Prediction
justswim/em:ab2d9e1e870b835b3a61b2dca3c631005a73ce1e54eb4e79e7e60ba5289d99adModelID3aflxslbnjulfrhua3j2faapfeStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- A sketch digital image of an astronaut in the style of TOK
- refine
- no_refiner
- scheduler
- K_EULER
- lora_scale
- 0.6
- num_outputs
- 4
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- background
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 1024, "height": 1024, "prompt": "A sketch digital image of an astronaut in the style of TOK", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "background", "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 justswim/em using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "justswim/em:ab2d9e1e870b835b3a61b2dca3c631005a73ce1e54eb4e79e7e60ba5289d99ad", { input: { width: 1024, height: 1024, prompt: "A sketch digital image of an astronaut in the style of TOK", refine: "no_refiner", scheduler: "K_EULER", lora_scale: 0.6, num_outputs: 4, guidance_scale: 7.5, apply_watermark: true, high_noise_frac: 0.8, negative_prompt: "background", 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 justswim/em using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "justswim/em:ab2d9e1e870b835b3a61b2dca3c631005a73ce1e54eb4e79e7e60ba5289d99ad", input={ "width": 1024, "height": 1024, "prompt": "A sketch digital image of an astronaut in the style of TOK", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": True, "high_noise_frac": 0.8, "negative_prompt": "background", "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 justswim/em 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": "justswim/em:ab2d9e1e870b835b3a61b2dca3c631005a73ce1e54eb4e79e7e60ba5289d99ad", "input": { "width": 1024, "height": 1024, "prompt": "A sketch digital image of an astronaut in the style of TOK", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "background", "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/justswim/em@sha256:ab2d9e1e870b835b3a61b2dca3c631005a73ce1e54eb4e79e7e60ba5289d99ad \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="A sketch digital image of an astronaut in the style of TOK"' \ -i 'refine="no_refiner"' \ -i 'scheduler="K_EULER"' \ -i 'lora_scale=0.6' \ -i 'num_outputs=4' \ -i 'guidance_scale=7.5' \ -i 'apply_watermark=true' \ -i 'high_noise_frac=0.8' \ -i 'negative_prompt="background"' \ -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/justswim/em@sha256:ab2d9e1e870b835b3a61b2dca3c631005a73ce1e54eb4e79e7e60ba5289d99adcurl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "A sketch digital image of an astronaut in the style of TOK", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "background", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-12-01T00:38:58.010027Z", "created_at": "2023-12-01T00:37:17.696862Z", "data_removed": false, "error": null, "id": "3aflxslbnjulfrhua3j2faapfe", "input": { "width": 1024, "height": 1024, "prompt": "A sketch digital image of an astronaut in the style of TOK", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "background", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 4357\nEnsuring enough disk space...\nFree disk space: 1615015243776\nDownloading weights: https://replicate.delivery/pbxt/ebsSpWwudgQfF076C9KBwUfqC6ZGAlem7DfqBeUM9U0dUcbfIA/trained_model.tar\nb'Downloaded 186 MB bytes in 4.701s (40 MB/s)\\nExtracted 186 MB in 0.075s (2.5 GB/s)\\n'\nDownloaded weights in 5.211457967758179 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: A sketch digital image of an astronaut in the style of <s0><s1>\ntxt2img mode\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:01<00:52, 1.06s/it]\n 4%|▍ | 2/50 [00:02<00:51, 1.06s/it]\n 6%|▌ | 3/50 [00:03<00:50, 1.06s/it]\n 8%|▊ | 4/50 [00:04<00:49, 1.07s/it]\n 10%|█ | 5/50 [00:05<00:47, 1.06s/it]\n 12%|█▏ | 6/50 [00:06<00:46, 1.06s/it]\n 14%|█▍ | 7/50 [00:07<00:45, 1.07s/it]\n 16%|█▌ | 8/50 [00:08<00:44, 1.07s/it]\n 18%|█▊ | 9/50 [00:09<00:43, 1.07s/it]\n 20%|██ | 10/50 [00:10<00:42, 1.07s/it]\n 22%|██▏ | 11/50 [00:11<00:41, 1.07s/it]\n 24%|██▍ | 12/50 [00:12<00:40, 1.07s/it]\n 26%|██▌ | 13/50 [00:13<00:39, 1.07s/it]\n 28%|██▊ | 14/50 [00:14<00:38, 1.07s/it]\n 30%|███ | 15/50 [00:15<00:37, 1.07s/it]\n 32%|███▏ | 16/50 [00:17<00:36, 1.07s/it]\n 34%|███▍ | 17/50 [00:18<00:35, 1.07s/it]\n 36%|███▌ | 18/50 [00:19<00:34, 1.07s/it]\n 38%|███▊ | 19/50 [00:20<00:33, 1.07s/it]\n 40%|████ | 20/50 [00:21<00:32, 1.07s/it]\n 42%|████▏ | 21/50 [00:22<00:30, 1.07s/it]\n 44%|████▍ | 22/50 [00:23<00:29, 1.07s/it]\n 46%|████▌ | 23/50 [00:24<00:28, 1.07s/it]\n 48%|████▊ | 24/50 [00:25<00:27, 1.07s/it]\n 50%|█████ | 25/50 [00:26<00:26, 1.07s/it]\n 52%|█████▏ | 26/50 [00:27<00:25, 1.07s/it]\n 54%|█████▍ | 27/50 [00:28<00:24, 1.07s/it]\n 56%|█████▌ | 28/50 [00:29<00:23, 1.07s/it]\n 58%|█████▊ | 29/50 [00:30<00:22, 1.07s/it]\n 60%|██████ | 30/50 [00:32<00:21, 1.07s/it]\n 62%|██████▏ | 31/50 [00:33<00:20, 1.07s/it]\n 64%|██████▍ | 32/50 [00:34<00:19, 1.07s/it]\n 66%|██████▌ | 33/50 [00:35<00:18, 1.07s/it]\n 68%|██████▊ | 34/50 [00:36<00:17, 1.07s/it]\n 70%|███████ | 35/50 [00:37<00:16, 1.07s/it]\n 72%|███████▏ | 36/50 [00:38<00:14, 1.07s/it]\n 74%|███████▍ | 37/50 [00:39<00:13, 1.07s/it]\n 76%|███████▌ | 38/50 [00:40<00:12, 1.07s/it]\n 78%|███████▊ | 39/50 [00:41<00:11, 1.07s/it]\n 80%|████████ | 40/50 [00:42<00:10, 1.07s/it]\n 82%|████████▏ | 41/50 [00:43<00:09, 1.07s/it]\n 84%|████████▍ | 42/50 [00:44<00:08, 1.07s/it]\n 86%|████████▌ | 43/50 [00:45<00:07, 1.07s/it]\n 88%|████████▊ | 44/50 [00:46<00:06, 1.07s/it]\n 90%|█████████ | 45/50 [00:48<00:05, 1.07s/it]\n 92%|█████████▏| 46/50 [00:49<00:04, 1.07s/it]\n 94%|█████████▍| 47/50 [00:50<00:03, 1.07s/it]\n 96%|█████████▌| 48/50 [00:51<00:02, 1.07s/it]\n 98%|█████████▊| 49/50 [00:52<00:01, 1.07s/it]\n100%|██████████| 50/50 [00:53<00:00, 1.07s/it]\n100%|██████████| 50/50 [00:53<00:00, 1.07s/it]", "metrics": { "predict_time": 65.555803, "total_time": 100.313165 }, "output": [ "https://replicate.delivery/pbxt/9K8bsC3eMnxFFacghgEMJrNvUE27E3rRXxsVyGINpn4P62eRA/out-0.png", "https://replicate.delivery/pbxt/vw3TMMKrdfTUEiCwgjcRY2WDJhLnXWkCYFSgoOSuLaLQ62eRA/out-1.png", "https://replicate.delivery/pbxt/8lzfY1IOZ5T4NqvRcGzgO5hRLXb9WBFw1nbkegqRaJkh0t9RA/out-2.png", "https://replicate.delivery/pbxt/vSifVbNkQZ3aaq6ZedfHk7HCVEFAK1WlvL5Kjfv8VTaES32HB/out-3.png" ], "started_at": "2023-12-01T00:37:52.454224Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/3aflxslbnjulfrhua3j2faapfe", "cancel": "https://api.replicate.com/v1/predictions/3aflxslbnjulfrhua3j2faapfe/cancel" }, "version": "ab2d9e1e870b835b3a61b2dca3c631005a73ce1e54eb4e79e7e60ba5289d99ad" }Generated inUsing seed: 4357 Ensuring enough disk space... Free disk space: 1615015243776 Downloading weights: https://replicate.delivery/pbxt/ebsSpWwudgQfF076C9KBwUfqC6ZGAlem7DfqBeUM9U0dUcbfIA/trained_model.tar b'Downloaded 186 MB bytes in 4.701s (40 MB/s)\nExtracted 186 MB in 0.075s (2.5 GB/s)\n' Downloaded weights in 5.211457967758179 seconds Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: A sketch digital image of an astronaut in the style of <s0><s1> txt2img mode 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:01<00:52, 1.06s/it] 4%|▍ | 2/50 [00:02<00:51, 1.06s/it] 6%|▌ | 3/50 [00:03<00:50, 1.06s/it] 8%|▊ | 4/50 [00:04<00:49, 1.07s/it] 10%|█ | 5/50 [00:05<00:47, 1.06s/it] 12%|█▏ | 6/50 [00:06<00:46, 1.06s/it] 14%|█▍ | 7/50 [00:07<00:45, 1.07s/it] 16%|█▌ | 8/50 [00:08<00:44, 1.07s/it] 18%|█▊ | 9/50 [00:09<00:43, 1.07s/it] 20%|██ | 10/50 [00:10<00:42, 1.07s/it] 22%|██▏ | 11/50 [00:11<00:41, 1.07s/it] 24%|██▍ | 12/50 [00:12<00:40, 1.07s/it] 26%|██▌ | 13/50 [00:13<00:39, 1.07s/it] 28%|██▊ | 14/50 [00:14<00:38, 1.07s/it] 30%|███ | 15/50 [00:15<00:37, 1.07s/it] 32%|███▏ | 16/50 [00:17<00:36, 1.07s/it] 34%|███▍ | 17/50 [00:18<00:35, 1.07s/it] 36%|███▌ | 18/50 [00:19<00:34, 1.07s/it] 38%|███▊ | 19/50 [00:20<00:33, 1.07s/it] 40%|████ | 20/50 [00:21<00:32, 1.07s/it] 42%|████▏ | 21/50 [00:22<00:30, 1.07s/it] 44%|████▍ | 22/50 [00:23<00:29, 1.07s/it] 46%|████▌ | 23/50 [00:24<00:28, 1.07s/it] 48%|████▊ | 24/50 [00:25<00:27, 1.07s/it] 50%|█████ | 25/50 [00:26<00:26, 1.07s/it] 52%|█████▏ | 26/50 [00:27<00:25, 1.07s/it] 54%|█████▍ | 27/50 [00:28<00:24, 1.07s/it] 56%|█████▌ | 28/50 [00:29<00:23, 1.07s/it] 58%|█████▊ | 29/50 [00:30<00:22, 1.07s/it] 60%|██████ | 30/50 [00:32<00:21, 1.07s/it] 62%|██████▏ | 31/50 [00:33<00:20, 1.07s/it] 64%|██████▍ | 32/50 [00:34<00:19, 1.07s/it] 66%|██████▌ | 33/50 [00:35<00:18, 1.07s/it] 68%|██████▊ | 34/50 [00:36<00:17, 1.07s/it] 70%|███████ | 35/50 [00:37<00:16, 1.07s/it] 72%|███████▏ | 36/50 [00:38<00:14, 1.07s/it] 74%|███████▍ | 37/50 [00:39<00:13, 1.07s/it] 76%|███████▌ | 38/50 [00:40<00:12, 1.07s/it] 78%|███████▊ | 39/50 [00:41<00:11, 1.07s/it] 80%|████████ | 40/50 [00:42<00:10, 1.07s/it] 82%|████████▏ | 41/50 [00:43<00:09, 1.07s/it] 84%|████████▍ | 42/50 [00:44<00:08, 1.07s/it] 86%|████████▌ | 43/50 [00:45<00:07, 1.07s/it] 88%|████████▊ | 44/50 [00:46<00:06, 1.07s/it] 90%|█████████ | 45/50 [00:48<00:05, 1.07s/it] 92%|█████████▏| 46/50 [00:49<00:04, 1.07s/it] 94%|█████████▍| 47/50 [00:50<00:03, 1.07s/it] 96%|█████████▌| 48/50 [00:51<00:02, 1.07s/it] 98%|█████████▊| 49/50 [00:52<00:01, 1.07s/it] 100%|██████████| 50/50 [00:53<00:00, 1.07s/it] 100%|██████████| 50/50 [00:53<00:00, 1.07s/it]Prediction
