|██ | 8/40 [00:01<00:06, 4.90it/s]\n 22%|██▎ | 9/40 [00:01<00:06, 4.89it/s]\n 25%|██▌ | 10/40 [00:02<00:06, 4.89it/s]\n 28%|██▊ | 11/40 [00:02<00:05, 4.89it/s]\n 30%|███ | 12/40 [00:02<00:05, 4.89it/s]\n 32%|███▎ | 13/40 [00:02<00:05, 4.89it/s]\n 35%|███▌ | 14/40 [00:02<00:05, 4.89it/s]\n 38%|███▊ | 15/40 [00:03<00:05, 4.89it/s]\n 40%|████ | 16/40 [00:03<00:04, 4.88it/s]\n 42%|████▎ | 17/40 [00:03<00:04, 4.88it/s]\n 45%|████▌ | 18/40 [00:03<00:04, 4.89it/s]\n 48%|████▊ | 19/40 [00:03<00:04, 4.89it/s]\n 50%|█████ | 20/40 [00:04<00:04, 4.89it/s]\n 52%|█████▎ | 21/40 [00:04<00:03, 4.89it/s]\n 55%|█████▌ | 22/40 [00:04<00:03, 4.88it/s]\n 57%|█████▊ | 23/40 [00:04<00:03, 4.88it/s]\n 60%|██████ | 24/40 [00:04<00:03, 4.88it/s]\n 62%|██████▎ | 25/40 [00:05<00:03, 4.88it/s]\n 65%|██████▌ | 26/40 [00:05<00:02, 4.88it/s]\n 68%|██████▊ | 27/40 [00:05<00:02, 4.87it/s]\n 70%|███████ | 28/40 [00:05<00:02, 4.88it/s]\n 72%|███████▎ | 29/40 [00:05<00:02, 4.88it/s]\n 75%|███████▌ | 30/40 [00:06<00:02, 4.88it/s]\n 78%|███████▊ | 31/40 [00:06<00:01, 4.86it/s]\n 80%|████████ | 32/40 [00:06<00:01, 4.84it/s]\n 82%|████████▎ | 33/40 [00:06<00:01, 4.85it/s]\n 85%|████████▌ | 34/40 [00:06<00:01, 4.86it/s]\n 88%|████████▊ | 35/40 [00:07<00:01, 4.87it/s]\n 90%|█████████ | 36/40 [00:07<00:00, 4.87it/s]\n 92%|█████████▎| 37/40 [00:07<00:00, 4.87it/s]\n 95%|█████████▌| 38/40 [00:07<00:00, 4.88it/s]\n 98%|█████████▊| 39/40 [00:07<00:00, 4.88it/s]\n100%|██████████| 40/40 [00:08<00:00, 4.88it/s]\n100%|██████████| 40/40 [00:08<00:00, 4.88it/s]", "metrics": { "predict_time": 9.427631, "total_time": 9.447807 }, "output": [ "https://replicate.delivery/pbxt/zT2QOy4BGvp2KVWGf0Z4YohNZC4nTFZDTOpuiGBd4w2BJyaJA/out-0.png" ], "started_at": "2024-05-18T11:35:22.774176Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/r7pxe69fg9rgj0cfhdyag4mpx8", "cancel": "https://api.replicate.com/v1/predictions/r7pxe69fg9rgj0cfhdyag4mpx8/cancel" }, "version": "2bccf2b55b92722cc8f6aa12b49af6da4557607b3ca9d3492a211cbd0697a15c" }
Generated inUsing seed: 17714 skipping loading .. weights already loaded Prompt: a photo of <s0><s1> img2img mode 0%| | 0/40 [00:00<?, ?it/s] 2%|▎ | 1/40 [00:00<00:07, 4.93it/s] 5%|▌ | 2/40 [00:00<00:07, 4.91it/s] 8%|▊ | 3/40 [00:00<00:07, 4.91it/s] 10%|█ | 4/40 [00:00<00:07, 4.91it/s] 12%|█▎ | 5/40 [00:01<00:07, 4.90it/s] 15%|█▌ | 6/40 [00:01<00:06, 4.90it/s] 18%|█▊ | 7/40 [00:01<00:06, 4.89it/s] 20%|██ | 8/40 [00:01<00:06, 4.90it/s] 22%|██▎ | 9/40 [00:01<00:06, 4.89it/s] 25%|██▌ | 10/40 [00:02<00:06, 4.89it/s] 28%|██▊ | 11/40 [00:02<00:05, 4.89it/s] 30%|███ | 12/40 [00:02<00:05, 4.89it/s] 32%|███▎ | 13/40 [00:02<00:05, 4.89it/s] 35%|███▌ | 14/40 [00:02<00:05, 4.89it/s] 38%|███▊ | 15/40 [00:03<00:05, 4.89it/s] 40%|████ | 16/40 [00:03<00:04, 4.88it/s] 42%|████▎ | 17/40 [00:03<00:04, 4.88it/s] 45%|████▌ | 18/40 [00:03<00:04, 4.89it/s] 48%|████▊ | 19/40 [00:03<00:04, 4.89it/s] 50%|█████ | 20/40 [00:04<00:04, 4.89it/s] 52%|█████▎ | 21/40 [00:04<00:03, 4.89it/s] 55%|█████▌ | 22/40 [00:04<00:03, 4.88it/s] 57%|█████▊ | 23/40 [00:04<00:03, 4.88it/s] 60%|██████ | 24/40 [00:04<00:03, 4.88it/s] 62%|██████▎ | 25/40 [00:05<00:03, 4.88it/s] 65%|██████▌ | 26/40 [00:05<00:02, 4.88it/s] 68%|██████▊ | 27/40 [00:05<00:02, 4.87it/s] 70%|███████ | 28/40 [00:05<00:02, 4.88it/s] 72%|███████▎ | 29/40 [00:05<00:02, 4.88it/s] 75%|███████▌ | 30/40 [00:06<00:02, 4.88it/s] 78%|███████▊ | 31/40 [00:06<00:01, 4.86it/s] 80%|████████ | 32/40 [00:06<00:01, 4.84it/s] 82%|████████▎ | 33/40 [00:06<00:01, 4.85it/s] 85%|████████▌ | 34/40 [00:06<00:01, 4.86it/s] 88%|████████▊ | 35/40 [00:07<00:01, 4.87it/s] 90%|█████████ | 36/40 [00:07<00:00, 4.87it/s] 92%|█████████▎| 37/40 [00:07<00:00, 4.87it/s] 95%|█████████▌| 38/40 [00:07<00:00, 4.88it/s] 98%|█████████▊| 39/40 [00:07<00:00, 4.88it/s] 100%|██████████| 40/40 [00:08<00:00, 4.88it/s] 100%|██████████| 40/40 [00:08<00:00, 4.88it/s]
Prediction
raviadi12/diffusion-testing:2bccf2b55b92722cc8f6aa12b49af6da4557607b3ca9d3492a211cbd0697a15cIDpw1p5dcz0xrgm0cfhdy8jvmermStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- a photo of TOK
