brinnaebent / blue-devil
This is a fun demo for the Duke course "Our Complex Relationships with Technology" 2023
- Public
- 20 runs
-
L40S
- SDXL fine-tune
Prediction
brinnaebent/blue-devil:e34b1f01c6c2a9670035b8a5ae1893005395214bda67f71802669c02f76b9f81IDqzlfjgdbov6p63tj5zoolcgh7eStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- a photo of a TOK mascot on a cruise ship
- refine
- no_refiner
- scheduler
- K_EULER
- lora_scale
- 0.6
- num_outputs
- 1
- guidance_scale
- 10
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- prompt_strength
- 0.8
- num_inference_steps
- 100
{ "width": 1024, "height": 1024, "prompt": "a photo of a TOK mascot on a cruise ship", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 10, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "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 brinnaebent/blue-devil using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "brinnaebent/blue-devil:e34b1f01c6c2a9670035b8a5ae1893005395214bda67f71802669c02f76b9f81", { input: { width: 1024, height: 1024, prompt: "a photo of a TOK mascot on a cruise ship", refine: "no_refiner", scheduler: "K_EULER", lora_scale: 0.6, num_outputs: 1, guidance_scale: 10, apply_watermark: true, high_noise_frac: 0.8, negative_prompt: "", 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 brinnaebent/blue-devil using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "brinnaebent/blue-devil:e34b1f01c6c2a9670035b8a5ae1893005395214bda67f71802669c02f76b9f81", input={ "width": 1024, "height": 1024, "prompt": "a photo of a TOK mascot on a cruise ship", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 10, "apply_watermark": True, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 100 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run brinnaebent/blue-devil 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": "brinnaebent/blue-devil:e34b1f01c6c2a9670035b8a5ae1893005395214bda67f71802669c02f76b9f81", "input": { "width": 1024, "height": 1024, "prompt": "a photo of a TOK mascot on a cruise ship", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 10, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "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/brinnaebent/blue-devil@sha256:e34b1f01c6c2a9670035b8a5ae1893005395214bda67f71802669c02f76b9f81 \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="a photo of a TOK mascot on a cruise ship"' \ -i 'refine="no_refiner"' \ -i 'scheduler="K_EULER"' \ -i 'lora_scale=0.6' \ -i 'num_outputs=1' \ -i 'guidance_scale=10' \ -i 'apply_watermark=true' \ -i 'high_noise_frac=0.8' \ -i 'negative_prompt=""' \ -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/brinnaebent/blue-devil@sha256:e34b1f01c6c2a9670035b8a5ae1893005395214bda67f71802669c02f76b9f81curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "a photo of a TOK mascot on a cruise ship", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 10, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 100 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-11-11T20:58:14.720610Z", "created_at": "2023-11-11T20:54:35.657016Z", "data_removed": false, "error": null, "id": "qzlfjgdbov6p63tj5zoolcgh7e", "input": { "width": 1024, "height": 1024, "prompt": "a photo of a TOK mascot on a cruise ship", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 10, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 100 }, "logs": "Using seed: 53682\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: a photo of a <s0><s1> mascot on a cruise ship\ntxt2img mode\n 0%| | 0/100 [00:00<?, ?it/s]\n 1%| | 1/100 [00:00<00:27, 3.65it/s]\n 2%|▏ | 2/100 [00:00<00:26, 3.64it/s]\n 3%|▎ | 3/100 [00:00<00:26, 3.65it/s]\n 4%|▍ | 4/100 [00:01<00:26, 3.65it/s]\n 5%|▌ | 5/100 [00:01<00:26, 3.65it/s]\n 6%|▌ | 6/100 [00:01<00:25, 3.65it/s]\n 7%|▋ | 7/100 [00:01<00:25, 3.65it/s]\n 8%|▊ | 8/100 [00:02<00:25, 3.65it/s]\n 9%|▉ | 9/100 [00:02<00:24, 3.65it/s]\n 10%|█ | 10/100 [00:02<00:24, 3.65it/s]\n 11%|█ | 11/100 [00:03<00:24, 3.65it/s]\n 12%|█▏ | 12/100 [00:03<00:24, 3.65it/s]\n 13%|█▎ | 13/100 [00:03<00:23, 3.65it/s]\n 14%|█▍ | 14/100 [00:03<00:23, 3.65it/s]\n 15%|█▌ | 15/100 [00:04<00:23, 3.64it/s]\n 16%|█▌ | 16/100 [00:04<00:23, 3.64it/s]\n 17%|█▋ | 17/100 [00:04<00:22, 3.64it/s]\n 18%|█▊ | 18/100 [00:04<00:22, 3.64it/s]\n 19%|█▉ | 19/100 [00:05<00:22, 3.63it/s]\n 20%|██ | 20/100 [00:05<00:22, 3.63it/s]\n 21%|██ | 21/100 [00:05<00:21, 3.63it/s]\n 22%|██▏ | 22/100 [00:06<00:21, 3.63it/s]\n 23%|██▎ | 23/100 [00:06<00:21, 3.63it/s]\n 24%|██▍ | 24/100 [00:06<00:20, 3.63it/s]\n 25%|██▌ | 25/100 [00:06<00:20, 3.63it/s]\n 26%|██▌ | 26/100 [00:07<00:20, 3.63it/s]\n 27%|██▋ | 27/100 [00:07<00:20, 3.63it/s]\n 28%|██▊ | 28/100 [00:07<00:19, 3.63it/s]\n 29%|██▉ | 29/100 [00:07<00:19, 3.63it/s]\n 30%|███ | 30/100 [00:08<00:19, 3.63it/s]\n 31%|███ | 31/100 [00:08<00:19, 3.63it/s]\n 32%|███▏ | 32/100 [00:08<00:18, 3.63it/s]\n 33%|███▎ | 33/100 [00:09<00:18, 3.63it/s]\n 34%|███▍ | 34/100 [00:09<00:18, 3.63it/s]\n 35%|███▌ | 35/100 [00:09<00:17, 3.63it/s]\n 36%|███▌ | 36/100 [00:09<00:17, 3.63it/s]\n 37%|███▋ | 37/100 [00:10<00:17, 3.63it/s]\n 38%|███▊ | 38/100 [00:10<00:17, 3.63it/s]\n 39%|███▉ | 39/100 [00:10<00:16, 3.63it/s]\n 40%|████ | 40/100 [00:10<00:16, 3.63it/s]\n 41%|████ | 41/100 [00:11<00:16, 3.63it/s]\n 42%|████▏ | 42/100 [00:11<00:15, 3.63it/s]\n 43%|████▎ | 43/100 [00:11<00:15, 3.63it/s]\n 44%|████▍ | 44/100 [00:12<00:15, 3.63it/s]\n 45%|████▌ | 45/100 [00:12<00:15, 3.63it/s]\n 46%|████▌ | 46/100 [00:12<00:14, 3.63it/s]\n 47%|████▋ | 47/100 [00:12<00:14, 3.62it/s]\n 48%|████▊ | 48/100 [00:13<00:14, 3.63it/s]\n 49%|████▉ | 49/100 [00:13<00:14, 3.63it/s]\n 50%|█████ | 50/100 [00:13<00:13, 3.63it/s]\n 51%|█████ | 51/100 [00:14<00:13, 3.63it/s]\n 52%|█████▏ | 52/100 [00:14<00:13, 3.63it/s]\n 53%|█████▎ | 53/100 [00:14<00:12, 3.63it/s]\n 54%|█████▍ | 54/100 [00:14<00:12, 3.63it/s]\n 55%|█████▌ | 55/100 [00:15<00:12, 3.63it/s]\n 56%|█████▌ | 56/100 [00:15<00:12, 3.63it/s]\n 57%|█████▋ | 57/100 [00:15<00:11, 3.63it/s]\n 58%|█████▊ | 58/100 [00:15<00:11, 3.63it/s]\n 59%|█████▉ | 59/100 [00:16<00:11, 3.63it/s]\n 60%|██████ | 60/100 [00:16<00:11, 3.63it/s]\n 61%|██████ | 61/100 [00:16<00:10, 3.63it/s]\n 62%|██████▏ | 62/100 [00:17<00:10, 3.62it/s]\n 63%|██████▎ | 63/100 [00:17<00:10, 3.63it/s]\n 64%|██████▍ | 64/100 [00:17<00:09, 3.62it/s]\n 65%|██████▌ | 65/100 [00:17<00:09, 3.62it/s]\n 66%|██████▌ | 66/100 [00:18<00:09, 3.62it/s]\n 67%|██████▋ | 67/100 [00:18<00:09, 3.62it/s]\n 68%|██████▊ | 68/100 [00:18<00:08, 3.62it/s]\n 69%|██████▉ | 69/100 [00:18<00:08, 3.63it/s]\n 70%|███████ | 70/100 [00:19<00:08, 3.62it/s]\n 71%|███████ | 71/100 [00:19<00:08, 3.62it/s]\n 72%|███████▏ | 72/100 [00:19<00:07, 3.63it/s]\n 73%|███████▎ | 73/100 [00:20<00:07, 3.62it/s]\n 74%|███████▍ | 74/100 [00:20<00:07, 3.62it/s]\n 75%|███████▌ | 75/100 [00:20<00:06, 3.62it/s]\n 76%|███████▌ | 76/100 [00:20<00:06, 3.62it/s]\n 77%|███████▋ | 77/100 [00:21<00:06, 3.62it/s]\n 78%|███████▊ | 78/100 [00:21<00:06, 3.62it/s]\n 79%|███████▉ | 79/100 [00:21<00:05, 3.62it/s]\n 80%|████████ | 80/100 [00:22<00:05, 3.63it/s]\n 81%|████████ | 81/100 [00:22<00:05, 3.62it/s]\n 82%|████████▏ | 82/100 [00:22<00:04, 3.62it/s]\n 83%|████████▎ | 83/100 [00:22<00:04, 3.62it/s]\n 84%|████████▍ | 84/100 [00:23<00:04, 3.62it/s]\n 85%|████████▌ | 85/100 [00:23<00:04, 3.62it/s]\n 86%|████████▌ | 86/100 [00:23<00:03, 3.62it/s]\n 87%|████████▋ | 87/100 [00:23<00:03, 3.62it/s]\n 88%|████████▊ | 88/100 [00:24<00:03, 3.62it/s]\n 89%|████████▉ | 89/100 [00:24<00:03, 3.62it/s]\n 90%|█████████ | 90/100 [00:24<00:02, 3.62it/s]\n 91%|█████████ | 91/100 [00:25<00:02, 3.62it/s]\n 92%|█████████▏| 92/100 [00:25<00:02, 3.62it/s]\n 93%|█████████▎| 93/100 [00:25<00:01, 3.62it/s]\n 94%|█████████▍| 94/100 [00:25<00:01, 3.62it/s]\n 95%|█████████▌| 95/100 [00:26<00:01, 3.62it/s]\n 96%|█████████▌| 96/100 [00:26<00:01, 3.62it/s]\n 97%|█████████▋| 97/100 [00:26<00:00, 3.62it/s]\n 98%|█████████▊| 98/100 [00:27<00:00, 3.62it/s]\n 99%|█████████▉| 99/100 [00:27<00:00, 3.62it/s]\n100%|██████████| 100/100 [00:27<00:00, 3.62it/s]\n100%|██████████| 100/100 [00:27<00:00, 3.63it/s]", "metrics": { "predict_time": 30.399108, "total_time": 219.063594 }, "output": [ "https://replicate.delivery/pbxt/nrAqJFh4fSxRQKchGib5UtEzPpJ0p4HE1iyPeuHSKcAlzZ3RA/out-0.png" ], "started_at": "2023-11-11T20:57:44.321502Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/qzlfjgdbov6p63tj5zoolcgh7e", "cancel": "https://api.replicate.com/v1/predictions/qzlfjgdbov6p63tj5zoolcgh7e/cancel" }, "version": "e34b1f01c6c2a9670035b8a5ae1893005395214bda67f71802669c02f76b9f81" }Generated inUsing seed: 53682 Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: a photo of a <s0><s1> mascot on a cruise ship txt2img mode 0%| | 0/100 [00:00<?, ?it/s] 1%| | 1/100 [00:00<00:27, 3.65it/s] 2%|▏ | 2/100 [00:00<00:26, 3.64it/s] 3%|▎ | 3/100 [00:00<00:26, 3.65it/s] 4%|▍ | 4/100 [00:01<00:26, 3.65it/s] 5%|▌ | 5/100 [00:01<00:26, 3.65it/s] 6%|▌ | 6/100 [00:01<00:25, 3.65it/s] 7%|▋ | 7/100 [00:01<00:25, 3.65it/s] 8%|▊ | 8/100 [00:02<00:25, 3.65it/s] 9%|▉ | 9/100 [00:02<00:24, 3.65it/s] 10%|█ | 10/100 [00:02<00:24, 3.65it/s] 11%|█ | 11/100 [00:03<00:24, 3.65it/s] 12%|█▏ | 12/100 [00:03<00:24, 3.65it/s] 13%|█▎ | 13/100 [00:03<00:23, 3.65it/s] 14%|█▍ | 14/100 [00:03<00:23, 3.65it/s] 15%|█▌ | 15/100 [00:04<00:23, 3.64it/s] 16%|█▌ | 16/100 [00:04<00:23, 3.64it/s] 17%|█▋ | 17/100 [00:04<00:22, 3.64it/s] 18%|█▊ | 18/100 [00:04<00:22, 3.64it/s] 19%|█▉ | 19/100 [00:05<00:22, 3.63it/s] 20%|██ | 20/100 [00:05<00:22, 3.63it/s] 21%|██ | 21/100 [00:05<00:21, 3.63it/s] 22%|██▏ | 22/100 [00:06<00:21, 3.63it/s] 23%|██▎ | 23/100 [00:06<00:21, 3.63it/s] 24%|██▍ | 24/100 [00:06<00:20, 3.63it/s] 25%|██▌ | 25/100 [00:06<00:20, 3.63it/s] 26%|██▌ | 26/100 [00:07<00:20, 3.63it/s] 27%|██▋ | 27/100 [00:07<00:20, 3.63it/s] 28%|██▊ | 28/100 [00:07<00:19, 3.63it/s] 29%|██▉ | 29/100 [00:07<00:19, 3.63it/s] 30%|███ | 30/100 [00:08<00:19, 3.63it/s] 31%|███ | 31/100 [00:08<00:19, 3.63it/s] 32%|███▏ | 32/100 [00:08<00:18, 3.63it/s] 33%|███▎ | 33/100 [00:09<00:18, 3.63it/s] 34%|███▍ | 34/100 [00:09<00:18, 3.63it/s] 35%|███▌ | 35/100 [00:09<00:17, 3.63it/s] 36%|███▌ | 36/100 [00:09<00:17, 3.63it/s] 37%|███▋ | 37/100 [00:10<00:17, 3.63it/s] 38%|███▊ | 38/100 [00:10<00:17, 3.63it/s] 39%|███▉ | 39/100 [00:10<00:16, 3.63it/s] 40%|████ | 40/100 [00:10<00:16, 3.63it/s] 41%|████ | 41/100 [00:11<00:16, 3.63it/s] 42%|████▏ | 42/100 [00:11<00:15, 3.63it/s] 43%|████▎ | 43/100 [00:11<00:15, 3.63it/s] 44%|████▍ | 44/100 [00:12<00:15, 3.63it/s] 45%|████▌ | 45/100 [00:12<00:15, 3.63it/s] 46%|████▌ | 46/100 [00:12<00:14, 3.63it/s] 47%|████▋ | 47/100 [00:12<00:14, 3.62it/s] 48%|████▊ | 48/100 [00:13<00:14, 3.63it/s] 49%|████▉ | 49/100 [00:13<00:14, 3.63it/s] 50%|█████ | 50/100 [00:13<00:13, 3.63it/s] 51%|█████ | 51/100 [00:14<00:13, 3.63it/s] 52%|█████▏ | 52/100 [00:14<00:13, 3.63it/s] 53%|█████▎ | 53/100 [00:14<00:12, 3.63it/s] 54%|█████▍ | 54/100 [00:14<00:12, 3.63it/s] 55%|█████▌ | 55/100 [00:15<00:12, 3.63it/s] 56%|█████▌ | 56/100 [00:15<00:12, 3.63it/s] 57%|█████▋ | 57/100 [00:15<00:11, 3.63it/s] 58%|█████▊ | 58/100 [00:15<00:11, 3.63it/s] 59%|█████▉ | 59/100 [00:16<00:11, 3.63it/s] 60%|██████ | 60/100 [00:16<00:11, 3.63it/s] 61%|██████ | 61/100 [00:16<00:10, 3.63it/s] 62%|██████▏ | 62/100 [00:17<00:10, 3.62it/s] 63%|██████▎ | 63/100 [00:17<00:10, 3.63it/s] 64%|██████▍ | 64/100 [00:17<00:09, 3.62it/s] 65%|██████▌ | 65/100 [00:17<00:09, 3.62it/s] 66%|██████▌ | 66/100 [00:18<00:09, 3.62it/s] 67%|██████▋ | 67/100 [00:18<00:09, 3.62it/s] 68%|██████▊ | 68/100 [00:18<00:08, 3.62it/s] 69%|██████▉ | 69/100 [00:18<00:08, 3.63it/s] 70%|███████ | 70/100 [00:19<00:08, 3.62it/s] 71%|███████ | 71/100 [00:19<00:08, 3.62it/s] 72%|███████▏ | 72/100 [00:19<00:07, 3.63it/s] 73%|███████▎ | 73/100 [00:20<00:07, 3.62it/s] 74%|███████▍ | 74/100 [00:20<00:07, 3.62it/s] 75%|███████▌ | 75/100 [00:20<00:06, 3.62it/s] 76%|███████▌ | 76/100 [00:20<00:06, 3.62it/s] 77%|███████▋ | 77/100 [00:21<00:06, 3.62it/s] 78%|███████▊ | 78/100 [00:21<00:06, 3.62it/s] 79%|███████▉ | 79/100 [00:21<00:05, 3.62it/s] 80%|████████ | 80/100 [00:22<00:05, 3.63it/s] 81%|████████ | 81/100 [00:22<00:05, 3.62it/s] 82%|████████▏ | 82/100 [00:22<00:04, 3.62it/s] 83%|████████▎ | 83/100 [00:22<00:04, 3.62it/s] 84%|████████▍ | 84/100 [00:23<00:04, 3.62it/s] 85%|████████▌ | 85/100 [00:23<00:04, 3.62it/s] 86%|████████▌ | 86/100 [00:23<00:03, 3.62it/s] 87%|████████▋ | 87/100 [00:23<00:03, 3.62it/s] 88%|████████▊ | 88/100 [00:24<00:03, 3.62it/s] 89%|████████▉ | 89/100 [00:24<00:03, 3.62it/s] 90%|█████████ | 90/100 [00:24<00:02, 3.62it/s] 91%|█████████ | 91/100 [00:25<00:02, 3.62it/s] 92%|█████████▏| 92/100 [00:25<00:02, 3.62it/s] 93%|█████████▎| 93/100 [00:25<00:01, 3.62it/s] 94%|█████████▍| 94/100 [00:25<00:01, 3.62it/s] 95%|█████████▌| 95/100 [00:26<00:01, 3.62it/s] 96%|█████████▌| 96/100 [00:26<00:01, 3.62it/s] 97%|█████████▋| 97/100 [00:26<00:00, 3.62it/s] 98%|█████████▊| 98/100 [00:27<00:00, 3.62it/s] 99%|█████████▉| 99/100 [00:27<00:00, 3.62it/s] 100%|██████████| 100/100 [00:27<00:00, 3.62it/s] 100%|██████████| 100/100 [00:27<00:00, 3.63it/s]Prediction