justswim/em:ab2d9e1e870b835b3a61b2dca3c631005a73ce1e54eb4e79e7e60ba5289d99adModelIDyasvqklb4ydacjklnrqfn2qleuStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- a girl in a hoodie in the style of TOK
- refine
- no_refiner
- scheduler
- K_EULER
- lora_scale
- 0.6
- num_outputs
- 4
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- background
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 1024, "height": 1024, "prompt": "a girl in a hoodie in the style of TOK", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "background", "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 justswim/em using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "justswim/em:ab2d9e1e870b835b3a61b2dca3c631005a73ce1e54eb4e79e7e60ba5289d99ad", { input: { width: 1024, height: 1024, prompt: "a girl in a hoodie in the style of TOK", refine: "no_refiner", scheduler: "K_EULER", lora_scale: 0.6, num_outputs: 4, guidance_scale: 7.5, apply_watermark: true, high_noise_frac: 0.8, negative_prompt: "background", 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 justswim/em using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "justswim/em:ab2d9e1e870b835b3a61b2dca3c631005a73ce1e54eb4e79e7e60ba5289d99ad", input={ "width": 1024, "height": 1024, "prompt": "a girl in a hoodie in the style of TOK", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": True, "high_noise_frac": 0.8, "negative_prompt": "background", "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 justswim/em 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": "justswim/em:ab2d9e1e870b835b3a61b2dca3c631005a73ce1e54eb4e79e7e60ba5289d99ad", "input": { "width": 1024, "height": 1024, "prompt": "a girl in a hoodie in the style of TOK", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "background", "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/justswim/em@sha256:ab2d9e1e870b835b3a61b2dca3c631005a73ce1e54eb4e79e7e60ba5289d99ad \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="a girl in a hoodie in the style of TOK"' \ -i 'refine="no_refiner"' \ -i 'scheduler="K_EULER"' \ -i 'lora_scale=0.6' \ -i 'num_outputs=4' \ -i 'guidance_scale=7.5' \ -i 'apply_watermark=true' \ -i 'high_noise_frac=0.8' \ -i 'negative_prompt="background"' \ -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/justswim/em@sha256:ab2d9e1e870b835b3a61b2dca3c631005a73ce1e54eb4e79e7e60ba5289d99adcurl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "a girl in a hoodie in the style of TOK", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "background", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-12-01T00:40:32.054464Z", "created_at": "2023-12-01T00:39:32.312069Z", "data_removed": false, "error": null, "id": "yasvqklb4ydacjklnrqfn2qleu", "input": { "width": 1024, "height": 1024, "prompt": "a girl in a hoodie in the style of TOK", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "background", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 55125\nskipping loading .. weights already loaded\nPrompt: a girl in a hoodie in the style of <s0><s1>\ntxt2img mode\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:01<00:51, 1.06s/it]\n 4%|▍ | 2/50 [00:02<00:50, 1.06s/it]\n 6%|▌ | 3/50 [00:03<00:49, 1.06s/it]\n 8%|▊ | 4/50 [00:04<00:48, 1.06s/it]\n 10%|█ | 5/50 [00:05<00:47, 1.06s/it]\n 12%|█▏ | 6/50 [00:06<00:46, 1.06s/it]\n 14%|█▍ | 7/50 [00:07<00:45, 1.06s/it]\n 16%|█▌ | 8/50 [00:08<00:44, 1.06s/it]\n 18%|█▊ | 9/50 [00:09<00:43, 1.07s/it]\n 20%|██ | 10/50 [00:10<00:42, 1.06s/it]\n 22%|██▏ | 11/50 [00:11<00:41, 1.07s/it]\n 24%|██▍ | 12/50 [00:12<00:40, 1.07s/it]\n 26%|██▌ | 13/50 [00:13<00:39, 1.07s/it]\n 28%|██▊ | 14/50 [00:14<00:38, 1.07s/it]\n 30%|███ | 15/50 [00:15<00:37, 1.07s/it]\n 32%|███▏ | 16/50 [00:17<00:36, 1.07s/it]\n 34%|███▍ | 17/50 [00:18<00:35, 1.07s/it]\n 36%|███▌ | 18/50 [00:19<00:34, 1.07s/it]\n 38%|███▊ | 19/50 [00:20<00:33, 1.07s/it]\n 40%|████ | 20/50 [00:21<00:31, 1.07s/it]\n 42%|████▏ | 21/50 [00:22<00:30, 1.07s/it]\n 44%|████▍ | 22/50 [00:23<00:29, 1.07s/it]\n 46%|████▌ | 23/50 [00:24<00:28, 1.07s/it]\n 48%|████▊ | 24/50 [00:25<00:27, 1.07s/it]\n 50%|█████ | 25/50 [00:26<00:26, 1.07s/it]\n 52%|█████▏ | 26/50 [00:27<00:25, 1.07s/it]\n 54%|█████▍ | 27/50 [00:28<00:24, 1.07s/it]\n 56%|█████▌ | 28/50 [00:29<00:23, 1.07s/it]\n 58%|█████▊ | 29/50 [00:30<00:22, 1.07s/it]\n 60%|██████ | 30/50 [00:31<00:21, 1.07s/it]\n 62%|██████▏ | 31/50 [00:33<00:20, 1.07s/it]\n 64%|██████▍ | 32/50 [00:34<00:19, 1.07s/it]\n 66%|██████▌ | 33/50 [00:35<00:18, 1.07s/it]\n 68%|██████▊ | 34/50 [00:36<00:17, 1.07s/it]\n 70%|███████ | 35/50 [00:37<00:16, 1.07s/it]\n 72%|███████▏ | 36/50 [00:38<00:14, 1.07s/it]\n 74%|███████▍ | 37/50 [00:39<00:13, 1.07s/it]\n 76%|███████▌ | 38/50 [00:40<00:12, 1.07s/it]\n 78%|███████▊ | 39/50 [00:41<00:11, 1.07s/it]\n 80%|████████ | 40/50 [00:42<00:10, 1.07s/it]\n 82%|████████▏ | 41/50 [00:43<00:09, 1.07s/it]\n 84%|████████▍ | 42/50 [00:44<00:08, 1.07s/it]\n 86%|████████▌ | 43/50 [00:45<00:07, 1.07s/it]\n 88%|████████▊ | 44/50 [00:46<00:06, 1.07s/it]\n 90%|█████████ | 45/50 [00:48<00:05, 1.07s/it]\n 92%|█████████▏| 46/50 [00:49<00:04, 1.07s/it]\n 94%|█████████▍| 47/50 [00:50<00:03, 1.07s/it]\n 96%|█████████▌| 48/50 [00:51<00:02, 1.07s/it]\n 98%|█████████▊| 49/50 [00:52<00:01, 1.07s/it]\n100%|██████████| 50/50 [00:53<00:00, 1.07s/it]\n100%|██████████| 50/50 [00:53<00:00, 1.07s/it]\nPotential NSFW content was detected in one or more images. A black image will be returned instead. Try again with a different prompt and/or seed.\nNSFW content detected in image 0\nNSFW content detected in image 2", "metrics": { "predict_time": 58.502549, "total_time": 59.742395 }, "output": [ "https://replicate.delivery/pbxt/yiONvReKEZUcDCNfahNtfodIhjec0AsZYWyrdrenqbsxvutPC/out-1.png", "https://replicate.delivery/pbxt/X0rM8qpUbWazC9bQgyDTfv3uew1248kDVebpy3LkgoofX32HB/out-3.png" ], "started_at": "2023-12-01T00:39:33.551915Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/yasvqklb4ydacjklnrqfn2qleu", "cancel": "https://api.replicate.com/v1/predictions/yasvqklb4ydacjklnrqfn2qleu/cancel" }, "version": "ab2d9e1e870b835b3a61b2dca3c631005a73ce1e54eb4e79e7e60ba5289d99ad" }Generated inUsing seed: 55125 skipping loading .. weights already loaded Prompt: a girl in a hoodie in the style of <s0><s1> txt2img mode 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:01<00:51, 1.06s/it] 4%|▍ | 2/50 [00:02<00:50, 1.06s/it] 6%|▌ | 3/50 [00:03<00:49, 1.06s/it] 8%|▊ | 4/50 [00:04<00:48, 1.06s/it] 10%|█ | 5/50 [00:05<00:47, 1.06s/it] 12%|█▏ | 6/50 [00:06<00:46, 1.06s/it] 14%|█▍ | 7/50 [00:07<00:45, 1.06s/it] 16%|█▌ | 8/50 [00:08<00:44, 1.06s/it] 18%|█▊ | 9/50 [00:09<00:43, 1.07s/it] 20%|██ | 10/50 [00:10<00:42, 1.06s/it] 22%|██▏ | 11/50 [00:11<00:41, 1.07s/it] 24%|██▍ | 12/50 [00:12<00:40, 1.07s/it] 26%|██▌ | 13/50 [00:13<00:39, 1.07s/it] 28%|██▊ | 14/50 [00:14<00:38, 1.07s/it] 30%|███ | 15/50 [00:15<00:37, 1.07s/it] 32%|███▏ | 16/50 [00:17<00:36, 1.07s/it] 34%|███▍ | 17/50 [00:18<00:35, 1.07s/it] 36%|███▌ | 18/50 [00:19<00:34, 1.07s/it] 38%|███▊ | 19/50 [00:20<00:33, 1.07s/it] 40%|████ | 20/50 [00:21<00:31, 1.07s/it] 42%|████▏ | 21/50 [00:22<00:30, 1.07s/it] 44%|████▍ | 22/50 [00:23<00:29, 1.07s/it] 46%|████▌ | 23/50 [00:24<00:28, 1.07s/it] 48%|████▊ | 24/50 [00:25<00:27, 1.07s/it] 50%|█████ | 25/50 [00:26<00:26, 1.07s/it] 52%|█████▏ | 26/50 [00:27<00:25, 1.07s/it] 54%|█████▍ | 27/50 [00:28<00:24, 1.07s/it] 56%|█████▌ | 28/50 [00:29<00:23, 1.07s/it] 58%|█████▊ | 29/50 [00:30<00:22, 1.07s/it] 60%|██████ | 30/50 [00:31<00:21, 1.07s/it] 62%|██████▏ | 31/50 [00:33<00:20, 1.07s/it] 64%|██████▍ | 32/50 [00:34<00:19, 1.07s/it] 66%|██████▌ | 33/50 [00:35<00:18, 1.07s/it] 68%|██████▊ | 34/50 [00:36<00:17, 1.07s/it] 70%|███████ | 35/50 [00:37<00:16, 1.07s/it] 72%|███████▏ | 36/50 [00:38<00:14, 1.07s/it] 74%|███████▍ | 37/50 [00:39<00:13, 1.07s/it] 76%|███████▌ | 38/50 [00:40<00:12, 1.07s/it] 78%|███████▊ | 39/50 [00:41<00:11, 1.07s/it] 80%|████████ | 40/50 [00:42<00:10, 1.07s/it] 82%|████████▏ | 41/50 [00:43<00:09, 1.07s/it] 84%|████████▍ | 42/50 [00:44<00:08, 1.07s/it] 86%|████████▌ | 43/50 [00:45<00:07, 1.07s/it] 88%|████████▊ | 44/50 [00:46<00:06, 1.07s/it] 90%|█████████ | 45/50 [00:48<00:05, 1.07s/it] 92%|█████████▏| 46/50 [00:49<00:04, 1.07s/it] 94%|█████████▍| 47/50 [00:50<00:03, 1.07s/it] 96%|█████████▌| 48/50 [00:51<00:02, 1.07s/it] 98%|█████████▊| 49/50 [00:52<00:01, 1.07s/it] 100%|██████████| 50/50 [00:53<00:00, 1.07s/it] 100%|██████████| 50/50 [00:53<00:00, 1.07s/it] Potential NSFW content was detected in one or more images. A black image will be returned instead. Try again with a different prompt and/or seed. NSFW content detected in image 0 NSFW content detected in image 2Prediction
justswim/em:ab2d9e1e870b835b3a61b2dca3c631005a73ce1e54eb4e79e7e60ba5289d99adModelIDc6ixuklb7rcybkn3kleabeqvvyStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- A sketch digital image of a forest, with signs pointing confusing directions in the style of TOK
- refine
- no_refiner
- scheduler
- K_EULER
- lora_scale
- 0.6
- num_outputs
- 4
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- texture, detail
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 1024, "height": 1024, "prompt": "A sketch digital image of a forest, with signs pointing confusing directions in the style of TOK", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "texture, detail", "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 justswim/em using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "justswim/em:ab2d9e1e870b835b3a61b2dca3c631005a73ce1e54eb4e79e7e60ba5289d99ad", { input: { width: 1024, height: 1024, prompt: "A sketch digital image of a forest, with signs pointing confusing directions in the style of TOK", refine: "no_refiner", scheduler: "K_EULER", lora_scale: 0.6, num_outputs: 4, guidance_scale: 7.5, apply_watermark: true, high_noise_frac: 0.8, negative_prompt: "texture, detail", 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 justswim/em using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "justswim/em:ab2d9e1e870b835b3a61b2dca3c631005a73ce1e54eb4e79e7e60ba5289d99ad", input={ "width": 1024, "height": 1024, "prompt": "A sketch digital image of a forest, with signs pointing confusing directions in the style of TOK", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": True, "high_noise_frac": 0.8, "negative_prompt": "texture, detail", "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 justswim/em 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": "justswim/em:ab2d9e1e870b835b3a61b2dca3c631005a73ce1e54eb4e79e7e60ba5289d99ad", "input": { "width": 1024, "height": 1024, "prompt": "A sketch digital image of a forest, with signs pointing confusing directions in the style of TOK", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "texture, detail", "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/justswim/em@sha256:ab2d9e1e870b835b3a61b2dca3c631005a73ce1e54eb4e79e7e60ba5289d99ad \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="A sketch digital image of a forest, with signs pointing confusing directions in the style of TOK"' \ -i 'refine="no_refiner"' \ -i 'scheduler="K_EULER"' \ -i 'lora_scale=0.6' \ -i 'num_outputs=4' \ -i 'guidance_scale=7.5' \ -i 'apply_watermark=true' \ -i 'high_noise_frac=0.8' \ -i 'negative_prompt="texture, detail"' \ -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/justswim/em@sha256:ab2d9e1e870b835b3a61b2dca3c631005a73ce1e54eb4e79e7e60ba5289d99adcurl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "A sketch digital image of a forest, with signs pointing confusing directions in the style of TOK", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "texture, detail", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-12-01T20:03:18.734677Z", "created_at": "2023-12-01T20:02:10.938329Z", "data_removed": false, "error": null, "id": "c6ixuklb7rcybkn3kleabeqvvy", "input": { "width": 1024, "height": 1024, "prompt": "A sketch digital image of a forest, with signs pointing confusing directions in the style of TOK", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "texture, detail", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 58107\nEnsuring enough disk space...\nFree disk space: 1479685357568\nDownloading weights: https://replicate.delivery/pbxt/ebsSpWwudgQfF076C9KBwUfqC6ZGAlem7DfqBeUM9U0dUcbfIA/trained_model.tar\nb'Downloaded 186 MB bytes in 3.871s (48 MB/s)\\nExtracted 186 MB in 0.056s (3.3 GB/s)\\n'\nDownloaded weights in 4.355781316757202 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: A sketch digital image of a forest, with signs pointing confusing directions in the style of <s0><s1>\ntxt2img mode\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:01<00:51, 1.06s/it]\n 4%|▍ | 2/50 [00:02<00:50, 1.05s/it]\n 6%|▌ | 3/50 [00:03<00:49, 1.05s/it]\n 8%|▊ | 4/50 [00:04<00:48, 1.06s/it]\n 10%|█ | 5/50 [00:05<00:47, 1.06s/it]\n 12%|█▏ | 6/50 [00:06<00:46, 1.06s/it]\n 14%|█▍ | 7/50 [00:07<00:45, 1.06s/it]\n 16%|█▌ | 8/50 [00:08<00:44, 1.06s/it]\n 18%|█▊ | 9/50 [00:09<00:43, 1.06s/it]\n 20%|██ | 10/50 [00:10<00:42, 1.06s/it]\n 22%|██▏ | 11/50 [00:11<00:41, 1.06s/it]\n 24%|██▍ | 12/50 [00:12<00:40, 1.06s/it]\n 26%|██▌ | 13/50 [00:13<00:39, 1.06s/it]\n 28%|██▊ | 14/50 [00:14<00:38, 1.06s/it]\n 30%|███ | 15/50 [00:15<00:37, 1.06s/it]\n 32%|███▏ | 16/50 [00:16<00:36, 1.06s/it]\n 34%|███▍ | 17/50 [00:17<00:34, 1.06s/it]\n 36%|███▌ | 18/50 [00:19<00:33, 1.06s/it]\n 38%|███▊ | 19/50 [00:20<00:32, 1.06s/it]\n 40%|████ | 20/50 [00:21<00:31, 1.06s/it]\n 42%|████▏ | 21/50 [00:22<00:30, 1.06s/it]\n 44%|████▍ | 22/50 [00:23<00:29, 1.06s/it]\n 46%|████▌ | 23/50 [00:24<00:28, 1.06s/it]\n 48%|████▊ | 24/50 [00:25<00:27, 1.06s/it]\n 50%|█████ | 25/50 [00:26<00:26, 1.06s/it]\n 52%|█████▏ | 26/50 [00:27<00:25, 1.06s/it]\n 54%|█████▍ | 27/50 [00:28<00:24, 1.06s/it]\n 56%|█████▌ | 28/50 [00:29<00:23, 1.06s/it]\n 58%|█████▊ | 29/50 [00:30<00:22, 1.06s/it]\n 60%|██████ | 30/50 [00:31<00:21, 1.06s/it]\n 62%|██████▏ | 31/50 [00:32<00:20, 1.06s/it]\n 64%|██████▍ | 32/50 [00:33<00:19, 1.06s/it]\n 66%|██████▌ | 33/50 [00:34<00:18, 1.06s/it]\n 68%|██████▊ | 34/50 [00:36<00:16, 1.06s/it]\n 70%|███████ | 35/50 [00:37<00:15, 1.06s/it]\n 72%|███████▏ | 36/50 [00:38<00:14, 1.06s/it]\n 74%|███████▍ | 37/50 [00:39<00:13, 1.06s/it]\n 76%|███████▌ | 38/50 [00:40<00:12, 1.06s/it]\n 78%|███████▊ | 39/50 [00:41<00:11, 1.06s/it]\n 80%|████████ | 40/50 [00:42<00:10, 1.06s/it]\n 82%|████████▏ | 41/50 [00:43<00:09, 1.06s/it]\n 84%|████████▍ | 42/50 [00:44<00:08, 1.06s/it]\n 86%|████████▌ | 43/50 [00:45<00:07, 1.06s/it]\n 88%|████████▊ | 44/50 [00:46<00:06, 1.06s/it]\n 90%|█████████ | 45/50 [00:47<00:05, 1.06s/it]\n 92%|█████████▏| 46/50 [00:48<00:04, 1.06s/it]\n 94%|█████████▍| 47/50 [00:49<00:03, 1.06s/it]\n 96%|█████████▌| 48/50 [00:50<00:02, 1.06s/it]\n 98%|█████████▊| 49/50 [00:51<00:01, 1.06s/it]\n100%|██████████| 50/50 [00:53<00:00, 1.06s/it]\n100%|██████████| 50/50 [00:53<00:00, 1.06s/it]", "metrics": { "predict_time": 65.458189, "total_time": 67.796348 }, "output": [ "https://replicate.delivery/pbxt/TWeMwKpes9v3IkF5Y0owr1PzMPcaTS3nFcX881XgcHhD4e7jA/out-0.png", "https://replicate.delivery/pbxt/UjRm65p9beRLbi5FqbBbLRGlg7XXGWCg2C5hN7TBC4UCcf9RA/out-1.png", "https://replicate.delivery/pbxt/FaulnnGLQNZgLRQKK5p1ngpNkDpezy27w6gCch0MkcpCcf9RA/out-2.png", "https://replicate.delivery/pbxt/nSqAxZdytzolC1JRGZvCj6Ck70u23KKSeZvbelxTjiCG4e7jA/out-3.png" ], "started_at": "2023-12-01T20:02:13.276488Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/c6ixuklb7rcybkn3kleabeqvvy", "cancel": "https://api.replicate.com/v1/predictions/c6ixuklb7rcybkn3kleabeqvvy/cancel" }, "version": "ab2d9e1e870b835b3a61b2dca3c631005a73ce1e54eb4e79e7e60ba5289d99ad" }Generated