- refine
- no_refiner
- scheduler
- K_EULER
- lora_scale
- 0.6
- num_outputs
- 1
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "image": "https://replicate.delivery/pbxt/KwLowoMP4zgobtrkPnevZ8rFwQi0QOnLoLwwIjjF9cv1B6mg/mask.png", "width": 1024, "height": 1024, "prompt": "a photo of TOK", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run raviadi12/diffusion-testing using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "raviadi12/diffusion-testing:2bccf2b55b92722cc8f6aa12b49af6da4557607b3ca9d3492a211cbd0697a15c", { input: { image: "https://replicate.delivery/pbxt/KwLowoMP4zgobtrkPnevZ8rFwQi0QOnLoLwwIjjF9cv1B6mg/mask.png", width: 1024, height: 1024, prompt: "a photo of TOK", refine: "no_refiner", scheduler: "K_EULER", lora_scale: 0.6, num_outputs: 1, guidance_scale: 7.5, apply_watermark: true, high_noise_frac: 0.8, negative_prompt: "", 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 replicate
Import the client:import replicate
Run raviadi12/diffusion-testing using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "raviadi12/diffusion-testing:2bccf2b55b92722cc8f6aa12b49af6da4557607b3ca9d3492a211cbd0697a15c", input={ "image": "https://replicate.delivery/pbxt/KwLowoMP4zgobtrkPnevZ8rFwQi0QOnLoLwwIjjF9cv1B6mg/mask.png", "width": 1024, "height": 1024, "prompt": "a photo of TOK", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": True, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run raviadi12/diffusion-testing 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": "raviadi12/diffusion-testing:2bccf2b55b92722cc8f6aa12b49af6da4557607b3ca9d3492a211cbd0697a15c", "input": { "image": "https://replicate.delivery/pbxt/KwLowoMP4zgobtrkPnevZ8rFwQi0QOnLoLwwIjjF9cv1B6mg/mask.png", "width": 1024, "height": 1024, "prompt": "a photo of TOK", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-05-18T11:36:02.525362Z", "created_at": "2024-05-18T11:35:51.303000Z", "data_removed": false, "error": null, "id": "pw1p5dcz0xrgm0cfhdy8jvmerm", "input": { "image": "https://replicate.delivery/pbxt/KwLowoMP4zgobtrkPnevZ8rFwQi0QOnLoLwwIjjF9cv1B6mg/mask.png", "width": 1024, "height": 1024, "prompt": "a photo of TOK", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 53797\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: a photo of <s0><s1>\nimg2img mode\n 0%| | 0/40 [00:00<?, ?it/s]\n 2%|▎ | 1/40 [00:00<00:08, 4.63it/s]\n 5%|▌ | 2/40 [00:00<00:07, 4.83it/s]\n 8%|▊ | 3/40 [00:00<00:07, 4.88it/s]\n 10%|█ | 4/40 [00:00<00:07, 4.92it/s]\n 12%|█▎ | 5/40 [00:01<00:07, 4.92it/s]\n 15%|█▌ | 6/40 [00:01<00:06, 4.93it/s]\n 18%|█▊ | 7/40 [00:01<00:06, 4.94it/s]\n 20%|██ | 8/40 [00:01<00:06, 4.96it/s]\n 22%|██▎ | 9/40 [00:01<00:06, 4.97it/s]\n 25%|██▌ | 10/40 [00:02<00:06, 4.97it/s]\n 28%|██▊ | 11/40 [00:02<00:05, 4.97it/s]\n 30%|███ | 12/40 [00:02<00:05, 4.97it/s]\n 32%|███▎ | 13/40 [00:02<00:05, 4.98it/s]\n 35%|███▌ | 14/40 [00:02<00:05, 4.98it/s]\n 38%|███▊ | 15/40 [00:03<00:05, 4.99it/s]\n 40%|████ | 16/40 [00:03<00:04, 4.98it/s]\n 42%|████▎ | 17/40 [00:03<00:04, 4.98it/s]\n 45%|████▌ | 18/40 [00:03<00:04, 4.98it/s]\n 48%|████▊ | 19/40 [00:03<00:04, 4.99it/s]\n 50%|█████ | 20/40 [00:04<00:04, 4.98it/s]\n 52%|█████▎ | 21/40 [00:04<00:03, 4.98it/s]\n 55%|█████▌ | 22/40 [00:04<00:03, 4.98it/s]\n 57%|█████▊ | 23/40 [00:04<00:03, 4.98it/s]\n 60%|██████ | 24/40 [00:04<00:03, 4.98it/s]\n 62%|██████▎ | 25/40 [00:05<00:03, 4.98it/s]\n 65%|██████▌ | 26/40 [00:05<00:02, 4.98it/s]\n 68%|██████▊ | 27/40 [00:05<00:02, 4.98it/s]\n 70%|███████ | 28/40 [00:05<00:02, 4.98it/s]\n 72%|███████▎ | 29/40 [00:05<00:02, 4.98it/s]\n 75%|███████▌ | 30/40 [00:06<00:02, 4.98it/s]\n 78%|███████▊ | 31/40 [00:06<00:01, 4.97it/s]\n 80%|████████ | 32/40 [00:06<00:01, 4.96it/s]\n 82%|████████▎ | 33/40 [00:06<00:01, 4.97it/s]\n 85%|████████▌ | 34/40 [00:06<00:01, 4.97it/s]\n 88%|████████▊ | 35/40 [00:07<00:01, 4.98it/s]\n 90%|█████████ | 36/40 [00:07<00:00, 4.97it/s]\n 92%|█████████▎| 37/40 [00:07<00:00, 4.97it/s]\n 95%|█████████▌| 38/40 [00:07<00:00, 4.98it/s]\n 98%|█████████▊| 39/40 [00:07<00:00, 4.98it/s]\n100%|██████████| 40/40 [00:08<00:00, 4.98it/s]\n100%|██████████| 40/40 [00:08<00:00, 4.97it/s]", "metrics": { "predict_time": 10.069035, "total_time": 11.222362 }, "output": [ "https://replicate.delivery/pbxt/VpeG4IaDWXUvCiLTKGSE7oxljfpYmWHsMqXJehPeFXKLKRWLB/out-0.png" ], "started_at": "2024-05-18T11:35:52.456327Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/pw1p5dcz0xrgm0cfhdy8jvmerm", "cancel": "https://api.replicate.com/v1/predictions/pw1p5dcz0xrgm0cfhdy8jvmerm/cancel" }, "version": "2bccf2b55b92722cc8f6aa12b49af6da4557607b3ca9d3492a211cbd0697a15c" }
Generated inUsing seed: 53797 Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: a photo of <s0><s1> img2img mode 0%| | 0/40 [00:00<?, ?it/s] 2%|▎ | 1/40 [00:00<00:08, 4.63it/s] 5%|▌ | 2/40 [00:00<00:07, 4.83it/s] 8%|▊ | 3/40 [00:00<00:07, 4.88it/s] 10%|█ | 4/40 [00:00<00:07, 4.92it/s] 12%|█▎ | 5/40 [00:01<00:07, 4.92it/s] 15%|█▌ | 6/40 [00:01<00:06, 4.93it/s] 18%|█▊ | 7/40 [00:01<00:06, 4.94it/s] 20%|██ | 8/40 [00:01<00:06, 4.96it/s] 22%|██▎ | 9/40 [00:01<00:06, 4.97it/s] 25%|██▌ | 10/40 [00:02<00:06, 4.97it/s] 28%|██▊ | 11/40 [00:02<00:05, 4.97it/s] 30%|███ | 12/40 [00:02<00:05, 4.97it/s] 32%|███▎ | 13/40 [00:02<00:05, 4.98it/s] 35%|███▌ | 14/40 [00:02<00:05, 4.98it/s] 38%|███▊ | 15/40 [00:03<00:05, 4.99it/s] 40%|████ | 16/40 [00:03<00:04, 4.98it/s] 42%|████▎ | 17/40 [00:03<00:04, 4.98it/s] 45%|████▌ | 18/40 [00:03<00:04, 4.98it/s] 48%|████▊ | 19/40 [00:03<00:04, 4.99it/s] 50%|█████ | 20/40 [00:04<00:04, 4.98it/s] 52%|█████▎ | 21/40 [00:04<00:03, 4.98it/s] 55%|█████▌ | 22/40 [00:04<00:03, 4.98it/s] 57%|█████▊ | 23/40 [00:04<00:03, 4.98it/s] 60%|██████ | 24/40 [00:04<00:03, 4.98it/s] 62%|██████▎ | 25/40 [00:05<00:03, 4.98it/s] 65%|██████▌ | 26/40 [00:05<00:02, 4.98it/s] 68%|██████▊ | 27/40 [00:05<00:02, 4.98it/s] 70%|███████ | 28/40 [00:05<00:02, 4.98it/s] 72%|███████▎ | 29/40 [00:05<00:02, 4.98it/s] 75%|███████▌ | 30/40 [00:06<00:02, 4.98it/s] 78%|███████▊ | 31/40 [00:06<00:01, 4.97it/s] 80%|████████ | 32/40 [00:06<00:01, 4.96it/s] 82%|████████▎ | 33/40 [00:06<00:01, 4.97it/s] 85%|████████▌ | 34/40 [00:06<00:01, 4.97it/s] 88%|████████▊ | 35/40 [00:07<00:01, 4.98it/s] 90%|█████████ | 36/40 [00:07<00:00, 4.97it/s] 92%|█████████▎| 37/40 [00:07<00:00, 4.97it/s] 95%|█████████▌| 38/40 [00:07<00:00, 4.98it/s] 98%|█████████▊| 39/40 [00:07<00:00, 4.98it/s] 100%|██████████| 40/40 [00:08<00:00, 4.98it/s] 100%|██████████| 40/40 [00:08<00:00, 4.97it/s]
Prediction
raviadi12/diffusion-testing:2bccf2b55b92722cc8f6aa12b49af6da4557607b3ca9d3492a211cbd0697a15cID983cq2ebfnrgj0cfhe2ajfk14wStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- a photo of TOK
- refine
- no_refiner
- scheduler
- K_EULER
- lora_scale
- 0.6
- num_outputs
- 1
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "image": "https://replicate.delivery/pbxt/KwLxOx30Vl1VrQ9g4Bb0c4VA8JoN1l0XPjNlXWHLIlFKK1bD/mask3.jpg", "width": 1024, "height": 1024, "prompt": "a photo of TOK", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run raviadi12/diffusion-testing using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "raviadi12/diffusion-testing:2bccf2b55b92722cc8f6aa12b49af6da4557607b3ca9d3492a211cbd0697a15c", { input: { image: "https://replicate.delivery/pbxt/KwLxOx30Vl1VrQ9g4Bb0c4VA8JoN1l0XPjNlXWHLIlFKK1bD/mask3.jpg", width: 1024, height: 1024, prompt: "a photo of TOK", refine: "no_refiner", scheduler: "K_EULER", lora_scale: 0.6, num_outputs: 1, guidance_scale: 7.5, apply_watermark: true, high_noise_frac: 0.8, negative_prompt: "", 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 replicate
Import the client:import replicate