brinnaebent/blue-devil:e34b1f01c6c2a9670035b8a5ae1893005395214bda67f71802669c02f76b9f81IDbyympxtbinsgbbkuvqnlog5jtaStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- a photo of a TOK mascot by the beach sipping a pina colada
- refine
- no_refiner
- scheduler
- K_EULER
- lora_scale
- 0.6
- num_outputs
- 1
- guidance_scale
- 10
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- prompt_strength
- 0.8
- num_inference_steps
- 100
{ "width": 1024, "height": 1024, "prompt": "a photo of a TOK mascot by the beach sipping a pina colada", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 10, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "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 brinnaebent/blue-devil using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "brinnaebent/blue-devil:e34b1f01c6c2a9670035b8a5ae1893005395214bda67f71802669c02f76b9f81", { input: { width: 1024, height: 1024, prompt: "a photo of a TOK mascot by the beach sipping a pina colada", refine: "no_refiner", scheduler: "K_EULER", lora_scale: 0.6, num_outputs: 1, guidance_scale: 10, apply_watermark: true, high_noise_frac: 0.8, negative_prompt: "", 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 brinnaebent/blue-devil using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "brinnaebent/blue-devil:e34b1f01c6c2a9670035b8a5ae1893005395214bda67f71802669c02f76b9f81", input={ "width": 1024, "height": 1024, "prompt": "a photo of a TOK mascot by the beach sipping a pina colada", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 10, "apply_watermark": True, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 100 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run brinnaebent/blue-devil 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": "brinnaebent/blue-devil:e34b1f01c6c2a9670035b8a5ae1893005395214bda67f71802669c02f76b9f81", "input": { "width": 1024, "height": 1024, "prompt": "a photo of a TOK mascot by the beach sipping a pina colada", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 10, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "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/brinnaebent/blue-devil@sha256:e34b1f01c6c2a9670035b8a5ae1893005395214bda67f71802669c02f76b9f81 \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="a photo of a TOK mascot by the beach sipping a pina colada"' \ -i 'refine="no_refiner"' \ -i 'scheduler="K_EULER"' \ -i 'lora_scale=0.6' \ -i 'num_outputs=1' \ -i 'guidance_scale=10' \ -i 'apply_watermark=true' \ -i 'high_noise_frac=0.8' \ -i 'negative_prompt=""' \ -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/brinnaebent/blue-devil@sha256:e34b1f01c6c2a9670035b8a5ae1893005395214bda67f71802669c02f76b9f81curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "a photo of a TOK mascot by the beach sipping a pina colada", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 10, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 100 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-11-11T20:59:28.490453Z", "created_at": "2023-11-11T20:58:47.745518Z", "data_removed": false, "error": null, "id": "byympxtbinsgbbkuvqnlog5jta", "input": { "width": 1024, "height": 1024, "prompt": "a photo of a TOK mascot by the beach sipping a pina colada", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 10, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 100 }, "logs": "Using seed: 8718\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: a photo of a <s0><s1> mascot by the beach sipping a pina colada\ntxt2img mode\n 0%| | 0/100 [00:00<?, ?it/s]\n 1%| | 1/100 [00:00<00:26, 3.69it/s]\n 2%|▏ | 2/100 [00:00<00:26, 3.68it/s]\n 3%|▎ | 3/100 [00:00<00:26, 3.68it/s]\n 4%|▍ | 4/100 [00:01<00:26, 3.67it/s]\n 5%|▌ | 5/100 [00:01<00:25, 3.67it/s]\n 6%|▌ | 6/100 [00:01<00:25, 3.67it/s]\n 7%|▋ | 7/100 [00:01<00:25, 3.67it/s]\n 8%|▊ | 8/100 [00:02<00:25, 3.66it/s]\n 9%|▉ | 9/100 [00:02<00:24, 3.66it/s]\n 10%|█ | 10/100 [00:02<00:24, 3.66it/s]\n 11%|█ | 11/100 [00:02<00:24, 3.66it/s]\n 12%|█▏ | 12/100 [00:03<00:24, 3.65it/s]\n 13%|█▎ | 13/100 [00:03<00:23, 3.65it/s]\n 14%|█▍ | 14/100 [00:03<00:23, 3.66it/s]\n 15%|█▌ | 15/100 [00:04<00:23, 3.65it/s]\n 16%|█▌ | 16/100 [00:04<00:23, 3.65it/s]\n 17%|█▋ | 17/100 [00:04<00:22, 3.65it/s]\n 18%|█▊ | 18/100 [00:04<00:22, 3.66it/s]\n 19%|█▉ | 19/100 [00:05<00:22, 3.65it/s]\n 20%|██ | 20/100 [00:05<00:21, 3.65it/s]\n 21%|██ | 21/100 [00:05<00:21, 3.65it/s]\n 22%|██▏ | 22/100 [00:06<00:21, 3.65it/s]\n 23%|██▎ | 23/100 [00:06<00:21, 3.65it/s]\n 24%|██▍ | 24/100 [00:06<00:20, 3.65it/s]\n 25%|██▌ | 25/100 [00:06<00:20, 3.65it/s]\n 26%|██▌ | 26/100 [00:07<00:20, 3.65it/s]\n 27%|██▋ | 27/100 [00:07<00:20, 3.65it/s]\n 28%|██▊ | 28/100 [00:07<00:19, 3.64it/s]\n 29%|██▉ | 29/100 [00:07<00:19, 3.64it/s]\n 30%|███ | 30/100 [00:08<00:19, 3.65it/s]\n 31%|███ | 31/100 [00:08<00:18, 3.64it/s]\n 32%|███▏ | 32/100 [00:08<00:18, 3.65it/s]\n 33%|███▎ | 33/100 [00:09<00:18, 3.65it/s]\n 34%|███▍ | 34/100 [00:09<00:18, 3.64it/s]\n 35%|███▌ | 35/100 [00:09<00:17, 3.64it/s]\n 36%|███▌ | 36/100 [00:09<00:17, 3.64it/s]\n 37%|███▋ | 37/100 [00:10<00:17, 3.64it/s]\n 38%|███▊ | 38/100 [00:10<00:17, 3.64it/s]\n 39%|███▉ | 39/100 [00:10<00:16, 3.64it/s]\n 40%|████ | 40/100 [00:10<00:16, 3.64it/s]\n 41%|████ | 41/100 [00:11<00:16, 3.64it/s]\n 42%|████▏ | 42/100 [00:11<00:15, 3.64it/s]\n 43%|████▎ | 43/100 [00:11<00:15, 3.64it/s]\n 44%|████▍ | 44/100 [00:12<00:15, 3.64it/s]\n 45%|████▌ | 45/100 [00:12<00:15, 3.64it/s]\n 46%|████▌ | 46/100 [00:12<00:14, 3.64it/s]\n 47%|████▋ | 47/100 [00:12<00:14, 3.64it/s]\n 48%|████▊ | 48/100 [00:13<00:14, 3.64it/s]\n 49%|████▉ | 49/100 [00:13<00:14, 3.64it/s]\n 50%|█████ | 50/100 [00:13<00:13, 3.64it/s]\n 51%|█████ | 51/100 [00:13<00:13, 3.64it/s]\n 52%|█████▏ | 52/100 [00:14<00:13, 3.64it/s]\n 53%|█████▎ | 53/100 [00:14<00:12, 3.64it/s]\n 54%|█████▍ | 54/100 [00:14<00:12, 3.64it/s]\n 55%|█████▌ | 55/100 [00:15<00:12, 3.64it/s]\n 56%|█████▌ | 56/100 [00:15<00:12, 3.64it/s]\n 57%|█████▋ | 57/100 [00:15<00:11, 3.64it/s]\n 58%|█████▊ | 58/100 [00:15<00:11, 3.64it/s]\n 