inUsing seed: 58107 Ensuring enough disk space... Free disk space: 1479685357568 Downloading weights: https://replicate.delivery/pbxt/ebsSpWwudgQfF076C9KBwUfqC6ZGAlem7DfqBeUM9U0dUcbfIA/trained_model.tar b'Downloaded 186 MB bytes in 3.871s (48 MB/s)\nExtracted 186 MB in 0.056s (3.3 GB/s)\n' Downloaded weights in 4.355781316757202 seconds Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: A sketch digital image of a forest, with signs pointing confusing directions in the style of <s0><s1> txt2img mode 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:01<00:51, 1.06s/it] 4%|▍ | 2/50 [00:02<00:50, 1.05s/it] 6%|▌ | 3/50 [00:03<00:49, 1.05s/it] 8%|▊ | 4/50 [00:04<00:48, 1.06s/it] 10%|█ | 5/50 [00:05<00:47, 1.06s/it] 12%|█▏ | 6/50 [00:06<00:46, 1.06s/it] 14%|█▍ | 7/50 [00:07<00:45, 1.06s/it] 16%|█▌ | 8/50 [00:08<00:44, 1.06s/it] 18%|█▊ | 9/50 [00:09<00:43, 1.06s/it] 20%|██ | 10/50 [00:10<00:42, 1.06s/it] 22%|██▏ | 11/50 [00:11<00:41, 1.06s/it] 24%|██▍ | 12/50 [00:12<00:40, 1.06s/it] 26%|██▌ | 13/50 [00:13<00:39, 1.06s/it] 28%|██▊ | 14/50 [00:14<00:38, 1.06s/it] 30%|███ | 15/50 [00:15<00:37, 1.06s/it] 32%|███▏ | 16/50 [00:16<00:36, 1.06s/it] 34%|███▍ | 17/50 [00:17<00:34, 1.06s/it] 36%|███▌ | 18/50 [00:19<00:33, 1.06s/it] 38%|███▊ | 19/50 [00:20<00:32, 1.06s/it] 40%|████ | 20/50 [00:21<00:31, 1.06s/it] 42%|████▏ | 21/50 [00:22<00:30, 1.06s/it] 44%|████▍ | 22/50 [00:23<00:29, 1.06s/it] 46%|████▌ | 23/50 [00:24<00:28, 1.06s/it] 48%|████▊ | 24/50 [00:25<00:27, 1.06s/it] 50%|█████ | 25/50 [00:26<00:26, 1.06s/it] 52%|█████▏ | 26/50 [00:27<00:25, 1.06s/it] 54%|█████▍ | 27/50 [00:28<00:24, 1.06s/it] 56%|█████▌ | 28/50 [00:29<00:23, 1.06s/it] 58%|█████▊ | 29/50 [00:30<00:22, 1.06s/it] 60%|██████ | 30/50 [00:31<00:21, 1.06s/it] 62%|██████▏ | 31/50 [00:32<00:20, 1.06s/it] 64%|██████▍ | 32/50 [00:33<00:19, 1.06s/it] 66%|██████▌ | 33/50 [00:34<00:18, 1.06s/it] 68%|██████▊ | 34/50 [00:36<00:16, 1.06s/it] 70%|███████ | 35/50 [00:37<00:15, 1.06s/it] 72%|███████▏ | 36/50 [00:38<00:14, 1.06s/it] 74%|███████▍ | 37/50 [00:39<00:13, 1.06s/it] 76%|███████▌ | 38/50 [00:40<00:12, 1.06s/it] 78%|███████▊ | 39/50 [00:41<00:11, 1.06s/it] 80%|████████ | 40/50 [00:42<00:10, 1.06s/it] 82%|████████▏ | 41/50 [00:43<00:09, 1.06s/it] 84%|████████▍ | 42/50 [00:44<00:08, 1.06s/it] 86%|████████▌ | 43/50 [00:45<00:07, 1.06s/it] 88%|████████▊ | 44/50 [00:46<00:06, 1.06s/it] 90%|█████████ | 45/50 [00:47<00:05, 1.06s/it] 92%|█████████▏| 46/50 [00:48<00:04, 1.06s/it] 94%|█████████▍| 47/50 [00:49<00:03, 1.06s/it] 96%|█████████▌| 48/50 [00:50<00:02, 1.06s/it] 98%|█████████▊| 49/50 [00:51<00:01, 1.06s/it] 100%|██████████| 50/50 [00:53<00:00, 1.06s/it] 100%|██████████| 50/50 [00:53<00:00, 1.06s/it]Prediction
justswim/em:ab2d9e1e870b835b3a61b2dca3c631005a73ce1e54eb4e79e7e60ba5289d99adModelIDrgqtabtb3eqyo6ljidjvbgs6ciStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- a couple dancing in the style of TOK
- refine
- no_refiner
- scheduler
- K_EULER
- lora_scale
- 0.8
- num_outputs
- 4
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.8
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 1024, "height": 1024, "prompt": "a couple dancing in the style of TOK", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "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 justswim/em using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "justswim/em:ab2d9e1e870b835b3a61b2dca3c631005a73ce1e54eb4e79e7e60ba5289d99ad", { input: { width: 1024, height: 1024, prompt: "a couple dancing in the style of TOK", refine: "no_refiner", scheduler: "K_EULER", lora_scale: 0.8, num_outputs: 4, guidance_scale: 7.5, apply_watermark: true, high_noise_frac: 0.8, 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 justswim/em using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "justswim/em:ab2d9e1e870b835b3a61b2dca3c631005a73ce1e54eb4e79e7e60ba5289d99ad", input={ "width": 1024, "height": 1024, "prompt": "a couple dancing in the style of TOK", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": True, "high_noise_frac": 0.8, "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 justswim/em 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": "justswim/em:ab2d9e1e870b835b3a61b2dca3c631005a73ce1e54eb4e79e7e60ba5289d99ad", "input": { "width": 1024, "height": 1024, "prompt": "a couple dancing in the style of TOK", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "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/justswim/em@sha256:ab2d9e1e870b835b3a61b2dca3c631005a73ce1e54eb4e79e7e60ba5289d99ad \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="a couple dancing in the style of TOK"' \ -i 'refine="no_refiner"' \ -i 'scheduler="K_EULER"' \ -i 'lora_scale=0.8' \ -i 'num_outputs=4' \ -i 'guidance_scale=7.5' \ -i 'apply_watermark=true' \ -i 'high_noise_frac=0.8' \ -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/justswim/em@sha256:ab2d9e1e870b835b3a61b2dca3c631005a73ce1e54eb4e79e7e60ba5289d99adcurl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "a couple dancing in the style of TOK", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-12-01T00:43:53.334028Z", "created_at": "2023-12-01T00:42:48.324570Z", "data_removed": false, "error": null, "id": "rgqtabtb3eqyo6ljidjvbgs6ci", "input": { "width": 1024, "height": 1024, "prompt": "a couple dancing in the style of TOK", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 6004\nEnsuring enough disk space...\nFree disk space: 1501504536576\nDownloading weights: https://replicate.delivery/pbxt/ebsSpWwudgQfF076C9KBwUfqC6ZGAlem7DfqBeUM9U0dUcbfIA/trained_model.tar\nb'Downloaded 186 MB bytes in 0.234s (795 MB/s)\\nExtracted 186 MB in 0.057s (3.2 GB/s)\\n'\nDownloaded weights in 0.39917993545532227 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: a couple dancing in the style of <s0><s1>\ntxt2img mode\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:01<00:51, 1.06s/it]\n 4%|▍ | 2/50 [00:02<00:50, 1.06s/it]\n 6%|▌ | 3/50 [00:03<00:49, 1.06s/it]\n 8%|▊ | 4/50 [00:04<00:48, 1.06s/it]\n 10%|█ | 5/50 [00:05<00:47, 1.06s/it]\n 12%|█▏ | 6/50 [00:06<00:46, 1.06s/it]\n 14%|█▍ | 7/50 [00:07<00:45, 1.06s/it]\n 16%|█▌ | 8/50 [00:08<00:44, 1.06s/it]\n 18%|█▊ | 9/50 [00:09<00:43, 1.06s/it]\n 20%|██ | 10/50 [00:10<00:42, 1.06s/it]\n 22%|██▏ | 11/50 [00:11<00:41, 1.06s/it]\n 24%|██▍ | 12/50 [00:12<00:40, 1.06s/it]\n 26%|██▌ | 13/50 [00:13<00:39, 1.06s/it]\n 28%|██▊ | 14/50 [00:14<00:38, 1.06s/it]\n 30%|███ | 15/50 [00:15<00:37, 1.06s/it]\n 32%|███▏ | 16/50 [00:16<00:36, 1.06s/it]\n 34%|███▍ | 17/50 [00:18<00:35, 1.06s/it]\n 36%|███▌ | 18/50 [00:19<00:33, 1.06s/it]\n 38%|███▊ | 19/50 [00:20<00:32, 1.06s/it]\n 40%|████ | 20/50 [00:21<00:31, 1.06s/it]\n 42%|████▏ | 21/50 [00:22<00:30, 1.06s/it]\n 44%|████▍ | 22/50 [00:23<00:29, 1.06s/it]\n 46%|████▌ | 23/50 [00:24<00:28, 1.06s/it]\n 48%|████▊ | 24/50 [00:25<00:27, 1.06s/it]\n 50%|█████ | 25/50 [00:26<00:26, 1.06s/it]\n 52%|█████▏ | 26/50 [00:27<00:25, 1.06s/it]\n 54%|█████▍ | 27/50 [00:28<00:24, 1.06s/it]\n 56%|█████▌ | 28/50 [00:29<00:23, 1.06s/it]\n 58%|█████▊ | 29/50 [00:30<00:22, 1.06s/it]\n 60%|██████ | 30/50 [00:31<00:21, 1.07s/it]\n 62%|██████▏ | 31/50 [00:32<00:20, 1.07s/it]\n 64%|██████▍ | 32/50 [00:33<00:19, 1.07s/it]\n 66%|██████▌ | 33/50 [00:35<00:18, 1.07s/it]\n 68%|██████▊ | 34/50 [00:36<00:17, 1.07s/it]\n 70%|███████ | 35/50 [00:37<00:15, 1.07s/it]\n 72%|███████▏ | 36/50 [00:38<00:14, 1.07s/it]\n 74%|███████▍ | 37/50 [00:39<00:13, 1.07s/it]\n 76%|███████▌ | 38/50 [00:40<00:12, 1.07s/it]\n 78%|███████▊ | 39/50 [00:41<00:11, 1.07s/it]\n 80%|████████ | 40/50 [00:42<00:10, 1.07s/it]\n 82%|████████▏ | 41/50 [00:43<00:09, 1.07s/it]\n 84%|████████▍ | 42/50 [00:44<00:08, 1.07s/it]\n 86%|████████▌ | 43/50 [00:45<00:07, 1.07s/it]\n 88%|████████▊ | 44/50 [00:46<00:06, 1.07s/it]\n 90%|█████████ | 45/50 [00:47<00:05, 1.07s/it]\n 92%|█████████▏| 46/50 [00:48<00:04, 1.07s/it]\n 94%|█████████▍| 47/50 [00:49<00:03, 1.07s/it]\n 96%|█████████▌| 