Run raviadi12/diffusion-testing using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "raviadi12/diffusion-testing:2bccf2b55b92722cc8f6aa12b49af6da4557607b3ca9d3492a211cbd0697a15c", input={ "image": "https://replicate.delivery/pbxt/KwLxOx30Vl1VrQ9g4Bb0c4VA8JoN1l0XPjNlXWHLIlFKK1bD/mask3.jpg", "width": 1024, "height": 1024, "prompt": "a photo of TOK", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": True, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run raviadi12/diffusion-testing 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": "raviadi12/diffusion-testing:2bccf2b55b92722cc8f6aa12b49af6da4557607b3ca9d3492a211cbd0697a15c", "input": { "image": "https://replicate.delivery/pbxt/KwLxOx30Vl1VrQ9g4Bb0c4VA8JoN1l0XPjNlXWHLIlFKK1bD/mask3.jpg", "width": 1024, "height": 1024, "prompt": "a photo of TOK", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-05-18T11:45:02.701045Z", "created_at": "2024-05-18T11:44:46.973000Z", "data_removed": false, "error": null, "id": "983cq2ebfnrgj0cfhe2ajfk14w", "input": { "image": "https://replicate.delivery/pbxt/KwLxOx30Vl1VrQ9g4Bb0c4VA8JoN1l0XPjNlXWHLIlFKK1bD/mask3.jpg", "width": 1024, "height": 1024, "prompt": "a photo of TOK", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 17081\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: a photo of <s0><s1>\nimg2img mode\n 0%| | 0/40 [00:00<?, ?it/s]\n 2%|▎ | 1/40 [00:00<00:08, 4.63it/s]\n 5%|▌ | 2/40 [00:00<00:07, 4.81it/s]\n 8%|▊ | 3/40 [00:00<00:07, 4.85it/s]\n 10%|█ | 4/40 [00:00<00:07, 4.87it/s]\n 12%|█▎ | 5/40 [00:01<00:07, 4.88it/s]\n 15%|█▌ | 6/40 [00:01<00:06, 4.89it/s]\n 18%|█▊ | 7/40 [00:01<00:06, 4.90it/s]\n 20%|██ | 8/40 [00:01<00:06, 4.90it/s]\n 22%|██▎ | 9/40 [00:01<00:06, 4.91it/s]\n 25%|██▌ | 10/40 [00:02<00:06, 4.90it/s]\n 28%|██▊ | 11/40 [00:02<00:05, 4.90it/s]\n 30%|███ | 12/40 [00:02<00:05, 4.90it/s]\n 32%|███▎ | 13/40 [00:02<00:05, 4.91it/s]\n 35%|███▌ | 14/40 [00:02<00:05, 4.91it/s]\n 38%|███▊ | 15/40 [00:03<00:05, 4.90it/s]\n 40%|████ | 16/40 [00:03<00:04, 4.90it/s]\n 42%|████▎ | 17/40 [00:03<00:04, 4.90it/s]\n 45%|████▌ | 18/40 [00:03<00:04, 4.90it/s]\n 48%|████▊ | 19/40 [00:03<00:04, 4.90it/s]\n 50%|█████ | 20/40 [00:04<00:04, 4.90it/s]\n 52%|█████▎ | 21/40 [00:04<00:03, 4.91it/s]\n 55%|█████▌ | 22/40 [00:04<00:03, 4.91it/s]\n 57%|█████▊ | 23/40 [00:04<00:03, 4.91it/s]\n 60%|██████ | 24/40 [00:04<00:03, 4.91it/s]\n 62%|██████▎ | 25/40 [00:05<00:03, 4.91it/s]\n 65%|██████▌ | 26/40 [00:05<00:02, 4.91it/s]\n 68%|██████▊ | 27/40 [00:05<00:02, 4.91it/s]\n 70%|███████ | 28/40 [00:05<00:02, 4.91it/s]\n 72%|███████▎ | 29/40 [00:05<00:02, 4.91it/s]\n 75%|███████▌ | 30/40 [00:06<00:02, 4.91it/s]\n 78%|███████▊ | 31/40 [00:06<00:01, 4.91it/s]\n 80%|████████ | 32/40 [00:06<00:01, 4.91it/s]\n 82%|████████▎ | 33/40 [00:06<00:01, 4.91it/s]\n 85%|████████▌ | 34/40 [00:06<00:01, 4.91it/s]\n 88%|████████▊ | 35/40 [00:07<00:01, 4.91it/s]\n 90%|█████████ | 36/40 [00:07<00:00, 4.91it/s]\n 92%|█████████▎| 37/40 [00:07<00:00, 4.91it/s]\n 95%|█████████▌| 38/40 [00:07<00:00, 4.91it/s]\n 98%|█████████▊| 39/40 [00:07<00:00, 4.91it/s]\n100%|██████████| 40/40 [00:08<00:00, 4.91it/s]\n100%|██████████| 40/40 [00:08<00:00, 4.90it/s]", "metrics": { "predict_time": 11.288336, "total_time": 15.728045 }, "output": [ "https://replicate.delivery/pbxt/rIsICe5dJSVaCSkJ3Wkx8HxvMY8EPF7ZgeuUWC7rHXF9ak1SA/out-0.png" ], "started_at": "2024-05-18T11:44:51.412709Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/983cq2ebfnrgj0cfhe2ajfk14w", "cancel": "https://api.replicate.com/v1/predictions/983cq2ebfnrgj0cfhe2ajfk14w/cancel" }, "version": "2bccf2b55b92722cc8f6aa12b49af6da4557607b3ca9d3492a211cbd0697a15c" }
Generated inUsing seed: 17081 Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: a photo of <s0><s1> img2img mode 0%| | 0/40 [00:00<?, ?it/s] 2%|▎ | 1/40 [00:00<00:08, 4.63it/s] 5%|▌ | 2/40 [00:00<00:07, 4.81it/s] 8%|▊ | 3/40 [00:00<00:07, 4.85it/s] 10%|█ | 4/40 [00:00<00:07, 4.87it/s] 12%|█▎ | 5/40 [00:01<00:07, 4.88it/s] 15%|█▌ | 6/40 [00:01<00:06, 4.89it/s] 18%|█▊ | 7/40 [00:01<00:06, 4.90it/s] 20%|██ | 8/40 [00:01<00:06, 4.90it/s] 22%|██▎ | 9/40 [00:01<00:06, 4.91it/s] 25%|██▌ | 10/40 [00:02<00:06, 4.90it/s] 28%|██▊ | 11/40 [00:02<00:05, 4.90it/s] 30%|███ | 12/40 [00:02<00:05, 4.90it/s] 32%|███▎ | 13/40 [00:02<00:05, 4.91it/s] 35%|███▌ | 14/40 [00:02<00:05, 4.91it/s] 38%|███▊ | 15/40 [00:03<00:05, 4.90it/s] 