59%|█████▉ | 59/100 [00:16<00:11, 3.64it/s]\n 60%|██████ | 60/100 [00:16<00:11, 3.64it/s]\n 61%|██████ | 61/100 [00:16<00:10, 3.64it/s]\n 62%|██████▏ | 62/100 [00:16<00:10, 3.64it/s]\n 63%|██████▎ | 63/100 [00:17<00:10, 3.64it/s]\n 64%|██████▍ | 64/100 [00:17<00:09, 3.64it/s]\n 65%|██████▌ | 65/100 [00:17<00:09, 3.64it/s]\n 66%|██████▌ | 66/100 [00:18<00:09, 3.64it/s]\n 67%|██████▋ | 67/100 [00:18<00:09, 3.64it/s]\n 68%|██████▊ | 68/100 [00:18<00:08, 3.64it/s]\n 69%|██████▉ | 69/100 [00:18<00:08, 3.63it/s]\n 70%|███████ | 70/100 [00:19<00:08, 3.64it/s]\n 71%|███████ | 71/100 [00:19<00:07, 3.64it/s]\n 72%|███████▏ | 72/100 [00:19<00:07, 3.64it/s]\n 73%|███████▎ | 73/100 [00:20<00:07, 3.63it/s]\n 74%|███████▍ | 74/100 [00:20<00:07, 3.64it/s]\n 75%|███████▌ | 75/100 [00:20<00:06, 3.63it/s]\n 76%|███████▌ | 76/100 [00:20<00:06, 3.63it/s]\n 77%|███████▋ | 77/100 [00:21<00:06, 3.63it/s]\n 78%|███████▊ | 78/100 [00:21<00:06, 3.64it/s]\n 79%|███████▉ | 79/100 [00:21<00:05, 3.64it/s]\n 80%|████████ | 80/100 [00:21<00:05, 3.63it/s]\n 81%|████████ | 81/100 [00:22<00:05, 3.63it/s]\n 82%|████████▏ | 82/100 [00:22<00:04, 3.63it/s]\n 83%|████████▎ | 83/100 [00:22<00:04, 3.63it/s]\n 84%|████████▍ | 84/100 [00:23<00:04, 3.63it/s]\n 85%|████████▌ | 85/100 [00:23<00:04, 3.63it/s]\n 86%|████████▌ | 86/100 [00:23<00:03, 3.64it/s]\n 87%|████████▋ | 87/100 [00:23<00:03, 3.64it/s]\n 88%|████████▊ | 88/100 [00:24<00:03, 3.63it/s]\n 89%|████████▉ | 89/100 [00:24<00:03, 3.64it/s]\n 90%|█████████ | 90/100 [00:24<00:02, 3.63it/s]\n 91%|█████████ | 91/100 [00:24<00:02, 3.63it/s]\n 92%|█████████▏| 92/100 [00:25<00:02, 3.63it/s]\n 93%|█████████▎| 93/100 [00:25<00:01, 3.63it/s]\n 94%|█████████▍| 94/100 [00:25<00:01, 3.64it/s]\n 95%|█████████▌| 95/100 [00:26<00:01, 3.64it/s]\n 96%|█████████▌| 96/100 [00:26<00:01, 3.63it/s]\n 97%|█████████▋| 97/100 [00:26<00:00, 3.64it/s]\n 98%|█████████▊| 98/100 [00:26<00:00, 3.64it/s]\n 99%|█████████▉| 99/100 [00:27<00:00, 3.64it/s]\n100%|██████████| 100/100 [00:27<00:00, 3.64it/s]\n100%|██████████| 100/100 [00:27<00:00, 3.64it/s]", "metrics": { "predict_time": 30.393602, "total_time": 40.744935 }, "output": [ "https://replicate.delivery/pbxt/9tGUCCjF6QJGOpeH2Us0n92RPeNq5qmTlVSP8kYMk43v0Z3RA/out-0.png" ], "started_at": "2023-11-11T20:58:58.096851Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/byympxtbinsgbbkuvqnlog5jta", "cancel": "https://api.replicate.com/v1/predictions/byympxtbinsgbbkuvqnlog5jta/cancel" }, "version": "e34b1f01c6c2a9670035b8a5ae1893005395214bda67f71802669c02f76b9f81" }Generated inUsing seed: 8718 Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: a photo of a <s0><s1> mascot by the beach sipping a pina colada txt2img mode 0%| | 0/100 [00:00<?, ?it/s] 1%| | 1/100 [00:00<00:26, 3.69it/s] 2%|▏ | 2/100 [00:00<00:26, 3.68it/s] 3%|▎ | 3/100 [00:00<00:26, 3.68it/s] 4%|▍ | 4/100 [00:01<00:26, 3.67it/s] 5%|▌ | 5/100 [00:01<00:25, 3.67it/s] 6%|▌ | 6/100 [00:01<00:25, 3.67it/s] 7%|▋ | 7/100 [00:01<00:25, 3.67it/s] 8%|▊ | 8/100 [00:02<00:25, 3.66it/s] 9%|▉ | 9/100 [00:02<00:24, 3.66it/s] 10%|█ | 10/100 [00:02<00:24, 3.66it/s] 11%|█ | 11/100 [00:02<00:24, 3.66it/s] 12%|█▏ | 12/100 [00:03<00:24, 3.65it/s] 13%|█▎ | 13/100 [00:03<00:23, 3.65it/s] 14%|█▍ | 14/100 [00:03<00:23, 3.66it/s] 15%|█▌ | 15/100 [00:04<00:23, 3.65it/s] 16%|█▌ | 16/100 [00:04<00:23, 3.65it/s] 17%|█▋ | 17/100 [00:04<00:22, 3.65it/s] 18%|█▊ | 18/100 [00:04<00:22, 3.66it/s] 19%|█▉ | 19/100 [00:05<00:22, 3.65it/s] 20%|██ | 20/100 [00:05<00:21, 3.65it/s] 21%|██ | 21/100 [00:05<00:21, 3.65it/s] 22%|██▏ | 22/100 [00:06<00:21, 3.65it/s] 23%|██▎ | 23/100 [00:06<00:21, 3.65it/s] 24%|██▍ | 24/100 [00:06<00:20, 3.65it/s] 25%|██▌ | 25/100 [00:06<00:20, 3.65it/s] 26%|██▌ | 26/100 [00:07<00:20, 3.65it/s] 27%|██▋ | 27/100 [00:07<00:20, 3.65it/s] 28%|██▊ | 28/100 [00:07<00:19, 3.64it/s] 29%|██▉ | 29/100 [00:07<00:19, 3.64it/s] 30%|███ | 30/100 [00:08<00:19, 3.65it/s] 31%|███ | 31/100 [00:08<00:18, 3.64it/s] 32%|███▏ | 32/100 [00:08<00:18, 3.65it/s] 33%|███▎ | 33/100 [00:09<00:18, 3.65it/s] 34%|███▍ | 34/100 [00:09<00:18, 3.64it/s] 35%|███▌ | 35/100 [00:09<00:17, 3.64it/s] 36%|███▌ | 36/100 [00:09<00:17, 3.64it/s] 37%|███▋ | 37/100 [00:10<00:17, 3.64it/s] 38%|███▊ | 38/100 [00:10<00:17, 3.64it/s] 39%|███▉ | 39/100 [00:10<00:16, 3.64it/s] 40%|████ | 40/100 [00:10<00:16, 3.64it/s] 41%|████ | 41/100 [00:11<00:16, 3.64it/s] 42%|████▏ | 42/100 [00:11<00:15, 3.64it/s] 43%|████▎ | 43/100 [00:11<00:15, 3.64it/s] 44%|████▍ | 44/100 [00:12<00:15, 3.64it/s] 45%|████▌ | 45/100 [00:12<00:15, 3.64it/s] 46%|████▌ | 46/100 [00:12<00:14, 3.64it/s] 47%|████▋ | 47/100 [00:12<00:14, 3.64it/s] 48%|████▊ | 48/100 [00:13<00:14, 3.64it/s] 49%|████▉ | 49/100 [00:13<00:14, 3.64it/s] 50%|█████ | 50/100 [00:13<00:13, 3.64it/s] 51%|█████ | 51/100 [00:13<00:13, 3.64it/s] 52%|█████▏ | 52/100 [00:14<00:13, 3.64it/s] 53%|█████▎ | 53/100 [00:14<00:12, 3.64it/s] 54%|█████▍ | 54/100 [00:14<00:12, 3.64it/s] 55%|█████▌ | 55/100 [00:15<00:12, 3.64it/s] 56%|█████▌ | 56/100 [00:15<00:12, 3.64it/s] 57%|█████▋ | 57/100 [00:15<00:11, 3.64it/s] 58%|█████▊ | 58/100 [00:15<00:11, 3.64it/s] 59%|█████▉ | 59/100 [00:16<00:11, 3.64it/s] 60%|██████ | 60/100 [00:16<00:11, 3.64it/s] 61%|██████ | 61/100 [00:16<00:10, 3.64it/s] 62%|██████▏ | 62/100 [00:16<00:10, 3.64it/s] 63%|██████▎ | 63/100 [00:17<00:10, 3.64it/s] 64%|██████▍ | 64/100 [00:17<00:09, 3.64it/s] 65%|██████▌ | 65/100 [00:17<00:09, 3.64it/s] 66%|██████▌ | 66/100 [00:18<00:09, 3.64it/s] 67%|██████▋ | 67/100 [00:18<00:09, 3.64it/s] 68%|██████▊ | 68/100 [00:18<00:08, 3.64it/s] 69%|██████▉ | 69/100 [00:18<00:08, 3.63it/s] 70%|███████ | 70/100 [00:19<00:08, 3.64it/s] 71%|███████ | 71/100 [00:19<00:07, 3.64it/s] 72%|███████▏ | 72/100 [00:19<00:07, 3.64it/s] 73%|███████▎ | 73/100 [00:20<00:07, 3.63it/s] 74%|███████▍ | 74/100 [00:20<00:07, 3.64it/s] 75%|███████▌ | 75/100 [00:20<00:06, 3.63it/s] 76%|███████▌ | 76/100 [00:20<00:06, 3.63it/s] 77%|███████▋ | 77/100 [00:21<00:06, 3.63it/s] 78%|███████▊ | 78/100 [00:21<00:06, 3.64it/s] 79%|███████▉ | 79/100 [00:21<00:05, 3.64it/s] 80%|████████ | 80/100 [00:21<00:05, 3.63it/s] 81%|████████ | 81/100 [00:22<00:05, 3.63it/s] 82%|████████▏ | 82/100 [00:22<00:04, 3.63it/s] 83%|████████▎ | 83/100 [00:22<00:04, 3.63it/s] 84%|████████▍ | 84/100 [00:23<00:04, 3.63it/s] 85%|████████▌ | 85/100 [00:23<00:04, 3.63it/s] 86%|████████▌ | 86/100 [00:23<00:03, 3.64it/s] 87%|████████▋ | 87/100 [00:23<00:03, 3.64it/s] 88%|████████▊ | 88/100 [00:24<00:03, 3.63it/s] 89%|████████▉ | 89/100 [00:24<00:03, 3.64it/s] 90%|█████████ | 90/100 [00:24<00:02, 3.63it/s] 91%|█████████ | 91/100 [00:24<00:02, 3.63it/s] 92%|█████████▏| 92/100 [00:25<00:02, 3.63it/s] 93%|█████████▎| 93/100 [00:25<00:01, 3.63it/s] 94%|█████████▍| 94/100 [00:25<00:01, 3.64it/s] 95%|█████████▌| 95/100 [00:26<00:01, 3.64it/s] 96%|█████████▌| 96/100 [00:26<00:01, 3.63it/s] 97%|█████████▋| 97/100 [00:26<00:00, 3.64it/s] 98%|█████████▊| 98/100 [00:26<00:00, 3.64it/s] 99%|█████████▉| 99/100 [00:27<00:00, 3.64it/s] 100%|██████████| 100/100 [00:27<00:00, 3.64it/s] 100%|██████████| 100/100 [00:27<00:00, 3.64it/s]Prediction