48/50 [00:51<00:02, 1.07s/it]\n 98%|█████████▊| 49/50 [00:52<00:01, 1.07s/it]\n100%|██████████| 50/50 [00:53<00:00, 1.07s/it]\n100%|██████████| 50/50 [00:53<00:00, 1.06s/it]", "metrics": { "predict_time": 61.143651, "total_time": 65.009458 }, "output": [ "https://replicate.delivery/pbxt/orPzepXbUb2sEq7LBDpc4w4D46Fm89hlLbsVXTvXEuWj82eRA/out-0.png", "https://replicate.delivery/pbxt/CBcg0Qf9XfpwzUB4nX7FsBNr6iCUy583EUHEEaSlTkFH5t9RA/out-1.png", "https://replicate.delivery/pbxt/pa17xgFs1SoEOZKWwsyKKjxlezxDcgDx6WDMnUI8oSNk82eRA/out-2.png", "https://replicate.delivery/pbxt/lWSFsUw61qInDtn2fMm1ozpUxxUwQcnnS7mmZcZNdDtk82eRA/out-3.png" ], "started_at": "2023-12-01T00:42:52.190377Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/rgqtabtb3eqyo6ljidjvbgs6ci", "cancel": "https://api.replicate.com/v1/predictions/rgqtabtb3eqyo6ljidjvbgs6ci/cancel" }, "version": "ab2d9e1e870b835b3a61b2dca3c631005a73ce1e54eb4e79e7e60ba5289d99ad" }Generated inUsing seed: 6004 Ensuring enough disk space... Free disk space: 1501504536576 Downloading weights: https://replicate.delivery/pbxt/ebsSpWwudgQfF076C9KBwUfqC6ZGAlem7DfqBeUM9U0dUcbfIA/trained_model.tar b'Downloaded 186 MB bytes in 0.234s (795 MB/s)\nExtracted 186 MB in 0.057s (3.2 GB/s)\n' Downloaded weights in 0.39917993545532227 seconds Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: a couple dancing in the style of <s0><s1> txt2img mode 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:01<00:51, 1.06s/it] 4%|▍ | 2/50 [00:02<00:50, 1.06s/it] 6%|▌ | 3/50 [00:03<00:49, 1.06s/it] 8%|▊ | 4/50 [00:04<00:48, 1.06s/it] 10%|█ | 5/50 [00:05<00:47, 1.06s/it] 12%|█▏ | 6/50 [00:06<00:46, 1.06s/it] 14%|█▍ | 7/50 [00:07<00:45, 1.06s/it] 16%|█▌ | 8/50 [00:08<00:44, 1.06s/it] 18%|█▊ | 9/50 [00:09<00:43, 1.06s/it] 20%|██ | 10/50 [00:10<00:42, 1.06s/it] 22%|██▏ | 11/50 [00:11<00:41, 1.06s/it] 24%|██▍ | 12/50 [00:12<00:40, 1.06s/it] 26%|██▌ | 13/50 [00:13<00:39, 1.06s/it] 28%|██▊ | 14/50 [00:14<00:38, 1.06s/it] 30%|███ | 15/50 [00:15<00:37, 1.06s/it] 32%|███▏ | 16/50 [00:16<00:36, 1.06s/it] 34%|███▍ | 17/50 [00:18<00:35, 1.06s/it] 36%|███▌ | 18/50 [00:19<00:33, 1.06s/it] 38%|███▊ | 19/50 [00:20<00:32, 1.06s/it] 40%|████ | 20/50 [00:21<00:31, 1.06s/it] 42%|████▏ | 21/50 [00:22<00:30, 1.06s/it] 44%|████▍ | 22/50 [00:23<00:29, 1.06s/it] 46%|████▌ | 23/50 [00:24<00:28, 1.06s/it] 48%|████▊ | 24/50 [00:25<00:27, 1.06s/it] 50%|█████ | 25/50 [00:26<00:26, 1.06s/it] 52%|█████▏ | 26/50 [00:27<00:25, 1.06s/it] 54%|█████▍ | 27/50 [00:28<00:24, 1.06s/it] 56%|█████▌ | 28/50 [00:29<00:23, 1.06s/it] 58%|█████▊ | 29/50 [00:30<00:22, 1.06s/it] 60%|██████ | 30/50 [00:31<00:21, 1.07s/it] 62%|██████▏ | 31/50 [00:32<00:20, 1.07s/it] 64%|██████▍ | 32/50 [00:33<00:19, 1.07s/it] 66%|██████▌ | 33/50 [00:35<00:18, 1.07s/it] 68%|██████▊ | 34/50 [00:36<00:17, 1.07s/it] 70%|███████ | 35/50 [00:37<00:15, 1.07s/it] 72%|███████▏ | 36/50 [00:38<00:14, 1.07s/it] 74%|███████▍ | 37/50 [00:39<00:13, 1.07s/it] 76%|███████▌ | 38/50 [00:40<00:12, 1.07s/it] 78%|███████▊ | 39/50 [00:41<00:11, 1.07s/it] 80%|████████ | 40/50 [00:42<00:10, 1.07s/it] 82%|████████▏ | 41/50 [00:43<00:09, 1.07s/it] 84%|████████▍ | 42/50 [00:44<00:08, 1.07s/it] 86%|████████▌ | 43/50 [00:45<00:07, 1.07s/it] 88%|████████▊ | 44/50 [00:46<00:06, 1.07s/it] 90%|█████████ | 45/50 [00:47<00:05, 1.07s/it] 92%|█████████▏| 46/50 [00:48<00:04, 1.07s/it] 94%|█████████▍| 47/50 [00:49<00:03, 1.07s/it] 96%|█████████▌| 48/50 [00:51<00:02, 1.07s/it] 98%|█████████▊| 49/50 [00:52<00:01, 1.07s/it] 100%|██████████| 50/50 [00:53<00:00, 1.07s/it] 100%|██████████| 50/50 [00:53<00:00, 1.06s/it]Prediction
justswim/em:ab2d9e1e870b835b3a61b2dca3c631005a73ce1e54eb4e79e7e60ba5289d99adModelID2xfoyg3b7xfmf54wr5qil37rd4StatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- A digital sketch of girl riding a bike in the style of TOK, red hue, closeup
- refine
- no_refiner
- scheduler
- K_EULER
- lora_scale
- 0.85
- num_outputs
- 4
- guidance_scale
- 10
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- detail, background
- prompt_strength
- 0.8
- num_inference_steps
- 100
{ "width": 1024, "height": 1024, "prompt": "A digital sketch of girl riding a bike in the style of TOK, red hue, closeup", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.85, "num_outputs": 4, "guidance_scale": 10, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "detail, background", "prompt_strength": 0.8, "num_inference_steps": 100 }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 justswim/em using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "justswim/em:ab2d9e1e870b835b3a61b2dca3c631005a73ce1e54eb4e79e7e60ba5289d99ad", { input: { width: 1024, height: 1024, prompt: "A digital sketch of girl riding a bike in the style of TOK, red hue, closeup", refine: "no_refiner", scheduler: "K_EULER", lora_scale: 0.85, num_outputs: 4, guidance_scale: 10, apply_watermark: true, high_noise_frac: 0.8, negative_prompt: "detail, background", prompt_strength: 0.8, num_inference_steps: 100 } } ); // 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 justswim/em using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "justswim/em:ab2d9e1e870b835b3a61b2dca3c631005a73ce1e54eb4e79e7e60ba5289d99ad", input={ "width": 1024, "height": 1024, "prompt": "A digital sketch of girl riding a bike in the style of TOK, red hue, closeup", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.85, "num_outputs": 4, "guidance_scale": 10, "apply_watermark": True, "high_noise_frac": 0.8, "negative_prompt": "detail, background", "prompt_strength": 0.8, "num_inference_steps": 100 } ) # 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 justswim/em 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": "justswim/em:ab2d9e1e870b835b3a61b2dca3c631005a73ce1e54eb4e79e7e60ba5289d99ad", "input": { "width": 1024, "height": 1024, "prompt": "A digital sketch of girl riding a bike in the style of TOK, red hue, closeup", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.85, "num_outputs": 4, "guidance_scale": 10, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "detail, background", "prompt_strength": 0.8, "num_inference_steps": 100 } }' \ 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/justswim/em@sha256:ab2d9e1e870b835b3a61b2dca3c631005a73ce1e54eb4e79e7e60ba5289d99ad \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="A digital sketch of girl riding a bike in the style of TOK, red hue, closeup"' \ -i 'refine="no_refiner"' \ -i 'scheduler="K_EULER"' \ -i 'lora_scale=0.85' \ -i 'num_outputs=4' \ -i 'guidance_scale=10' \ -i 'apply_watermark=true' \ -i 'high_noise_frac=0.8' \ -i 'negative_prompt="detail, background"' \ -i 'prompt_strength=0.8' \ -i 'num_inference_steps=100'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/justswim/em@sha256:ab2d9e1e870b835b3a61b2dca3c631005a73ce1e54eb4e79e7e60ba5289d99adcurl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "A digital sketch of girl riding a bike in the style of TOK, red hue, closeup", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.85, "num_outputs": 4, "guidance_scale": 10, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "detail, background", "prompt_strength": 0.8, "num_inference_steps": 100 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-12-01T00:50:04.894394Z", "created_at": "2023-12-01T00:48:05.736019Z", "data_removed": false, "error": null, "id": "2xfoyg3b7xfmf54wr5qil37rd4", "input": { "width": 1024, "height": 1024, "prompt": "A digital sketch of girl riding a bike in the style of TOK, red hue, closeup", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.85, "num_outputs": 4, "guidance_scale": 10, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "detail, background", "prompt_strength": 0.8, "num_inference_steps": 100 }, "logs": "Using seed: 47187\nEnsuring enough disk space...