40%|████ | 16/40 [00:03<00:04, 4.90it/s] 42%|████▎ | 17/40 [00:03<00:04, 4.90it/s] 45%|████▌ | 18/40 [00:03<00:04, 4.90it/s] 48%|████▊ | 19/40 [00:03<00:04, 4.90it/s] 50%|█████ | 20/40 [00:04<00:04, 4.90it/s] 52%|█████▎ | 21/40 [00:04<00:03, 4.91it/s] 55%|█████▌ | 22/40 [00:04<00:03, 4.91it/s] 57%|█████▊ | 23/40 [00:04<00:03, 4.91it/s] 60%|██████ | 24/40 [00:04<00:03, 4.91it/s] 62%|██████▎ | 25/40 [00:05<00:03, 4.91it/s] 65%|██████▌ | 26/40 [00:05<00:02, 4.91it/s] 68%|██████▊ | 27/40 [00:05<00:02, 4.91it/s] 70%|███████ | 28/40 [00:05<00:02, 4.91it/s] 72%|███████▎ | 29/40 [00:05<00:02, 4.91it/s] 75%|███████▌ | 30/40 [00:06<00:02, 4.91it/s] 78%|███████▊ | 31/40 [00:06<00:01, 4.91it/s] 80%|████████ | 32/40 [00:06<00:01, 4.91it/s] 82%|████████▎ | 33/40 [00:06<00:01, 4.91it/s] 85%|████████▌ | 34/40 [00:06<00:01, 4.91it/s] 88%|████████▊ | 35/40 [00:07<00:01, 4.91it/s] 90%|█████████ | 36/40 [00:07<00:00, 4.91it/s] 92%|█████████▎| 37/40 [00:07<00:00, 4.91it/s] 95%|█████████▌| 38/40 [00:07<00:00, 4.91it/s] 98%|█████████▊| 39/40 [00:07<00:00, 4.91it/s] 100%|██████████| 40/40 [00:08<00:00, 4.91it/s] 100%|██████████| 40/40 [00:08<00:00, 4.90it/s]
Prediction
raviadi12/diffusion-testing:19e60fe54911cb6338ac8944b88e9d6a2cbdf9ef382eb46008456ff515c3bc2dIDdar6r0wtyhrgp0cfjm1a3nxfkrStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- A photo of TOK
- refine
- no_refiner
- scheduler
- K_EULER
- lora_scale
- 0.6
- num_outputs
- 1
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "image": "https://www.static-src.com/wcsstore/Indraprastha/images/catalog/full//catalog-image/111/MTA-131896587/no-brand_no-brand_full01.jpg", "width": 1024, "height": 1024, "prompt": "A photo of TOK", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run raviadi12/diffusion-testing using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "raviadi12/diffusion-testing:19e60fe54911cb6338ac8944b88e9d6a2cbdf9ef382eb46008456ff515c3bc2d", { input: { image: "https://www.static-src.com/wcsstore/Indraprastha/images/catalog/full//catalog-image/111/MTA-131896587/no-brand_no-brand_full01.jpg", width: 1024, height: 1024, prompt: "A photo of TOK", refine: "no_refiner", scheduler: "K_EULER", lora_scale: 0.6, num_outputs: 1, guidance_scale: 7.5, apply_watermark: true, high_noise_frac: 0.8, negative_prompt: "", 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 replicate
Import the client:import replicate
Run raviadi12/diffusion-testing using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "raviadi12/diffusion-testing:19e60fe54911cb6338ac8944b88e9d6a2cbdf9ef382eb46008456ff515c3bc2d", input={ "image": "https://www.static-src.com/wcsstore/Indraprastha/images/catalog/full//catalog-image/111/MTA-131896587/no-brand_no-brand_full01.jpg", "width": 1024, "height": 1024, "prompt": "A photo of TOK", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": True, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run raviadi12/diffusion-testing 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": "raviadi12/diffusion-testing:19e60fe54911cb6338ac8944b88e9d6a2cbdf9ef382eb46008456ff515c3bc2d", "input": { "image": "https://www.static-src.com/wcsstore/Indraprastha/images/catalog/full//catalog-image/111/MTA-131896587/no-brand_no-brand_full01.jpg", "width": 1024, "height": 1024, "prompt": "A photo of TOK", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-05-20T07:59:46.636065Z", "created_at": "2024-05-20T07:58:47.028000Z", "data_removed": false, "error": null, "id": "dar6r0wtyhrgp0cfjm1a3nxfkr", "input": { "image": "https://www.static-src.com/wcsstore/Indraprastha/images/catalog/full//catalog-image/111/MTA-131896587/no-brand_no-brand_full01.jpg", "width": 1024, "height": 1024, "prompt": "A photo of TOK", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 4283\nEnsuring enough disk space...