brinnaebent/blue-devil:e34b1f01c6c2a9670035b8a5ae1893005395214bda67f71802669c02f76b9f81IDl4ny3bdbmj7b7zvfkzq4e5ngfqStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- a photo of a TOK mascot taking a selfie in front of the Taj Mahal
- refine
- expert_ensemble_refiner
- scheduler
- K_EULER
- lora_scale
- 0.6
- num_outputs
- 1
- guidance_scale
- 10
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- stadium
- prompt_strength
- 0.9
- num_inference_steps
- 100
{ "width": 1024, "height": 1024, "prompt": "a photo of a TOK mascot taking a selfie in front of the Taj Mahal", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 10, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "stadium", "prompt_strength": 0.9, "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 brinnaebent/blue-devil using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "brinnaebent/blue-devil:e34b1f01c6c2a9670035b8a5ae1893005395214bda67f71802669c02f76b9f81", { input: { width: 1024, height: 1024, prompt: "a photo of a TOK mascot taking a selfie in front of the Taj Mahal", refine: "expert_ensemble_refiner", scheduler: "K_EULER", lora_scale: 0.6, num_outputs: 1, guidance_scale: 10, apply_watermark: true, high_noise_frac: 0.8, negative_prompt: "stadium", prompt_strength: 0.9, 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 brinnaebent/blue-devil using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "brinnaebent/blue-devil:e34b1f01c6c2a9670035b8a5ae1893005395214bda67f71802669c02f76b9f81", input={ "width": 1024, "height": 1024, "prompt": "a photo of a TOK mascot taking a selfie in front of the Taj Mahal", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 10, "apply_watermark": True, "high_noise_frac": 0.8, "negative_prompt": "stadium", "prompt_strength": 0.9, "num_inference_steps": 100 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run brinnaebent/blue-devil 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": "brinnaebent/blue-devil:e34b1f01c6c2a9670035b8a5ae1893005395214bda67f71802669c02f76b9f81", "input": { "width": 1024, "height": 1024, "prompt": "a photo of a TOK mascot taking a selfie in front of the Taj Mahal", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 10, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "stadium", "prompt_strength": 0.9, "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/brinnaebent/blue-devil@sha256:e34b1f01c6c2a9670035b8a5ae1893005395214bda67f71802669c02f76b9f81 \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="a photo of a TOK mascot taking a selfie in front of the Taj Mahal"' \ -i 'refine="expert_ensemble_refiner"' \ -i 'scheduler="K_EULER"' \ -i 'lora_scale=0.6' \ -i 'num_outputs=1' \ -i 'guidance_scale=10' \ -i 'apply_watermark=true' \ -i 'high_noise_frac=0.8' \ -i 'negative_prompt="stadium"' \ -i 'prompt_strength=0.9' \ -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/brinnaebent/blue-devil@sha256:e34b1f01c6c2a9670035b8a5ae1893005395214bda67f71802669c02f76b9f81curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "a photo of a TOK mascot taking a selfie in front of the Taj Mahal", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 10, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "stadium", "prompt_strength": 0.9, "num_inference_steps": 100 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-11-11T21:05:26.113739Z", "created_at": "2023-11-11T21:04:48.557877Z", "data_removed": false, "error": null, "id": "l4ny3bdbmj7b7zvfkzq4e5ngfq", "input": { "width": 1024, "height": 1024, "prompt": "a photo of a TOK mascot taking a selfie in front of the Taj Mahal", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 10, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "stadium", "prompt_strength": 0.9, "num_inference_steps": 100 }, "logs": "Using seed: 21746\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: a photo of a <s0><s1> mascot taking a selfie in front of the Taj Mahal\ntxt2img mode\n 0%| | 0/80 [00:00<?, ?it/s]\n 1%|▏ | 1/80 [00:00<00:21, 3.70it/s]\n 2%|▎ | 2/80 [00:00<00:21, 3.68it/s]\n 4%|▍ | 3/80 [00:00<00:20, 3.68it/s]\n 5%|▌ | 4/80 [00:01<00:20, 3.67it/s]\n 6%|▋ | 5/80 [00:01<00:20, 3.66it/s]\n 8%|▊ | 6/80 [00:01<00:20, 3.67it/s]\n 9%|▉ | 7/80 [00:01<00:19, 3.66it/s]\n 10%|█ | 8/80 [00:02<00:19, 3.66it/s]\n 11%|█▏ | 9/80 [00:02<00:19, 3.66it/s]\n 12%|█▎ | 10/80 [00:02<00:19, 3.66it/s]\n 14%|█▍ | 11/80 [00:03<00:18, 3.66it/s]\n 15%|█▌ | 12/80 [00:03<00:18, 3.66it/s]\n 16%|█▋ | 13/80 [00:03<00:18, 3.67it/s]\n 18%|█▊ | 14/80 [00:03<00:17, 3.67it/s]\n 19%|█▉ | 15/80 [00:04<00:17, 3.67it/s]\n 20%|██ | 16/80 [00:04<00:17, 3.67it/s]\n 21%|██▏ | 17/80 [00:04<00:17, 3.67it/s]\n 22%|██▎ | 18/80 [00:04<00:16, 3.67it/s]\n 24%|██▍ | 19/80 [00:05<00:16, 3.67it/s]\n 25%|██▌ | 20/80 [00:05<00:16, 3.67it/s]\n 26%|██▋ | 21/80 [00:05<00:16, 3.67it/s]\n 28%|██▊ | 22/80 [00:05<00:15, 3.67it/s]\n 29%|██▉ | 23/80 [00:06<00:15, 3.67it/s]\n 30%|███ | 24/80 [00:06<00:15, 3.67it/s]\n 31%|███▏ | 25/80 [00:06<00:14, 3.67it/s]\n 32%|███▎ | 26/80 [00:07<00:14, 3.67it/s]\n 34%|███▍ | 27/80 [00:07<00:14, 3.67it/s]\n 35%|███▌ | 28/80 [00:07<00:14, 3.67it/s]\n 36%|███▋ | 29/80 [00:07<00:13, 3.66it/s]\n 38%|███▊ | 30/80 [00:08<00:13, 3.66it/s]\n 39%|███▉ | 31/80 [00:08<00:13, 3.67it/s]\n 40%|████ | 32/80 [00:08<00:13, 3.67it/s]\n 41%|████▏ | 33/80 [00:08<00:12, 3.66it/s]\n 42%|████▎ | 34/80 [00:09<00:12, 3.66it/s]\n 44%|████▍ | 35/80 [00:09<00:12, 3.67it/s]\n 45%|████▌ | 36/80 [00:09<00:12, 3.66it/s]\n 46%|████▋ | 37/80 [00:10<00:11, 3.66it/s]\n 48%|████▊ | 38/80 [00:10<00:11, 3.66it/s]\n 49%|████▉ | 39/80 [00:10<00:11, 3.66it/s]\n 50%|█████ | 40/80 [00:10<00:10, 3.66it/s]\n 51%|█████▏ | 41/80 [00:11<00:10, 3.66it/s]\n 52%|█████▎ | 42/80 [00:11<00:10, 3.66it/s]\n 54%|█████▍ | 43/80 [00:11<00:10, 3.66it/s]\n 55%|█████▌ | 44/80 [00:12<00:09, 3.66it/s]\n 56%|█████▋ | 45/80 [00:12<00:09, 3.66it/s]\n 57%|█████▊ | 46/80 [00:12<00:09, 3.66it/s]\n 59%|█████▉ | 47/80 [00:12<00:09, 3.66it/s]\n 60%|██████ | 48/80 [00:13<00:08, 3.66it/s]\n 61%|██████▏ | 49/80 [00:13<00:08, 3.66it/s]\n 62%|██████▎ | 50/80 [00:13<00:08, 3.66it/s]\n 64%|██████▍ | 51/80 [00:13<00:07, 3.66it/s]\n 65%|██████▌ | 52/80 [00:14<00:07, 3.66it/s]\n 66%|██████▋ | 53/80 [00:14<00:07, 3.66it/s]\n 68%|██████▊ | 54/80 [00:14<00:07, 3.66it/s]\n 69%|██████▉ | 55/80 [00:15<00:06, 3.66it/s]\n 70%|███████ | 56/80 [00:15<00:06, 3.66it/s]\n 71%|███████▏ | 57/80 [00:15<00:06, 3.66it/s]\n 72%|███████▎ | 58/80 [00:15<00:06, 3.65it/s]\n 74%|███████▍ | 59/80 [00:16<00:05, 3.65it/s]\n 75%|███████▌ | 60/80 [00:16<00:05, 3.65it/s]\n 76%|███████▋ | 61/80 [00:16<00:05, 3.65it/s]\n 78%|███████▊ | 62/80 [00:16<00:04, 3.65it/s]\n 79%|███████▉ | 63/80 [00:17<00:04, 3.65it/s]\n 80%|████████ | 64/80 [00:17<00:04, 3.65it/s]\n 81%|████████▏ | 65/80 [00:17<00:04, 3.65it/s]\n 82%|████████▎ | 66/80 [00:18<00:03, 3.65it/s]\n 84%|████████▍ | 67/80 [00:18<00:03, 3.65it/s]\n 85%|████████▌ | 68/80 [00:18<00:03, 3.65it/s]\n 86%|████████▋ | 69/80 [00:18<00:03, 3.65it/s]\n 88%|████████▊ | 70/80 [00:19<00:02, 3.65it/s]\n 89%|████████▉ | 71/80 [00:19<00:02, 3.65it/s]\n 90%|█████████ | 72/80 [00:19<00:02, 3.65it/s]\n 91%|█████████▏| 73/80 [00:19<00:01, 3.65it/s]\n 92%|█████████▎| 74/80 [00:20<00:01, 3.65it/s]\n 94%|█████████▍| 75/80 [00:20<00:01, 3.65it/s]\n 95%|█████████▌| 76/80 [00:20<00:01, 3.64it/s]\n 96%|█████████▋| 77/80 [00:21<00:00, 3.64it/s]\n 98%|█████████▊| 78/80 [00:21<00:00, 3.64it/s]\n 99%|█████████▉| 79/80 [00:21<00:00, 3.64it/s]\n100%|██████████| 80/80 [00:21<00:00, 3.65it/s]\n100%|██████████| 80/80 [00:21<00:00, 3.66it/s]\n 0%| | 0/20 [00:00<?, ?it/s]\n 5%|▌ | 1/20 [00:00<00:04, 4.06it/s]\n 10%|█ | 2/20 [00:00<00:04, 4.15it/s]\n 15%|█▌ | 3/20 [00:00<00:04, 4.19it/s]\n 20%|██ | 4/20 [00:00<00:03, 4.19it/s]\n 25%|██▌ | 5/20 [00:01<00:03, 4.20it/s]\n 30%|███ | 6/20 [00:01<00:03, 4.21it/s]\n 35%|███▌ | 7/20 [00:01<00:03, 4.21it/s]\n 40%|████ | 8/20 [00:01<00:02, 4.21it/s]\n 45%|████▌ | 9/20 [00:02<00:02, 4.21it/s]\n 50%|█████ | 10/20 [00:02<00:02, 4.21it/s]\n 55%|█████▌ | 11/20 [00:02<00:02, 4.22it/s]\n 60%|██████ | 12/20 [00:02<00:01, 4.21it/s]\n 65%|██████▌ | 13/20 [00:03<00:01, 4.21it/s]\n 70%|███████ | 14/20 [00:03<00:01, 4.21it/s]\n 75%|███████▌ | 15/20 [00:03<00:01, 4.21it/s]\n 80%|████████ | 16/20 [00:03<00:00, 4.20it/s]\n 85%|████████▌ | 17/20 [00:04<00:00, 4.21it/s]\n 90%|█████████ | 18/20 [00:04<00:00, 4.21it/s]\n 95%|█████████▌| 19/20 [00:04<00:00, 4.21it/s]\n100%|██████████| 20/20 [00:04<00:00, 4.22it/s]\n100%|██████████| 20/20 [00:04<00:00, 4.20it/s]", "metrics": { "predict_time": 29.630831, "total_time": 37.555862 }, "output": [ "https://replicate.delivery/pbxt/0P4J058RH8pxO5TOzyqhbFWspYg9ftxTlBS1C3L8HIqK9s7IA/out-0.png" ], "started_at": "2023-11-11T21:04:56.482908Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/l4ny3bdbmj7b7zvfkzq4e5ngfq", "cancel": "https://api.replicate.com/v1/predictions/l4ny3bdbmj7b7zvfkzq4e5ngfq/cancel" }, "version": "e34b1f01c6c2a9670035b8a5ae1893005395214bda67f71802669c02f76b9f81" }Generated inUsing seed: 21746 Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: a photo of a <s0><s1> mascot taking a selfie in front of the Taj Mahal txt2img mode 0%| | 0/80 [00:00<?, ?it/s] 1%|▏ | 1/80 [00:00<00:21, 3.70it/s] 2%|▎ | 2/80 [00:00<00:21, 3.68it/s] 4%|▍ | 3/80 [00:00<00:20, 3.68it/s] 5%|▌ | 4/80 [00:01<00:20, 3.67it/s] 6%|▋ | 5/80 [00:01<00:20, 3.66it/s] 8%|▊ | 6/80 [00:01<00:20, 3.67it/s] 9%|▉ | 7/80 [00:01<00:19, 3.66it/s] 10%|█ | 8/80 [00:02<00:19, 3.66it/s] 11%|█▏ | 9/80 [00:02<00:19, 3.66it/s] 12%|█▎ | 10/80 [00:02<00:19, 3.66it/s] 14%|█▍ | 11/80 [00:03<00:18, 3.66it/s] 15%|█▌ | 12/80 [00:03<00:18, 3.66it/s] 16%|█▋ | 13/80 [00:03<00:18, 3.67it/s] 18%|█▊ | 14/80 [00:03<00:17, 3.67it/s] 19%|█▉ | 15/80 [00:04<00:17, 3.67it/s] 20%|██ | 16/80 [00:04<00:17, 3.67it/s] 21%|██▏ | 17/80 [00:04<00:17, 3.67it/s] 22%|██▎ | 18/80 [00:04<00:16, 3.67it/s] 24%|██▍ | 19/80 [00:05<00:16, 3.67it/s] 25%|██▌ | 20/80 [00:05<00:16, 3.67it/s] 26%|██▋ | 21/80 [00:05<00:16, 3.67it/s] 28%|██▊ | 22/80 [00:05<00:15, 3.67it/s] 29%|██▉ | 23/80 [00:06<00:15, 3.67it/s] 30%|███ | 24/80 [00:06<00:15, 3.67it/s] 31%|███▏ | 25/80 [00:06<00:14, 3.67it/s] 32%|███▎ | 26/80 [00:07<00:14, 3.67it/s] 34%|███▍ | 27/80 [00:07<00:14, 3.67it/s] 35%|███▌ | 28/80 [00:07<00:14, 3.67it/s] 36%|███▋ | 29/80 [00:07<00:13, 3.66it/s] 38%|███▊ | 30/80 [00:08<00:13, 3.66it/s] 39%|███▉ | 31/80 [00:08<00:13, 3.67it/s] 40%|████ | 32/80 [00:08<00:13, 3.67it/s] 41%|████▏ | 33/80 [00:08<00:12, 3.66it/s] 42%|████▎ | 34/80 [00:09<00:12, 3.66it/s] 44%|████▍ | 35/80 [00:09<00:12, 3.67it/s] 45%|████▌ | 36/80 [00:09<00:12, 3.66it/s] 46%|████▋ | 37/80 [00:10<00:11, 3.66it/s] 48%|████▊ | 38/80 [00:10<00:11, 3.66it/s] 49%|████▉ | 39/80 [00:10<00:11, 3.66it/s] 50%|█████ | 40/80 [00:10<00:10, 3.66it/s] 51%|█████▏ | 41/80 [00:11<00:10, 3.66it/s] 52%|█████▎ | 42/80 [00:11<00:10, 3.66it/s] 54%|█████▍ | 43/80 [00:11<00:10, 3.66it/s] 55%|█████▌ | 44/80 [00:12<00:09, 3.66it/s] 56%|█████▋ | 45/80 [00:12<00:09, 3.66it/s] 57%|█████▊ | 46/80 [00:12<00:09, 3.66it/s] 59%|█████▉ | 47/80 [00:12<00:09, 3.66it/s] 60%|██████ | 48/80 [00:13<00:08, 3.66it/s] 61%|██████▏ | 49/80 [00:13<00:08, 3.66it/s] 62%|██████▎ | 50/80 [00:13<00:08, 3.66it/s] 64%|██████▍ | 51/80 [00:13<00:07, 3.66it/s] 65%|██████▌ | 52/80 [00:14<00:07, 3.66it/s] 66%|██████▋ | 53/80 [00:14<00:07, 3.66it/s] 68%|██████▊ | 54/80 [00:14<00:07, 3.66it/s] 69%|██████▉ | 55/80 [00:15<00:06, 3.66it/s] 70%|███████ | 56/80 [00:15<00:06, 3.66it/s] 71%|███████▏ | 57/80 [00:15<00:06, 3.66it/s] 72%|███████▎ | 58/80 [00:15<00:06, 3.65it/s] 74%|███████▍ | 59/80 [00:16<00:05, 3.65it/s] 75%|███████▌ | 60/80 [00:16<00:05, 3.65it/s] 76%|███████▋ | 61/80 [00:16<00:05, 3.65it/s] 78%|███████▊ | 62/80 [00:16<00:04, 3.65it/s] 79%|███████▉ | 63/80 [00:17<00:04, 3.65it/s] 80%|████████ | 64/80 [00:17<00:04, 3.65it/s] 81%|████████▏ | 65/80 [00:17<00:04, 3.65it/s] 82%|████████▎ | 66/80 [00:18<00:03, 3.65it/s] 84%|████████▍ | 67/80 [00:18<00:03, 3.65it/s] 85%|████████▌ | 68/80 [00:18<00:03, 3.65it/s] 86%|████████▋ | 69/80 [00:18<00:03, 3.65it/s] 88%|████████▊ | 70/80 [00:19<00:02, 3.65it/s] 