\nFree disk space: 1839371165696\nDownloading weights: https://replicate.delivery/pbxt/ebsSpWwudgQfF076C9KBwUfqC6ZGAlem7DfqBeUM9U0dUcbfIA/trained_model.tar\nb'Downloaded 186 MB bytes in 2.830s (66 MB/s)\\nExtracted 186 MB in 0.047s (3.9 GB/s)\\n'\nDownloaded weights in 3.0661065578460693 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: A digital sketch of girl riding a bike in the style of <s0><s1>, red hue, closeup\ntxt2img mode\n 0%| | 0/100 [00:00<?, ?it/s]\n 1%| | 1/100 [00:01<01:45, 1.06s/it]\n 2%|▏ | 2/100 [00:02<01:44, 1.06s/it]\n 3%|▎ | 3/100 [00:03<01:43, 1.06s/it]\n 4%|▍ | 4/100 [00:04<01:42, 1.06s/it]\n 5%|▌ | 5/100 [00:05<01:41, 1.06s/it]\n 6%|▌ | 6/100 [00:06<01:40, 1.06s/it]\n 7%|▋ | 7/100 [00:07<01:38, 1.06s/it]\n 8%|▊ | 8/100 [00:08<01:37, 1.06s/it]\n 9%|▉ | 9/100 [00:09<01:36, 1.06s/it]\n 10%|█ | 10/100 [00:10<01:35, 1.06s/it]\n 11%|█ | 11/100 [00:11<01:34, 1.06s/it]\n 12%|█▏ | 12/100 [00:12<01:33, 1.06s/it]\n 13%|█▎ | 13/100 [00:13<01:32, 1.06s/it]\n 14%|█▍ | 14/100 [00:14<01:31, 1.06s/it]\n 15%|█▌ | 15/100 [00:15<01:30, 1.06s/it]\n 16%|█▌ | 16/100 [00:16<01:29, 1.06s/it]\n 17%|█▋ | 17/100 [00:18<01:28, 1.06s/it]\n 18%|█▊ | 18/100 [00:19<01:27, 1.06s/it]\n 19%|█▉ | 19/100 [00:20<01:26, 1.06s/it]\n 20%|██ | 20/100 [00:21<01:25, 1.06s/it]\n 21%|██ | 21/100 [00:22<01:24, 1.07s/it]\n 22%|██▏ | 22/100 [00:23<01:23, 1.06s/it]\n 23%|██▎ | 23/100 [00:24<01:21, 1.06s/it]\n 24%|██▍ | 24/100 [00:25<01:20, 1.06s/it]\n 25%|██▌ | 25/100 [00:26<01:19, 1.07s/it]\n 26%|██▌ | 26/100 [00:27<01:18, 1.06s/it]\n 27%|██▋ | 27/100 [00:28<01:17, 1.06s/it]\n 28%|██▊ | 28/100 [00:29<01:16, 1.06s/it]\n 29%|██▉ | 29/100 [00:30<01:15, 1.06s/it]\n 30%|███ | 30/100 [00:31<01:14, 1.06s/it]\n 31%|███ | 31/100 [00:32<01:13, 1.06s/it]\n 32%|███▏ | 32/100 [00:34<01:12, 1.07s/it]\n 33%|███▎ | 33/100 [00:35<01:11, 1.07s/it]\n 34%|███▍ | 34/100 [00:36<01:10, 1.07s/it]\n 35%|███▌ | 35/100 [00:37<01:09, 1.07s/it]\n 36%|███▌ | 36/100 [00:38<01:08, 1.07s/it]\n 37%|███▋ | 37/100 [00:39<01:07, 1.07s/it]\n 38%|███▊ | 38/100 [00:40<01:06, 1.07s/it]\n 39%|███▉ | 39/100 [00:41<01:05, 1.07s/it]\n 40%|████ | 40/100 [00:42<01:04, 1.07s/it]\n 41%|████ | 41/100 [00:43<01:03, 1.07s/it]\n 42%|████▏ | 42/100 [00:44<01:01, 1.07s/it]\n 43%|████▎ | 43/100 [00:45<01:00, 1.07s/it]\n 44%|████▍ | 44/100 [00:46<00:59, 1.07s/it]\n 45%|████▌ | 45/100 [00:47<00:58, 1.07s/it]\n 46%|████▌ | 46/100 [00:48<00:57, 1.07s/it]\n 47%|████▋ | 47/100 [00:50<00:56, 1.07s/it]\n 48%|████▊ | 48/100 [00:51<00:55, 1.07s/it]\n 49%|████▉ | 49/100 [00:52<00:54, 1.07s/it]\n 50%|█████ | 50/100 [00:53<00:53, 1.07s/it]\n 51%|█████ | 51/100 [00:54<00:52, 1.07s/it]\n 52%|█████▏ | 52/100 [00:55<00:51, 1.07s/it]\n 53%|█████▎ | 53/100 [00:56<00:50, 1.07s/it]\n 54%|█████▍ | 54/100 [00:57<00:49, 1.07s/it]\n 55%|█████▌ | 55/100 [00:58<00:48, 1.07s/it]\n 56%|█████▌ | 56/100 [00:59<00:46, 1.07s/it]\n 57%|█████▋ | 57/100 [01:00<00:45, 1.07s/it]\n 58%|█████▊ | 58/100 [01:01<00:44, 1.07s/it]\n 59%|█████▉ | 59/100 [01:02<00:43, 1.07s/it]\n 60%|██████ | 60/100 [01:03<00:42, 1.07s/it]\n 61%|██████ | 61/100 [01:05<00:41, 1.07s/it]\n 62%|██████▏ | 62/100 [01:06<00:40, 1.07s/it]\n 63%|██████▎ | 63/100 [01:07<00:39, 1.07s/it]\n 64%|██████▍ | 64/100 [01:08<00:38, 1.07s/it]\n 65%|██████▌ | 65/100 [01:09<00:37, 1.07s/it]\n 66%|██████▌ | 66/100 [01:10<00:36, 1.07s/it]\n 67%|██████▋ | 67/100 [01:11<00:35, 1.07s/it]\n 68%|██████▊ | 68/100 [01:12<00:34, 1.07s/it]\n 69%|██████▉ | 69/100 [01:13<00:33, 1.07s/it]\n 70%|███████ | 70/100 [01:14<00:32, 1.07s/it]\n 71%|███████ | 71/100 [01:15<00:31, 1.07s/it]\n 72%|███████▏ | 72/100 [01:16<00:29, 1.07s/it]\n 73%|███████▎ | 73/100 [01:17<00:28, 1.07s/it]\n 74%|███████▍ | 74/100 [01:18<00:27, 1.07s/it]\n 75%|███████▌ | 75/100 [01:20<00:26, 1.07s/it]\n 76%|███████▌ | 76/100 [01:21<00:25, 1.07s/it]\n 77%|███████▋ | 77/100 [01:22<00:24, 1.07s/it]\n 78%|███████▊ | 78/100 [01:23<00:23, 1.07s/it]\n 79%|███████▉ | 79/100 [01:24<00:22, 1.07s/it]\n 80%|████████ | 80/100 [01:25<00:21, 1.07s/it]\n 81%|████████ | 81/100 [01:26<00:20, 1.07s/it]\n 82%|████████▏ | 82/100 [01:27<00:19, 1.07s/it]\n 83%|████████▎ | 83/100 [01:28<00:18, 1.07s/it]\n 84%|████████▍ | 84/100 [01:29<00:17, 1.07s/it]\n 85%|████████▌ | 85/100 [01:30<00:16, 1.07s/it]\n 86%|████████▌ | 86/100 [01:31<00:14, 1.07s/it]\n 87%|████████▋ | 87/100 [01:32<00:13, 1.07s/it]\n 88%|████████▊ | 88/100 [01:33<00:12, 1.07s/it]\n 89%|████████▉ | 89/100 [01:34<00:11, 1.07s/it]\n 90%|█████████ | 90/100 [01:36<00:10, 1.07s/it]\n 91%|█████████ | 91/100 [01:37<00:09, 1.07s/it]\n 92%|█████████▏| 92/100 [01:38<00:08, 1.07s/it]\n 93%|█████████▎| 93/100 [01:39<00:07, 1.07s/it]\n 94%|█████████▍| 94/100 [01:40<00:06, 1.07s/it]\n 95%|█████████▌| 95/100 [01:41<00:05, 1.07s/it]\n 96%|█████████▌| 96/100 [01:42<00:04, 1.07s/it]\n 97%|█████████▋| 97/100 [01:43<00:03, 1.07s/it]\n 98%|█████████▊| 98/100 [01:44<00:02, 1.07s/it]\n 99%|█████████▉| 99/100 [01:45<00:01, 1.07s/it]\n100%|██████████| 100/100 [01:46<00:00, 1.07s/it]\n100%|██████████| 100/100 [01:46<00:00, 1.07s/it]", "metrics": { "predict_time": 115.203911, "total_time": 119.158375 }, "output": [ "https://replicate.delivery/pbxt/U3OCZNBGto7bB9Xs2oGlS675f6vdCOXGnAd3uTuBfke29b7jA/out-0.png", "https://replicate.delivery/pbxt/pp9WQTGhB1rpKx0GIRMLvOEm4RsaPByURBXGOUBJWlAvf2eRA/out-1.png", "https://replicate.delivery/pbxt/foeetCG8FQThuIMGiuaQBWy1PjfiNuk6pymL9OchmGDw732HB/out-2.png", "https://replicate.delivery/pbxt/bkfdf7zRTTqZLUWWhP2UaoTYvNGHEt0gIVwNjas5E9M8eb7jA/out-3.png" ], "started_at": "2023-12-01T00:48:09.690483Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/2xfoyg3b7xfmf54wr5qil37rd4", "cancel": "https://api.replicate.com/v1/predictions/2xfoyg3b7xfmf54wr5qil37rd4/cancel" }, "version": "ab2d9e1e870b835b3a61b2dca3c631005a73ce1e54eb4e79e7e60ba5289d99ad" }Generated inUsing seed: 47187 Ensuring enough disk space... Free disk space: 1839371165696 Downloading weights: https://replicate.delivery/pbxt/ebsSpWwudgQfF076C9KBwUfqC6ZGAlem7DfqBeUM9U0dUcbfIA/trained_model.tar b'Downloaded 186 MB bytes in 2.830s (66 MB/s)\nExtracted 186 MB in 0.047s (3.9 GB/s)\n' Downloaded weights in 3.0661065578460693 seconds Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: A digital sketch of girl riding a bike in the style of <s0><s1>, red hue, closeup txt2img mode 0%| | 0/100 [00:00<?, ?it/s] 1%| | 1/100 [00:01<01:45, 1.06s/it] 2%|▏ | 2/100 [00:02<01:44, 1.06s/it] 3%|▎ | 3/100 [00:03<01:43, 1.06s/it] 4%|▍ | 4/100 [00:04<01:42, 1.06s/it] 5%|▌ | 5/100 [00:05<01:41, 1.06s/it] 6%|▌ | 6/100 [00:06<01:40, 1.06s/it] 7%|▋ | 7/100 [00:07<01:38, 1.06s/it] 8%|▊ | 8/100 [00:08<01:37, 1.06s/it] 9%|▉ | 9/100 [00:09<01:36, 1.06s/it] 10%|█ | 10/100 [00:10<01:35, 1.06s/it] 11%|█ | 11/100 [00:11<01:34, 1.06s/it] 12%|█▏ | 12/100 [00:12<01:33, 1.06s/it] 13%|█▎ | 13/100 [00:13<01:32, 1.06s/it] 14%|█▍ | 14/100 [00:14<01:31, 1.06s/it] 15%|█▌ | 15/100 [00:15<01:30, 1.06s/it] 16%|█▌ | 16/100 [00:16<01:29, 1.06s/it] 17%|█▋ | 17/100 [00:18<01:28, 1.06s/it] 18%|█▊ | 18/100 [00:19<01:27, 1.06s/it] 19%|█▉ | 19/100 [00:20<01:26, 1.06s/it] 20%|██ | 20/100 [00:21<01:25, 1.06s/it] 21%|██ | 21/100 [00:22<01:24, 1.07s/it] 22%|██▏ | 22/100 [00:23<01:23, 1.06s/it] 23%|██▎ | 23/100 [00:24<01:21, 1.06s/it] 24%|██▍ | 24/100 [00:25<01:20, 1.06s/it] 25%|██▌ | 25/100 [00:26<01:19, 1.07s/it] 26%|██▌ | 26/100 [00:27<01:18, 1.06s/it] 27%|██▋ | 27/100 [00:28<01:17, 1.06s/it] 28%|██▊ | 28/100 [00:29<01:16, 1.06s/it] 29%|██▉ | 29/100 [00:30<01:15, 1.06s/it] 30%|███ | 30/100 [00:31<01:14, 1.06s/it] 31%|███ | 31/100 [00:32<01:13, 1.06s/it] 32%|███▏ | 32/100 [00:34<01:12, 1.07s/it] 33%|███▎ | 33/100 [00:35<01:11, 1.07s/it] 34%|███▍ | 34/100 [00:36<01:10, 1.07s/it] 35%|███▌ | 35/100 [00:37<01:09, 1.07s/it] 36%|███▌ | 36/100 [00:38<01:08, 1.07s/it] 37%|███▋ | 37/100 [00:39<01:07, 1.07s/it] 38%|███▊ | 38/100 [00:40<01:06, 1.07s/it] 39%|███▉ | 39/100 [00:41<01:05, 1.07s/it] 40%|████ | 40/100 [00:42<01:04, 1.07s/it] 41%|████ | 41/100 [00:43<01:03, 1.07s/it] 42%|████▏ | 42/100 [00:44<01:01, 1.07s/it] 43%|████▎ | 43/100 [00:45<01:00, 1.07s/it] 44%|████▍ | 44/100 [00:46<00:59, 1.07s/it] 45%|████▌ | 45/100 [00:47<00:58, 1.07s/it] 46%|████▌ | 46/100 [00:48<00:57, 1.07s/it] 47%|████▋ | 47/100 [00:50<00:56, 1.07s/it] 48%|████▊ | 48/100 [00:51<00:55, 1.07s/it] 49%|████▉ | 49/100 [00:52<00:54, 1.07s/it] 50%|█████ | 50/100 [00:53<00:53, 1.07s/it] 51%|█████ | 51/100 [00:54<00:52, 1.07s/it] 52%|█████▏ | 52/100 [00:55<00:51, 1.07s/it] 53%|█████▎ | 53/100 [00:56<00:50, 1.07s/it] 54%|█████▍ | 54/100 [00:57<00:49, 1.07s/it] 55%|█████▌ | 55/100 [00:58<00:48, 1.07s/it] 56%|█████▌ | 56/100 [00:59<00:46, 1.07s/it] 57%|█████▋ | 57/100 [01:00<00:45, 1.07s/it] 58%|█████▊ | 58/100 [01:01<00:44, 