\nFree disk space: 1712067919872\nDownloading weights: https://replicate.delivery/pbxt/mrZeLybeYTv0TEXegUq8pguDUEcODpgNDruG5G9tVdHriWslA/trained_model.tar\n2024-05-20T07:59:31Z | INFO | [ Initiating ] chunk_size=150M dest=/src/weights-cache/28bacfed3dffc9e6 url=https://replicate.delivery/pbxt/mrZeLybeYTv0TEXegUq8pguDUEcODpgNDruG5G9tVdHriWslA/trained_model.tar\n2024-05-20T07:59:36Z | INFO | [ Complete ] dest=/src/weights-cache/28bacfed3dffc9e6 size=\"186 MB\" total_elapsed=4.735s url=https://replicate.delivery/pbxt/mrZeLybeYTv0TEXegUq8pguDUEcODpgNDruG5G9tVdHriWslA/trained_model.tar\nb''\nDownloaded weights in 4.876891613006592 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: A photo of <s0><s1>\nimg2img mode\n 0%| | 0/40 [00:00<?, ?it/s]\n 2%|▎ | 1/40 [00:00<00:07, 5.16it/s]\n 5%|▌ | 2/40 [00:00<00:06, 5.45it/s]\n 8%|▊ | 3/40 [00:00<00:06, 5.55it/s]\n 10%|█ | 4/40 [00:00<00:06, 5.59it/s]\n 12%|█▎ | 5/40 [00:00<00:06, 5.61it/s]\n 15%|█▌ | 6/40 [00:01<00:06, 5.62it/s]\n 18%|█▊ | 7/40 [00:01<00:05, 5.64it/s]\n 20%|██ | 8/40 [00:01<00:05, 5.65it/s]\n 22%|██▎ | 9/40 [00:01<00:05, 5.65it/s]\n 25%|██▌ | 10/40 [00:01<00:05, 5.65it/s]\n 28%|██▊ | 11/40 [00:01<00:05, 5.64it/s]\n 30%|███ | 12/40 [00:02<00:04, 5.63it/s]\n 32%|███▎ | 13/40 [00:02<00:04, 5.64it/s]\n 35%|███▌ | 14/40 [00:02<00:04, 5.64it/s]\n 38%|███▊ | 15/40 [00:02<00:04, 5.64it/s]\n 40%|████ | 16/40 [00:02<00:04, 5.64it/s]\n 42%|████▎ | 17/40 [00:03<00:04, 5.64it/s]\n 45%|████▌ | 18/40 [00:03<00:03, 5.63it/s]\n 48%|████▊ | 19/40 [00:03<00:03, 5.63it/s]\n 50%|█████ | 20/40 [00:03<00:03, 5.62it/s]\n 52%|█████▎ | 21/40 [00:03<00:03, 5.62it/s]\n 55%|█████▌ | 22/40 [00:03<00:03, 5.63it/s]\n 57%|█████▊ | 23/40 [00:04<00:03, 5.64it/s]\n 60%|██████ | 24/40 [00:04<00:02, 5.63it/s]\n 62%|██████▎ | 25/40 [00:04<00:02, 5.64it/s]\n 65%|██████▌ | 26/40 [00:04<00:02, 5.63it/s]\n 68%|██████▊ | 27/40 [00:04<00:02, 5.62it/s]\n 70%|███████ | 28/40 [00:04<00:02, 5.62it/s]\n 72%|███████▎ | 29/40 [00:05<00:01, 5.63it/s]\n 75%|███████▌ | 30/40 [00:05<00:01, 5.63it/s]\n 78%|███████▊ | 31/40 [00:05<00:01, 5.63it/s]\n 80%|████████ | 32/40 [00:05<00:01, 5.63it/s]\n 82%|████████▎ | 33/40 [00:05<00:01, 5.63it/s]\n 85%|████████▌ | 34/40 [00:06<00:01, 5.63it/s]\n 88%|████████▊ | 35/40 [00:06<00:00, 5.63it/s]\n 90%|█████████ | 36/40 [00:06<00:00, 5.62it/s]\n 92%|█████████▎| 37/40 [00:06<00:00, 5.62it/s]\n 95%|█████████▌| 38/40 [00:06<00:00, 5.61it/s]\n 98%|█████████▊| 39/40 [00:06<00:00, 5.62it/s]\n100%|██████████| 40/40 [00:07<00:00, 5.63it/s]\n100%|██████████| 40/40 [00:07<00:00, 5.62it/s]", "metrics": { "predict_time": 15.914269, "total_time": 59.608065 }, "output": [ "https://replicate.delivery/pbxt/eenGm8WTAatVYESUWzktrEFABBDnecEx8xtUAVqGLehFPtYLB/out-0.png" ], "started_at": "2024-05-20T07:59:30.721796Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/dar6r0wtyhrgp0cfjm1a3nxfkr", "cancel": "https://api.replicate.com/v1/predictions/dar6r0wtyhrgp0cfjm1a3nxfkr/cancel" }, "version": "19e60fe54911cb6338ac8944b88e9d6a2cbdf9ef382eb46008456ff515c3bc2d" }
Generated inUsing seed: 4283 Ensuring enough disk space... Free disk space: 1712067919872 Downloading weights: https://replicate.delivery/pbxt/mrZeLybeYTv0TEXegUq8pguDUEcODpgNDruG5G9tVdHriWslA/trained_model.tar 2024-05-20T07:59:31Z | INFO | [ Initiating ] chunk_size=150M dest=/src/weights-cache/28bacfed3dffc9e6 url=https://replicate.delivery/pbxt/mrZeLybeYTv0TEXegUq8pguDUEcODpgNDruG5G9tVdHriWslA/trained_model.tar 2024-05-20T07:59:36Z | INFO | [ Complete ] dest=/src/weights-cache/28bacfed3dffc9e6 size="186 MB" total_elapsed=4.735s url=https://replicate.delivery/pbxt/mrZeLybeYTv0TEXegUq8pguDUEcODpgNDruG5G9tVdHriWslA/trained_model.tar b'' Downloaded weights in 4.876891613006592 seconds Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: A photo of <s0><s1> img2img mode 0%| | 0/40 [00:00<?, ?it/s] 2%|▎ | 1/40 [00:00<00:07, 5.16it/s] 5%|▌ | 2/40 [00:00<00:06, 5.45it/s] 8%|▊ | 3/40 [00:00<00:06, 5.55it/s] 10%|█ | 4/40 [00:00<00:06, 5.59it/s] 12%|█▎ | 5/40 [00:00<00:06, 5.61it/s] 15%|█▌ | 6/40 [00:01<00:06, 5.62it/s] 18%|█▊ | 7/40 [00:01<00:05, 5.64it/s] 20%|██ | 8/40 [00:01<00:05, 5.65it/s] 22%|██▎ | 9/40 [00:01<00:05, 5.65it/s] 25%|██▌ | 10/40 [00:01<00:05, 5.65it/s] 28%|██▊ | 11/40 [00:01<00:05, 5.64it/s] 