89%|████████▉ | 71/80 [00:19<00:02, 3.65it/s] 90%|█████████ | 72/80 [00:19<00:02, 3.65it/s] 91%|█████████▏| 73/80 [00:19<00:01, 3.65it/s] 92%|█████████▎| 74/80 [00:20<00:01, 3.65it/s] 94%|█████████▍| 75/80 [00:20<00:01, 3.65it/s] 95%|█████████▌| 76/80 [00:20<00:01, 3.64it/s] 96%|█████████▋| 77/80 [00:21<00:00, 3.64it/s] 98%|█████████▊| 78/80 [00:21<00:00, 3.64it/s] 99%|█████████▉| 79/80 [00:21<00:00, 3.64it/s] 100%|██████████| 80/80 [00:21<00:00, 3.65it/s] 100%|██████████| 80/80 [00:21<00:00, 3.66it/s] 0%| | 0/20 [00:00<?, ?it/s] 5%|▌ | 1/20 [00:00<00:04, 4.06it/s] 10%|█ | 2/20 [00:00<00:04, 4.15it/s] 15%|█▌ | 3/20 [00:00<00:04, 4.19it/s] 20%|██ | 4/20 [00:00<00:03, 4.19it/s] 25%|██▌ | 5/20 [00:01<00:03, 4.20it/s] 30%|███ | 6/20 [00:01<00:03, 4.21it/s] 35%|███▌ | 7/20 [00:01<00:03, 4.21it/s] 40%|████ | 8/20 [00:01<00:02, 4.21it/s] 45%|████▌ | 9/20 [00:02<00:02, 4.21it/s] 50%|█████ | 10/20 [00:02<00:02, 4.21it/s] 55%|█████▌ | 11/20 [00:02<00:02, 4.22it/s] 60%|██████ | 12/20 [00:02<00:01, 4.21it/s] 65%|██████▌ | 13/20 [00:03<00:01, 4.21it/s] 70%|███████ | 14/20 [00:03<00:01, 4.21it/s] 75%|███████▌ | 15/20 [00:03<00:01, 4.21it/s] 80%|████████ | 16/20 [00:03<00:00, 4.20it/s] 85%|████████▌ | 17/20 [00:04<00:00, 4.21it/s] 90%|█████████ | 18/20 [00:04<00:00, 4.21it/s] 95%|█████████▌| 19/20 [00:04<00:00, 4.21it/s] 100%|██████████| 20/20 [00:04<00:00, 4.22it/s] 100%|██████████| 20/20 [00:04<00:00, 4.20it/s]Prediction
brinnaebent/blue-devil:e34b1f01c6c2a9670035b8a5ae1893005395214bda67f71802669c02f76b9f81IDv7di6odb5x6ggp2onhngcgijkmStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- a photo of a TOK mascot rock climbing
- refine
- no_refiner
- scheduler
- K_EULER
- lora_scale
- 0.6
- num_outputs
- 1
- guidance_scale
- 10
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- prompt_strength
- 0.8
- num_inference_steps
- 100
{ "width": 1024, "height": 1024, "prompt": "a photo of a TOK mascot rock climbing", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 10, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "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 brinnaebent/blue-devil using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "brinnaebent/blue-devil:e34b1f01c6c2a9670035b8a5ae1893005395214bda67f71802669c02f76b9f81", { input: { width: 1024, height: 1024, prompt: "a photo of a TOK mascot rock climbing", refine: "no_refiner", scheduler: "K_EULER", lora_scale: 0.6, num_outputs: 1, guidance_scale: 10, apply_watermark: true, high_noise_frac: 0.8, negative_prompt: "", 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 brinnaebent/blue-devil using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "brinnaebent/blue-devil:e34b1f01c6c2a9670035b8a5ae1893005395214bda67f71802669c02f76b9f81", input={ "width": 1024, "height": 1024, "prompt": "a photo of a TOK mascot rock climbing", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 10, "apply_watermark": True, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 100 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run brinnaebent/blue-devil 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": "brinnaebent/blue-devil:e34b1f01c6c2a9670035b8a5ae1893005395214bda67f71802669c02f76b9f81", "input": { "width": 1024, "height": 1024, "prompt": "a photo of a TOK mascot rock climbing", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 10, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "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/brinnaebent/blue-devil@sha256:e34b1f01c6c2a9670035b8a5ae1893005395214bda67f71802669c02f76b9f81 \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="a photo of a TOK mascot rock climbing"' \ -i 'refine="no_refiner"' \ -i 'scheduler="K_EULER"' \ -i 'lora_scale=0.6' \ -i 'num_outputs=1' \ -i 'guidance_scale=10' \ -i 'apply_watermark=true' \ -i 'high_noise_frac=0.8' \ -i 'negative_prompt=""' \ -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/brinnaebent/blue-devil@sha256:e34b1f01c6c2a9670035b8a5ae1893005395214bda67f71802669c02f76b9f81curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "a photo of a TOK mascot rock climbing", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 10, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 100 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-11-12T16:13:58.194605Z", "created_at": "2023-11-12T16:12:35.340298Z", "data_removed": false, "error": null, "id": "v7di6odb5x6ggp2onhngcgijkm", "input": { "width": 1024, "height": 1024, "prompt": "a photo of a TOK mascot rock climbing", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 10, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 100 }, "logs": "Using seed: 49019\nEnsuring enough disk space...\nFree disk space: 1781494681600\nDownloading weights: https://replicate.delivery/pbxt/cp1geevnxTmdmEbRZ07dYHGIYIFAh16ct82QnJippkFIeyujA/trained_model.tar\nb'Downloaded 186 MB bytes in 3.479s (54 MB/s)\\nExtracted 186 MB in 0.053s (3.5 GB/s)\\n'\nDownloaded weights in 3.9946088790893555 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: a photo of a <s0><s1> mascot rock climbing\ntxt2img mode\n 0%| | 0/100 [00:00<?, ?it/s]\n 1%| | 1/100 [00:00<00:26, 3.70it/s]\n 2%|▏ | 2/100 [00:00<00:26, 3.68it/s]\n 3%|▎ | 3/100 [00:00<00:26, 3.68it/s]\n 4%|▍ | 4/100 [00:01<00:26, 3.67it/s]\n 5%|▌ | 5/100 [00:01<00:25, 3.67it/s]\n 6%|▌ | 6/100 [00:01<00:25, 3.67it/s]\n 7%|▋ | 7/100 [00:01<00:25, 3.66it/s]\n 8%|▊ | 8/100 [00:02<00:25, 3.67it/s]\n 9%|▉ | 9/100 [00:02<00:24, 3.66it/s]\n 10%|█ | 10/100 [00:02<00:24, 3.66it/s]\n 11%|█ | 11/100 [00:03<00:24, 3.66it/s]\n 12%|█▏ | 12/100 [00:03<00:24, 3.66it/s]\n 13%|█▎ | 13/100 [00:03<00:23, 3.66it/s]\n 14%|█▍ | 14/100 [00:03<00:23, 3.66it/s]\n 15%|█▌ | 15/100 [00:04<00:23, 3.66it/s]\n 16%|█▌ | 16/100 [00:04<00:22, 3.66it/s]\n 17%|█▋ | 17/100 [00:04<00:22, 3.65it/s]\n 18%|█▊ | 18/100 [00:04<00:22, 3.65it/s]\n 19%|█▉ | 19/100 [00:05<00:22, 3.65it/s]\n 20%|██ | 20/100 [00:05<00:21, 3.65it/s]\n 21%|██ | 21/100 [00:05<00:21, 3.65it/s]\n 22%|██▏ | 22/100 [00:06<00:21, 3.65it/s]\n 23%|██▎ | 23/100 [00:06<00:21, 3.65it/s]\n 24%|██▍ | 24/100 [00:06<00:20, 3.65it/s]\n 25%|██▌ | 25/100 [00:06<00:20, 3.65it/s]\n 26%|██▌ | 26/100 [00:07<00:20, 3.65it/s]\n 27%|██▋ | 27/100 [00:07<00:19, 3.65it/s]\n 28%|██▊ | 28/100 [00:07<00:19, 3.65it/s]\n 29%|██▉ | 29/100 [00:07<00:19, 3.64it/s]\n 30%|███ | 30/100 [00:08<00:19, 3.65it/s]\n 31%|███ | 31/100 [00:08<00:18, 3.65it/s]\n 