1.07s/it] 59%|█████▉ | 59/100 [01:02<00:43, 1.07s/it] 60%|██████ | 60/100 [01:03<00:42, 1.07s/it] 61%|██████ | 61/100 [01:05<00:41, 1.07s/it] 62%|██████▏ | 62/100 [01:06<00:40, 1.07s/it] 63%|██████▎ | 63/100 [01:07<00:39, 1.07s/it] 64%|██████▍ | 64/100 [01:08<00:38, 1.07s/it] 65%|██████▌ | 65/100 [01:09<00:37, 1.07s/it] 66%|██████▌ | 66/100 [01:10<00:36, 1.07s/it] 67%|██████▋ | 67/100 [01:11<00:35, 1.07s/it] 68%|██████▊ | 68/100 [01:12<00:34, 1.07s/it] 69%|██████▉ | 69/100 [01:13<00:33, 1.07s/it] 70%|███████ | 70/100 [01:14<00:32, 1.07s/it] 71%|███████ | 71/100 [01:15<00:31, 1.07s/it] 72%|███████▏ | 72/100 [01:16<00:29, 1.07s/it] 73%|███████▎ | 73/100 [01:17<00:28, 1.07s/it] 74%|███████▍ | 74/100 [01:18<00:27, 1.07s/it] 75%|███████▌ | 75/100 [01:20<00:26, 1.07s/it] 76%|███████▌ | 76/100 [01:21<00:25, 1.07s/it] 77%|███████▋ | 77/100 [01:22<00:24, 1.07s/it] 78%|███████▊ | 78/100 [01:23<00:23, 1.07s/it] 79%|███████▉ | 79/100 [01:24<00:22, 1.07s/it] 80%|████████ | 80/100 [01:25<00:21, 1.07s/it] 81%|████████ | 81/100 [01:26<00:20, 1.07s/it] 82%|████████▏ | 82/100 [01:27<00:19, 1.07s/it] 83%|████████▎ | 83/100 [01:28<00:18, 1.07s/it] 84%|████████▍ | 84/100 [01:29<00:17, 1.07s/it] 85%|████████▌ | 85/100 [01:30<00:16, 1.07s/it] 86%|████████▌ | 86/100 [01:31<00:14, 1.07s/it] 87%|████████▋ | 87/100 [01:32<00:13, 1.07s/it] 88%|████████▊ | 88/100 [01:33<00:12, 1.07s/it] 89%|████████▉ | 89/100 [01:34<00:11, 1.07s/it] 90%|█████████ | 90/100 [01:36<00:10, 1.07s/it] 91%|█████████ | 91/100 [01:37<00:09, 1.07s/it] 92%|█████████▏| 92/100 [01:38<00:08, 1.07s/it] 93%|█████████▎| 93/100 [01:39<00:07, 1.07s/it] 94%|█████████▍| 94/100 [01:40<00:06, 1.07s/it] 95%|█████████▌| 95/100 [01:41<00:05, 1.07s/it] 96%|█████████▌| 96/100 [01:42<00:04, 1.07s/it] 97%|█████████▋| 97/100 [01:43<00:03, 1.07s/it] 98%|█████████▊| 98/100 [01:44<00:02, 1.07s/it] 99%|█████████▉| 99/100 [01:45<00:01, 1.07s/it] 100%|██████████| 100/100 [01:46<00:00, 1.07s/it] 100%|██████████| 100/100 [01:46<00:00, 1.07s/it]Prediction
justswim/em:ab2d9e1e870b835b3a61b2dca3c631005a73ce1e54eb4e79e7e60ba5289d99adModelID4zsvxhdbqdoshyut27tpaqtnoqStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- in the style of TOK, a digital sketch of portrait of a boy taking a picture, blue hue, closeup
- refine
- no_refiner
- scheduler
- K_EULER
- lora_scale
- 0.85
- num_outputs
- 4
- guidance_scale
- 10
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- detail, background
- prompt_strength
- 0.8
- num_inference_steps
- 100
{ "width": 1024, "height": 1024, "prompt": "in the style of TOK, a digital sketch of portrait of a boy taking a picture, blue hue, closeup", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.85, "num_outputs": 4, "guidance_scale": 10, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "detail, background", "prompt_strength": 0.8, "num_inference_steps": 100 }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 justswim/em using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "justswim/em:ab2d9e1e870b835b3a61b2dca3c631005a73ce1e54eb4e79e7e60ba5289d99ad", { input: { width: 1024, height: 1024, prompt: "in the style of TOK, a digital sketch of portrait of a boy taking a picture, blue hue, closeup", refine: "no_refiner", scheduler: "K_EULER", lora_scale: 0.85, num_outputs: 4, guidance_scale: 10, apply_watermark: true, high_noise_frac: 0.8, negative_prompt: "detail, background", prompt_strength: 0.8, num_inference_steps: 100 } } ); // 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 justswim/em using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "justswim/em:ab2d9e1e870b835b3a61b2dca3c631005a73ce1e54eb4e79e7e60ba5289d99ad", input={ "width": 1024, "height": 1024, "prompt": "in the style of TOK, a digital sketch of portrait of a boy taking a picture, blue hue, closeup", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.85, "num_outputs": 4, "guidance_scale": 10, "apply_watermark": True, "high_noise_frac": 0.8, "negative_prompt": "detail, background", "prompt_strength": 0.8, "num_inference_steps": 100 } ) # 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 justswim/em 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": "justswim/em:ab2d9e1e870b835b3a61b2dca3c631005a73ce1e54eb4e79e7e60ba5289d99ad", "input": { "width": 1024, "height": 1024, "prompt": "in the style of TOK, a digital sketch of portrait of a boy taking a picture, blue hue, closeup", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.85, "num_outputs": 4, "guidance_scale": 10, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "detail, background", "prompt_strength": 0.8, "num_inference_steps": 100 } }' \ 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/justswim/em@sha256:ab2d9e1e870b835b3a61b2dca3c631005a73ce1e54eb4e79e7e60ba5289d99ad \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="in the style of TOK, a digital sketch of portrait of a boy taking a picture, blue hue, closeup"' \ -i 'refine="no_refiner"' \ -i 'scheduler="K_EULER"' \ -i 'lora_scale=0.85' \ -i 'num_outputs=4' \ -i 'guidance_scale=10' \ -i 'apply_watermark=true' \ -i 'high_noise_frac=0.8' \ -i 'negative_prompt="detail, background"' \ -i 'prompt_strength=0.8' \ -i 'num_inference_steps=100'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/justswim/em@sha256:ab2d9e1e870b835b3a61b2dca3c631005a73ce1e54eb4e79e7e60ba5289d99adcurl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "in the style of TOK, a digital sketch of portrait of a boy taking a picture, blue hue, closeup", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.85, "num_outputs": 4, "guidance_scale": 10, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "detail, background", "prompt_strength": 0.8, "num_inference_steps": 100 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-12-01T00:54:22.152111Z", "created_at": "2023-12-01T00:52:23.114939Z", "data_removed": false, "error": null, "id": "4zsvxhdbqdoshyut27tpaqtnoq", "input": { "width": 1024, "height": 1024, "prompt": "in the style of TOK, a digital sketch of portrait of a boy taking a picture, blue hue, closeup", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.85, "num_outputs": 4, "guidance_scale": 10, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "detail, background", "prompt_strength": 0.8, "num_inference_steps": 100 }, "logs": "Using seed: 57566\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: in the style of <s0><s1>, a digital sketch of portrait of a boy taking a picture, blue hue, closeup\ntxt2img mode\n 0%| | 0/100 [00:00<?, ?it/s]\n 1%| | 1/100 [00:01<01:44, 1.05s/it]\n 2%|▏ | 2/100 [00:02<01:42, 1.05s/it]\n 3%|▎ | 3/100 [00:03<01:41, 1.05s/it]\n 4%|▍ | 4/100 [00:04<01:41, 1.05s/it]\n 5%|▌ | 5/100 [00:05<01:40, 1.05s/it]\n 6%|▌ | 6/100 [00:06<01:39, 1.06s/it]\n 7%|▋ | 7/100 [00:07<01:38, 1.06s/it]\n 8%|▊ | 8/100 [00:08<01:37, 1.06s/it]\n 9%|▉ | 9/100 [00:09<01:36, 1.06s/it]\n 10%|█ | 10/100 [00:10<01:35, 1.06s/it]\n 11%|█ | 11/100 [00:11<01:34, 1.06s/it]\n 12%|█▏ | 12/100 [00:12<01:32, 1.06s/it]\n 13%|█▎ | 13/100 [00:13<01:31, 1.06s/it]\n 14%|█▍ | 14/100 [00:14<01:30, 1.06s/it]\n 15%|█▌ | 15/100 [00:15<01:29, 1.06s/it]\n 16%|█▌ | 16/100 [00:16<01:28, 1.06s/it]\n 17%|█▋ | 17/100 [00:17<01:27, 1.06s/it]\n 18%|█▊ | 18/100 [00:19<01:26, 1.06s/it]\n 19%|█▉ | 19/100 [00:20<01:25, 1.06s/it]\n 20%|██ | 20/100 [00:21<01:24, 1.06s/it]\n 21%|██ | 21/100 [00:22<01:23, 1.06s/it]\n 22%|██▏ | 22/100 [00:23<01:22, 1.06s/it]\n 23%|██▎ | 23/100 [00:24<01:21, 1.06s/it]\n 24%|██▍ | 24/100 [00:25<01:20, 1.06s/it]\n 25%|██▌ | 25/100 [00:26<01:19, 1.06s/it]\n 26%|██▌ | 26/100 [00:27<01:18, 1.06s/it]\n 27%|██▋ | 27/100 [00:28<01:17, 1.06s/it]\n 28%|██▊ | 28/100 [00:29<01:16, 1.06s/it]\n 29%|██▉ | 29/100 [00:30<01:15, 1.06s/it]\n 30%|███ | 30/100 [00:31<01:14, 1.06s/it]\n 31%|███ | 31/100 [00:32<01:13, 1.06s/it]\n 32%|███▏ | 32/100 [00:33<01:12, 1.06s/it]\n 33%|███▎ | 33/100 [00:34<01:11, 1.06s/it]\n 34%|███▍ | 34/100 [00:36<01:10, 1.06s/it]\n 35%|███▌ | 35/100 [00:37<01:09, 1.06s/it]\n 36%|███▌ | 36/100 [00:38<01:08, 1.06s/it]\n 37%|███▋ | 37/100 [00:39<01:06, 1.06s/it]\n 38%|███▊ | 38/100 [00:40<01:05, 1.06s/it]\n 39%|███▉ | 39/100 [00:41<01:04, 1.06s/it]\n 40%|████ | 40/100 [00:42<01:03, 1.06s/it]\n 41%|████ | 41/100 [00:43<01:02, 1.06s/it]\n 