30%|███ | 12/40 [00:02<00:04, 5.63it/s] 32%|███▎ | 13/40 [00:02<00:04, 5.64it/s] 35%|███▌ | 14/40 [00:02<00:04, 5.64it/s] 38%|███▊ | 15/40 [00:02<00:04, 5.64it/s] 40%|████ | 16/40 [00:02<00:04, 5.64it/s] 42%|████▎ | 17/40 [00:03<00:04, 5.64it/s] 45%|████▌ | 18/40 [00:03<00:03, 5.63it/s] 48%|████▊ | 19/40 [00:03<00:03, 5.63it/s] 50%|█████ | 20/40 [00:03<00:03, 5.62it/s] 52%|█████▎ | 21/40 [00:03<00:03, 5.62it/s] 55%|█████▌ | 22/40 [00:03<00:03, 5.63it/s] 57%|█████▊ | 23/40 [00:04<00:03, 5.64it/s] 60%|██████ | 24/40 [00:04<00:02, 5.63it/s] 62%|██████▎ | 25/40 [00:04<00:02, 5.64it/s] 65%|██████▌ | 26/40 [00:04<00:02, 5.63it/s] 68%|██████▊ | 27/40 [00:04<00:02, 5.62it/s] 70%|███████ | 28/40 [00:04<00:02, 5.62it/s] 72%|███████▎ | 29/40 [00:05<00:01, 5.63it/s] 75%|███████▌ | 30/40 [00:05<00:01, 5.63it/s] 78%|███████▊ | 31/40 [00:05<00:01, 5.63it/s] 80%|████████ | 32/40 [00:05<00:01, 5.63it/s] 82%|████████▎ | 33/40 [00:05<00:01, 5.63it/s] 85%|████████▌ | 34/40 [00:06<00:01, 5.63it/s] 88%|████████▊ | 35/40 [00:06<00:00, 5.63it/s] 90%|█████████ | 36/40 [00:06<00:00, 5.62it/s] 92%|█████████▎| 37/40 [00:06<00:00, 5.62it/s] 95%|█████████▌| 38/40 [00:06<00:00, 5.61it/s] 98%|█████████▊| 39/40 [00:06<00:00, 5.62it/s] 100%|██████████| 40/40 [00:07<00:00, 5.63it/s] 100%|██████████| 40/40 [00:07<00:00, 5.62it/s]
Prediction
raviadi12/diffusion-testing:19e60fe54911cb6338ac8944b88e9d6a2cbdf9ef382eb46008456ff515c3bc2dIDch6cjyazqhrgp0cfjm596jqqjrStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- a photo of TOK
- refine
- no_refiner
- scheduler
- K_EULER
- lora_scale
- 0.6
- num_outputs
- 1
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "image": "https://replicate.delivery/pbxt/Kx0eCnBmIjloqcZfzyxCkQ2kcnyBqXKCYeaBAa9gOQ1qaaTM/mask3.jpg", "width": 1024, "height": 1024, "prompt": "a photo of TOK", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run raviadi12/diffusion-testing using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "raviadi12/diffusion-testing:19e60fe54911cb6338ac8944b88e9d6a2cbdf9ef382eb46008456ff515c3bc2d", { input: { image: "https://replicate.delivery/pbxt/Kx0eCnBmIjloqcZfzyxCkQ2kcnyBqXKCYeaBAa9gOQ1qaaTM/mask3.jpg", width: 1024, height: 1024, prompt: "a photo of TOK", refine: "no_refiner", scheduler: "K_EULER", lora_scale: 0.6, num_outputs: 1, guidance_scale: 7.5, apply_watermark: true, high_noise_frac: 0.8, negative_prompt: "", 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 replicate
Import the client:import replicate
Run raviadi12/diffusion-testing using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "raviadi12/diffusion-testing:19e60fe54911cb6338ac8944b88e9d6a2cbdf9ef382eb46008456ff515c3bc2d", input={ "image": "https://replicate.delivery/pbxt/Kx0eCnBmIjloqcZfzyxCkQ2kcnyBqXKCYeaBAa9gOQ1qaaTM/mask3.jpg", "width": 1024, "height": 1024, "prompt": "a photo of TOK", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": True, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run raviadi12/diffusion-testing 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": "raviadi12/diffusion-testing:19e60fe54911cb6338ac8944b88e9d6a2cbdf9ef382eb46008456ff515c3bc2d", "input": { "image": "https://replicate.delivery/pbxt/Kx0eCnBmIjloqcZfzyxCkQ2kcnyBqXKCYeaBAa9gOQ1qaaTM/mask3.jpg", "width": 1024, "height": 1024, "prompt": "a photo of TOK", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-05-20T08:07:27.441803Z", "created_at": "2024-05-20T08:07:16.156000Z", "data_removed": false, "error": null, "id": "ch6cjyazqhrgp0cfjm596jqqjr", "input": { "image": "https://replicate.delivery/pbxt/Kx0eCnBmIjloqcZfzyxCkQ2kcnyBqXKCYeaBAa9gOQ1qaaTM/mask3.jpg", "width": 1024, "height": 1024, "prompt": "a photo of TOK", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 57154\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: a photo of <s0><s1>\nimg2img mode\n 0%| | 0/40 [00:00<?, ?it/s]\n 2%|▎ | 1/40 [00:00<00:08, 4.63it/s]\n 5%|▌ | 2/40 [00:00<00:07, 4.83it/s]\n 8%|▊ | 3/40 [00:00<00:07, 4.89it/s]\n 10%|█ | 4/40 [00:00<00:07, 4.92it/s]\n 12%|█▎ | 5/40 [00:01<00:07, 