42%|████▏ | 42/100 [00:44<01:01, 1.06s/it]\n 43%|████▎ | 43/100 [00:45<01:00, 1.06s/it]\n 44%|████▍ | 44/100 [00:46<00:59, 1.06s/it]\n 45%|████▌ | 45/100 [00:47<00:58, 1.06s/it]\n 46%|████▌ | 46/100 [00:48<00:57, 1.07s/it]\n 47%|████▋ | 47/100 [00:49<00:56, 1.06s/it]\n 48%|████▊ | 48/100 [00:50<00:55, 1.06s/it]\n 49%|████▉ | 49/100 [00:51<00:54, 1.06s/it]\n 50%|█████ | 50/100 [00:53<00:53, 1.06s/it]\n 51%|█████ | 51/100 [00:54<00:52, 1.06s/it]\n 52%|█████▏ | 52/100 [00:55<00:51, 1.07s/it]\n 53%|█████▎ | 53/100 [00:56<00:50, 1.07s/it]\n 54%|█████▍ | 54/100 [00:57<00:48, 1.06s/it]\n 55%|█████▌ | 55/100 [00:58<00:47, 1.06s/it]\n 56%|█████▌ | 56/100 [00:59<00:46, 1.06s/it]\n 57%|█████▋ | 57/100 [01:00<00:45, 1.06s/it]\n 58%|█████▊ | 58/100 [01:01<00:44, 1.07s/it]\n 59%|█████▉ | 59/100 [01:02<00:43, 1.06s/it]\n 60%|██████ | 60/100 [01:03<00:42, 1.06s/it]\n 61%|██████ | 61/100 [01:04<00:41, 1.06s/it]\n 62%|██████▏ | 62/100 [01:05<00:40, 1.07s/it]\n 63%|██████▎ | 63/100 [01:06<00:39, 1.06s/it]\n 64%|██████▍ | 64/100 [01:07<00:38, 1.06s/it]\n 65%|██████▌ | 65/100 [01:08<00:37, 1.06s/it]\n 66%|██████▌ | 66/100 [01:10<00:36, 1.06s/it]\n 67%|██████▋ | 67/100 [01:11<00:35, 1.07s/it]\n 68%|██████▊ | 68/100 [01:12<00:34, 1.07s/it]\n 69%|██████▉ | 69/100 [01:13<00:33, 1.07s/it]\n 70%|███████ | 70/100 [01:14<00:32, 1.07s/it]\n 71%|███████ | 71/100 [01:15<00:30, 1.07s/it]\n 72%|███████▏ | 72/100 [01:16<00:29, 1.07s/it]\n 73%|███████▎ | 73/100 [01:17<00:28, 1.06s/it]\n 74%|███████▍ | 74/100 [01:18<00:27, 1.07s/it]\n 75%|███████▌ | 75/100 [01:19<00:26, 1.07s/it]\n 76%|███████▌ | 76/100 [01:20<00:25, 1.07s/it]\n 77%|███████▋ | 77/100 [01:21<00:24, 1.07s/it]\n 78%|███████▊ | 78/100 [01:22<00:23, 1.07s/it]\n 79%|███████▉ | 79/100 [01:23<00:22, 1.07s/it]\n 80%|████████ | 80/100 [01:24<00:21, 1.07s/it]\n 81%|████████ | 81/100 [01:26<00:20, 1.07s/it]\n 82%|████████▏ | 82/100 [01:27<00:19, 1.07s/it]\n 83%|████████▎ | 83/100 [01:28<00:18, 1.07s/it]\n 84%|████████▍ | 84/100 [01:29<00:17, 1.07s/it]\n 85%|████████▌ | 85/100 [01:30<00:16, 1.07s/it]\n 86%|████████▌ | 86/100 [01:31<00:14, 1.07s/it]\n 87%|████████▋ | 87/100 [01:32<00:13, 1.07s/it]\n 88%|████████▊ | 88/100 [01:33<00:12, 1.07s/it]\n 89%|████████▉ | 89/100 [01:34<00:11, 1.07s/it]\n 90%|█████████ | 90/100 [01:35<00:10, 1.07s/it]\n 91%|█████████ | 91/100 [01:36<00:09, 1.07s/it]\n 92%|█████████▏| 92/100 [01:37<00:08, 1.07s/it]\n 93%|█████████▎| 93/100 [01:38<00:07, 1.07s/it]\n 94%|█████████▍| 94/100 [01:39<00:06, 1.07s/it]\n 95%|█████████▌| 95/100 [01:41<00:05, 1.07s/it]\n 96%|█████████▌| 96/100 [01:42<00:04, 1.07s/it]\n 97%|█████████▋| 97/100 [01:43<00:03, 1.07s/it]\n 98%|█████████▊| 98/100 [01:44<00:02, 1.07s/it]\n 99%|█████████▉| 99/100 [01:45<00:01, 1.07s/it]\n100%|██████████| 100/100 [01:46<00:00, 1.07s/it]\n100%|██████████| 100/100 [01:46<00:00, 1.06s/it]", "metrics": { "predict_time": 114.451735, "total_time": 119.037172 }, "output": [ "https://replicate.delivery/pbxt/WFuBphD8vnoMDhEOzpxKmtomTHMPPD1rJldkXBfe2KY7Cu9RA/out-0.png", "https://replicate.delivery/pbxt/DQxxr3lyfV1eYUQVQRfLmac8k8tipQifjOLMT9Cj5b5zL42HB/out-1.png", "https://replicate.delivery/pbxt/JPWR0eswsPxlGqqEmzSee9iU7GH9lZHjfTtHFU8OiYq0L42HB/out-2.png", "https://replicate.delivery/pbxt/aR6jbiDjegQrPiJZp4XI7R0UBx8fbewsLte4AkojTlq3L42HB/out-3.png" ], "started_at": "2023-12-01T00:52:27.700376Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/4zsvxhdbqdoshyut27tpaqtnoq", "cancel": "https://api.replicate.com/v1/predictions/4zsvxhdbqdoshyut27tpaqtnoq/cancel" }, "version": "ab2d9e1e870b835b3a61b2dca3c631005a73ce1e54eb4e79e7e60ba5289d99ad" }Generated inUsing seed: 57566 Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: in the style of <s0><s1>, a digital sketch of portrait of a boy taking a picture, blue hue, closeup txt2img mode 0%| | 0/100 [00:00<?, ?it/s] 1%| | 1/100 [00:01<01:44, 1.05s/it] 2%|▏ | 2/100 [00:02<01:42, 1.05s/it] 3%|▎ | 3/100 [00:03<01:41, 1.05s/it] 4%|▍ | 4/100 [00:04<01:41, 1.05s/it] 5%|▌ | 5/100 [00:05<01:40, 1.05s/it] 6%|▌ | 6/100 [00:06<01:39, 1.06s/it] 7%|▋ | 7/100 [00:07<01:38, 1.06s/it] 8%|▊ | 8/100 [00:08<01:37, 1.06s/it] 9%|▉ | 9/100 [00:09<01:36, 1.06s/it] 10%|█ | 10/100 [00:10<01:35, 1.06s/it] 11%|█ | 11/100 [00:11<01:34, 1.06s/it] 12%|█▏ | 12/100 [00:12<01:32, 1.06s/it] 13%|█▎ | 13/100 [00:13<01:31, 1.06s/it] 14%|█▍ | 14/100 [00:14<01:30, 1.06s/it] 15%|█▌ | 15/100 [00:15<01:29, 1.06s/it] 16%|█▌ | 16/100 [00:16<01:28, 1.06s/it] 17%|█▋ | 17/100 [00:17<01:27, 1.06s/it] 18%|█▊ | 18/100 [00:19<01:26, 1.06s/it] 19%|█▉ | 19/100 [00:20<01:25, 1.06s/it] 20%|██ | 20/100 [00:21<01:24, 1.06s/it] 21%|██ | 21/100 [00:22<01:23, 1.06s/it] 22%|██▏ | 22/100 [00:23<01:22, 1.06s/it] 23%|██▎ | 23/100 [00:24<01:21, 1.06s/it] 24%|██▍ | 24/100 [00:25<01:20, 1.06s/it] 25%|██▌ | 25/100 [00:26<01:19, 1.06s/it] 26%|██▌ | 26/100 [00:27<01:18, 1.06s/it] 27%|██▋ | 27/100 [00:28<01:17, 1.06s/it] 28%|██▊ | 28/100 [00:29<01:16, 1.06s/it] 29%|██▉ | 29/100 [00:30<01:15, 1.06s/it] 30%|███ | 30/100 [00:31<01:14, 1.06s/it] 31%|███ | 31/100 [00:32<01:13, 1.06s/it] 32%|███▏ | 32/100 [00:33<01:12, 1.06s/it] 33%|███▎ | 33/100 [00:34<01:11, 1.06s/it] 34%|███▍ | 34/100 [00:36<01:10, 1.06s/it] 35%|███▌ | 35/100 [00:37<01:09, 1.06s/it] 36%|███▌ | 36/100 [00:38<01:08, 1.06s/it] 37%|███▋ | 37/100 [00:39<01:06, 1.06s/it] 38%|███▊ | 38/100 [00:40<01:05, 1.06s/it] 39%|███▉ | 39/100 [00:41<01:04, 1.06s/it] 40%|████ | 40/100 [00:42<01:03, 1.06s/it] 41%|████ | 41/100 [00:43<01:02, 1.06s/it] 42%|████▏ | 42/100 [00:44<01:01, 1.06s/it] 43%|████▎ | 43/100 [00:45<01:00, 1.06s/it] 44%|████▍ | 44/100 [00:46<00:59, 1.06s/it] 45%|████▌ | 45/100 [00:47<00:58, 1.06s/it] 46%|████▌ | 46/100 [00:48<00:57, 1.07s/it] 47%|████▋ | 47/100 [00:49<00:56, 1.06s/it] 48%|████▊ | 48/100 [00:50<00:55, 1.06s/it] 49%|████▉ | 49/100 [00:51<00:54, 1.06s/it] 50%|█████ | 50/100 [00:53<00:53, 1.06s/it] 51%|█████ | 51/100 [00:54<00:52, 1.06s/it] 52%|█████▏ | 52/100 [00:55<00:51, 1.07s/it] 53%|█████▎ | 53/100 [00:56<00:50, 1.07s/it] 54%|█████▍ | 54/100 [00:57<00:48, 1.06s/it] 55%|█████▌ | 55/100 [00:58<00:47, 1.06s/it] 56%|█████▌ | 56/100 [00:59<00:46, 1.06s/it] 57%|█████▋ | 57/100 [01:00<00:45, 1.06s/it] 58%|█████▊ | 58/100 [01:01<00:44, 1.07s/it] 59%|█████▉ | 59/100 [01:02<00:43, 1.06s/it] 60%|██████ | 60/100 [01:03<00:42, 1.06s/it] 61%|██████ | 61/100 [01:04<00:41, 1.06s/it] 62%|██████▏ | 62/100 [01:05<00:40, 1.07s/it] 63%|██████▎ | 63/100 [01:06<00:39, 1.06s/it] 64%|██████▍ | 64/100 [01:07<00:38, 1.06s/it] 65%|██████▌ | 65/100 [01:08<00:37, 1.06s/it] 66%|██████▌ | 66/100 [01:10<00:36, 1.06s/it] 67%|██████▋ | 67/100 [01:11<00:35, 1.07s/it] 68%|██████▊ | 68/100 [01:12<00:34, 1.07s/it] 69%|██████▉ | 69/100 [01:13<00:33, 1.07s/it] 70%|███████ | 70/100 [01:14<00:32, 1.07s/it] 71%|███████ | 71/100 [01:15<00:30, 1.07s/it] 72%|███████▏ | 72/100 [01:16<00:29, 1.07s/it] 73%|███████▎ | 73/100 [01:17<00:28, 1.06s/it] 74%|███████▍ | 74/100 [01:18<00:27, 1.07s/it] 75%|███████▌ | 75/100 [01:19<00:26, 1.07s/it] 76%|███████▌ | 76/100 [01:20<00:25, 1.07s/it] 77%|███████▋ | 77/100 [01:21<00:24, 1.07s/it] 78%|███████▊ | 78/100 [01:22<00:23, 1.07s/it] 79%|███████▉ | 79/100 [01:23<00:22, 1.07s/it] 80%|████████ | 80/100 [01:24<00:21, 1.07s/it] 81%|████████ | 81/100 [01:26<00:20, 1.07s/it] 82%|████████▏ | 82/100 [01:27<00:19, 1.07s/it] 83%|████████▎ | 83/100 [01:28<00:18, 1.07s/it] 84%|████████▍ | 84/100 [01:29<00:17, 1.07s/it] 85%|████████▌ | 85/100 [01:30<00:16, 1.07s/it] 86%|████████▌ | 86/100 [01:31<00:14, 1.07s/it] 87%|████████▋ | 87/100 [01:32<00:13, 1.07s/it] 88%|████████▊ | 88/100 [01:33<00:12, 1.07s/it] 89%|████████▉ | 89/100 [01:34<00:11, 1.07s/it] 90%|█████████ | 90/100 [01:35<00:10, 1.07s/it] 91%|█████████ | 91/100 [01:36<00:09, 1.07s/it] 92%|█████████▏| 92/100 [01:37<00:08, 1.07s/it] 93%|█████████▎| 93/100 [01:38<00:07, 1.07s/it] 94%|█████████▍| 94/100 [01:39<00:06, 1.07s/it] 95%|█████████▌| 95/100 [01:41<00:05, 1.07s/it] 96%|█████████▌| 96/100 [01:42<00:04, 1.07s/it] 97%|█████████▋| 97/100 [01:43<00:03, 1.07s/it] 98%|█████████▊| 98/100 [01:44<00:02, 1.07s/it] 99%|█████████▉| 99/100 [01:45<00:01, 1.07s/it] 100%|██████████| 100/100 [01:46<00:00, 1.07s/it] 100%|██████████| 100/100 [01:46<00:00, 1.06s/it]
Want to make some of these yourself?
Run this model