4.93it/s]\n 15%|█▌ | 6/40 [00:01<00:06, 4.94it/s]\n 18%|█▊ | 7/40 [00:01<00:06, 4.94it/s]\n 20%|██ | 8/40 [00:01<00:06, 4.94it/s]\n 22%|██▎ | 9/40 [00:01<00:06, 4.94it/s]\n 25%|██▌ | 10/40 [00:02<00:06, 4.95it/s]\n 28%|██▊ | 11/40 [00:02<00:05, 4.95it/s]\n 30%|███ | 12/40 [00:02<00:05, 4.95it/s]\n 32%|███▎ | 13/40 [00:02<00:05, 4.95it/s]\n 35%|███▌ | 14/40 [00:02<00:05, 4.95it/s]\n 38%|███▊ | 15/40 [00:03<00:05, 4.95it/s]\n 40%|████ | 16/40 [00:03<00:04, 4.95it/s]\n 42%|████▎ | 17/40 [00:03<00:04, 4.95it/s]\n 45%|████▌ | 18/40 [00:03<00:04, 4.95it/s]\n 48%|████▊ | 19/40 [00:03<00:04, 4.95it/s]\n 50%|█████ | 20/40 [00:04<00:04, 4.95it/s]\n 52%|█████▎ | 21/40 [00:04<00:03, 4.94it/s]\n 55%|█████▌ | 22/40 [00:04<00:03, 4.94it/s]\n 57%|█████▊ | 23/40 [00:04<00:03, 4.94it/s]\n 60%|██████ | 24/40 [00:04<00:03, 4.94it/s]\n 62%|██████▎ | 25/40 [00:05<00:03, 4.93it/s]\n 65%|██████▌ | 26/40 [00:05<00:02, 4.93it/s]\n 68%|██████▊ | 27/40 [00:05<00:02, 4.93it/s]\n 70%|███████ | 28/40 [00:05<00:02, 4.94it/s]\n 72%|███████▎ | 29/40 [00:05<00:02, 4.93it/s]\n 75%|███████▌ | 30/40 [00:06<00:02, 4.93it/s]\n 78%|███████▊ | 31/40 [00:06<00:01, 4.93it/s]\n 80%|████████ | 32/40 [00:06<00:01, 4.93it/s]\n 82%|████████▎ | 33/40 [00:06<00:01, 4.93it/s]\n 85%|████████▌ | 34/40 [00:06<00:01, 4.93it/s]\n 88%|████████▊ | 35/40 [00:07<00:01, 4.93it/s]\n 90%|█████████ | 36/40 [00:07<00:00, 4.93it/s]\n 92%|█████████▎| 37/40 [00:07<00:00, 4.92it/s]\n 95%|█████████▌| 38/40 [00:07<00:00, 4.93it/s]\n 98%|█████████▊| 39/40 [00:07<00:00, 4.93it/s]\n100%|██████████| 40/40 [00:08<00:00, 4.93it/s]\n100%|██████████| 40/40 [00:08<00:00, 4.93it/s]", "metrics": { "predict_time": 10.1558, "total_time": 11.285803 }, "output": [ "https://replicate.delivery/pbxt/lqabNCMwnf3er0Yc4ZJWqWeywr5zikGSm7813MKxUVY91WslA/out-0.png" ], "started_at": "2024-05-20T08:07:17.286003Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/ch6cjyazqhrgp0cfjm596jqqjr", "cancel": "https://api.replicate.com/v1/predictions/ch6cjyazqhrgp0cfjm596jqqjr/cancel" }, "version": "19e60fe54911cb6338ac8944b88e9d6a2cbdf9ef382eb46008456ff515c3bc2d" }
Generated inUsing seed: 57154 Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: a photo of <s0><s1> img2img mode 0%| | 0/40 [00:00<?, ?it/s] 2%|▎ | 1/40 [00:00<00:08, 4.63it/s] 5%|▌ | 2/40 [00:00<00:07, 4.83it/s] 8%|▊ | 3/40 [00:00<00:07, 4.89it/s] 10%|█ | 4/40 [00:00<00:07, 4.92it/s] 12%|█▎ | 5/40 [00:01<00:07, 4.93it/s] 15%|█▌ | 6/40 [00:01<00:06, 4.94it/s] 18%|█▊ | 7/40 [00:01<00:06, 4.94it/s] 20%|██ | 8/40 [00:01<00:06, 4.94it/s] 22%|██▎ | 9/40 [00:01<00:06, 4.94it/s] 25%|██▌ | 10/40 [00:02<00:06, 4.95it/s] 28%|██▊ | 11/40 [00:02<00:05, 4.95it/s] 30%|███ | 12/40 [00:02<00:05, 4.95it/s] 32%|███▎ | 13/40 [00:02<00:05, 4.95it/s] 35%|███▌ | 14/40 [00:02<00:05, 4.95it/s] 38%|███▊ | 15/40 [00:03<00:05, 4.95it/s] 40%|████ | 16/40 [00:03<00:04, 4.95it/s] 42%|████▎ | 17/40 [00:03<00:04, 4.95it/s] 45%|████▌ | 18/40 [00:03<00:04, 4.95it/s] 48%|████▊ | 19/40 [00:03<00:04, 4.95it/s] 50%|█████ | 20/40 [00:04<00:04, 4.95it/s] 52%|█████▎ | 21/40 [00:04<00:03, 4.94it/s] 55%|█████▌ | 22/40 [00:04<00:03, 4.94it/s] 57%|█████▊ | 23/40 [00:04<00:03, 4.94it/s] 60%|██████ | 24/40 [00:04<00:03, 4.94it/s] 62%|██████▎ | 25/40 [00:05<00:03, 4.93it/s] 65%|██████▌ | 26/40 [00:05<00:02, 4.93it/s] 68%|██████▊ | 27/40 [00:05<00:02, 4.93it/s] 70%|███████ | 28/40 [00:05<00:02, 4.94it/s] 72%|███████▎ | 29/40 [00:05<00:02, 4.93it/s] 75%|███████▌ | 30/40 [00:06<00:02, 4.93it/s] 78%|███████▊ | 31/40 [00:06<00:01, 4.93it/s] 80%|████████ | 32/40 [00:06<00:01, 4.93it/s] 82%|████████▎ | 33/40 [00:06<00:01, 4.93it/s] 85%|████████▌ | 34/40 [00:06<00:01, 4.93it/s] 88%|████████▊ | 35/40 [00:07<00:01, 4.93it/s] 90%|█████████ | 36/40 [00:07<00:00, 4.93it/s] 92%|█████████▎| 37/40 [00:07<00:00, 4.92it/s] 95%|█████████▌| 38/40 [00:07<00:00, 4.93it/s] 98%|█████████▊| 39/40 [00:07<00:00, 4.93it/s] 100%|██████████| 40/40 [00:08<00:00, 4.93it/s] 100%|██████████| 40/40 [00:08<00:00, 4.93it/s]
Want to make some of these yourself?
Run this model