32%|███▏ | 32/100 [00:08<00:18, 3.65it/s]\n 33%|███▎ | 33/100 [00:09<00:18, 3.65it/s]\n 34%|███▍ | 34/100 [00:09<00:18, 3.65it/s]\n 35%|███▌ | 35/100 [00:09<00:17, 3.64it/s]\n 36%|███▌ | 36/100 [00:09<00:17, 3.64it/s]\n 37%|███▋ | 37/100 [00:10<00:17, 3.64it/s]\n 38%|███▊ | 38/100 [00:10<00:17, 3.64it/s]\n 39%|███▉ | 39/100 [00:10<00:16, 3.64it/s]\n 40%|████ | 40/100 [00:10<00:16, 3.64it/s]\n 41%|████ | 41/100 [00:11<00:16, 3.64it/s]\n 42%|████▏ | 42/100 [00:11<00:15, 3.64it/s]\n 43%|████▎ | 43/100 [00:11<00:15, 3.64it/s]\n 44%|████▍ | 44/100 [00:12<00:15, 3.64it/s]\n 45%|████▌ | 45/100 [00:12<00:15, 3.64it/s]\n 46%|████▌ | 46/100 [00:12<00:14, 3.64it/s]\n 47%|████▋ | 47/100 [00:12<00:14, 3.64it/s]\n 48%|████▊ | 48/100 [00:13<00:14, 3.64it/s]\n 49%|████▉ | 49/100 [00:13<00:14, 3.64it/s]\n 50%|█████ | 50/100 [00:13<00:13, 3.64it/s]\n 51%|█████ | 51/100 [00:13<00:13, 3.64it/s]\n 52%|█████▏ | 52/100 [00:14<00:13, 3.64it/s]\n 53%|█████▎ | 53/100 [00:14<00:12, 3.64it/s]\n 54%|█████▍ | 54/100 [00:14<00:12, 3.64it/s]\n 55%|█████▌ | 55/100 [00:15<00:12, 3.64it/s]\n 56%|█████▌ | 56/100 [00:15<00:12, 3.64it/s]\n 57%|█████▋ | 57/100 [00:15<00:11, 3.64it/s]\n 58%|█████▊ | 58/100 [00:15<00:11, 3.63it/s]\n 59%|█████▉ | 59/100 [00:16<00:11, 3.64it/s]\n 60%|██████ | 60/100 [00:16<00:10, 3.64it/s]\n 61%|██████ | 61/100 [00:16<00:10, 3.64it/s]\n 62%|██████▏ | 62/100 [00:16<00:10, 3.63it/s]\n 63%|██████▎ | 63/100 [00:17<00:10, 3.64it/s]\n 64%|██████▍ | 64/100 [00:17<00:09, 3.63it/s]\n 65%|██████▌ | 65/100 [00:17<00:09, 3.63it/s]\n 66%|██████▌ | 66/100 [00:18<00:09, 3.63it/s]\n 67%|██████▋ | 67/100 [00:18<00:09, 3.63it/s]\n 68%|██████▊ | 68/100 [00:18<00:08, 3.64it/s]\n 69%|██████▉ | 69/100 [00:18<00:08, 3.64it/s]\n 70%|███████ | 70/100 [00:19<00:08, 3.64it/s]\n 71%|███████ | 71/100 [00:19<00:07, 3.64it/s]\n 72%|███████▏ | 72/100 [00:19<00:07, 3.64it/s]\n 73%|███████▎ | 73/100 [00:20<00:07, 3.64it/s]\n 74%|███████▍ | 74/100 [00:20<00:07, 3.63it/s]\n 75%|███████▌ | 75/100 [00:20<00:06, 3.64it/s]\n 76%|███████▌ | 76/100 [00:20<00:06, 3.64it/s]\n 77%|███████▋ | 77/100 [00:21<00:06, 3.64it/s]\n 78%|███████▊ | 78/100 [00:21<00:06, 3.64it/s]\n 79%|███████▉ | 79/100 [00:21<00:05, 3.64it/s]\n 80%|████████ | 80/100 [00:21<00:05, 3.64it/s]\n 81%|████████ | 81/100 [00:22<00:05, 3.64it/s]\n 82%|████████▏ | 82/100 [00:22<00:04, 3.64it/s]\n 83%|████████▎ | 83/100 [00:22<00:04, 3.64it/s]\n 84%|████████▍ | 84/100 [00:23<00:04, 3.64it/s]\n 85%|████████▌ | 85/100 [00:23<00:04, 3.64it/s]\n 86%|████████▌ | 86/100 [00:23<00:03, 3.64it/s]\n 87%|████████▋ | 87/100 [00:23<00:03, 3.64it/s]\n 88%|████████▊ | 88/100 [00:24<00:03, 3.64it/s]\n 89%|████████▉ | 89/100 [00:24<00:03, 3.64it/s]\n 90%|█████████ | 90/100 [00:24<00:02, 3.64it/s]\n 91%|█████████ | 91/100 [00:24<00:02, 3.63it/s]\n 92%|█████████▏| 92/100 [00:25<00:02, 3.64it/s]\n 93%|█████████▎| 93/100 [00:25<00:01, 3.64it/s]\n 94%|█████████▍| 94/100 [00:25<00:01, 3.63it/s]\n 95%|█████████▌| 95/100 [00:26<00:01, 3.64it/s]\n 96%|█████████▌| 96/100 [00:26<00:01, 3.63it/s]\n 97%|█████████▋| 97/100 [00:26<00:00, 3.63it/s]\n 98%|█████████▊| 98/100 [00:26<00:00, 3.63it/s]\n 99%|█████████▉| 99/100 [00:27<00:00, 3.64it/s]\n100%|██████████| 100/100 [00:27<00:00, 3.64it/s]\n100%|██████████| 100/100 [00:27<00:00, 3.64it/s]", "metrics": { "predict_time": 34.198933, "total_time": 82.854307 }, "output": [ "https://replicate.delivery/pbxt/pbtlF9cZx25fNyhDiTPcw0lHR9LyYpIeflwlpN45Le2V8qeOC/out-0.png" ], "started_at": "2023-11-12T16:13:23.995672Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/v7di6odb5x6ggp2onhngcgijkm", "cancel": "https://api.replicate.com/v1/predictions/v7di6odb5x6ggp2onhngcgijkm/cancel" }, "version": "e34b1f01c6c2a9670035b8a5ae1893005395214bda67f71802669c02f76b9f81" }Generated inUsing seed: 49019 Ensuring enough disk space... Free disk space: 1781494681600 Downloading weights: https://replicate.delivery/pbxt/cp1geevnxTmdmEbRZ07dYHGIYIFAh16ct82QnJippkFIeyujA/trained_model.tar b'Downloaded 186 MB bytes in 3.479s (54 MB/s)\nExtracted 186 MB in 0.053s (3.5 GB/s)\n' Downloaded weights in 3.9946088790893555 seconds Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: a photo of a <s0><s1> mascot rock climbing txt2img mode 0%| | 0/100 [00:00<?, ?it/s] 1%| | 1/100 [00:00<00:26, 3.70it/s] 2%|▏ | 2/100 [00:00<00:26, 3.68it/s] 3%|▎ | 3/100 [00:00<00:26, 3.68it/s] 4%|▍ | 4/100 [00:01<00:26, 3.67it/s] 5%|▌ | 5/100 [00:01<00:25, 3.67it/s] 6%|▌ | 6/100 [00:01<00:25, 3.67it/s] 7%|▋ | 7/100 [00:01<00:25, 3.66it/s] 8%|▊ | 8/100 [00:02<00:25, 3.67it/s] 9%|▉ | 9/100 [00:02<00:24, 3.66it/s] 10%|█ | 10/100 [00:02<00:24, 3.66it/s] 11%|█ | 11/100 [00:03<00:24, 3.66it/s] 12%|█▏ | 12/100 [00:03<00:24, 3.66it/s] 13%|█▎ | 13/100 [00:03<00:23, 3.66it/s] 14%|█▍ | 14/100 [00:03<00:23, 3.66it/s] 15%|█▌ | 15/100 [00:04<00:23, 3.66it/s] 16%|█▌ | 16/100 [00:04<00:22, 3.66it/s] 17%|█▋ | 17/100 [00:04<00:22, 3.65it/s] 18%|█▊ | 18/100 [00:04<00:22, 3.65it/s] 19%|█▉ | 19/100 [00:05<00:22, 3.65it/s] 20%|██ | 20/100 [00:05<00:21, 3.65it/s] 21%|██ | 21/100 [00:05<00:21, 3.65it/s] 22%|██▏ | 22/100 [00:06<00:21, 3.65it/s] 23%|██▎ | 23/100 [00:06<00:21, 3.65it/s] 24%|██▍ | 24/100 [00:06<00:20, 3.65it/s] 25%|██▌ | 25/100 [00:06<00:20, 3.65it/s] 26%|██▌ | 26/100 [00:07<00:20, 3.65it/s] 27%|██▋ | 27/100 [00:07<00:19, 3.65it/s] 28%|██▊ | 28/100 [00:07<00:19, 3.65it/s] 29%|██▉ | 29/100 [00:07<00:19, 3.64it/s] 30%|███ | 30/100 [00:08<00:19, 3.65it/s] 31%|███ | 31/100 [00:08<00:18, 3.65it/s] 32%|███▏ | 32/100 [00:08<00:18, 3.65it/s] 33%|███▎ | 33/100 [00:09<00:18, 3.65it/s] 34%|███▍ | 34/100 [00:09<00:18, 3.65it/s] 35%|███▌ | 35/100 [00:09<00:17, 3.64it/s] 36%|███▌ | 36/100 [00:09<00:17, 3.64it/s] 37%|███▋ | 37/100 [00:10<00:17, 3.64it/s] 38%|███▊ | 38/100 [00:10<00:17, 3.64it/s] 39%|███▉ | 39/100 [00:10<00:16, 3.64it/s] 40%|████ | 40/100 [00:10<00:16, 3.64it/s] 41%|████ | 41/100 [00:11<00:16, 3.64it/s] 42%|████▏ | 42/100 [00:11<00:15, 3.64it/s] 43%|████▎ | 43/100 [00:11<00:15, 3.64it/s] 44%|████▍ | 44/100 [00:12<00:15, 3.64it/s] 45%|████▌ | 45/100 [00:12<00:15, 3.64it/s] 46%|████▌ | 46/100 [00:12<00:14, 3.64it/s] 47%|████▋ | 47/100 [00:12<00:14, 3.64it/s] 48%|████▊ | 48/100 [00:13<00:14, 3.64it/s] 49%|████▉ | 49/100 [00:13<00:14, 3.64it/s] 50%|█████ | 50/100 [00:13<00:13, 3.64it/s] 51%|█████ | 51/100 [00:13<00:13, 3.64it/s] 52%|█████▏ | 52/100 [00:14<00:13, 3.64it/s] 53%|█████▎ | 53/100 [00:14<00:12, 3.64it/s] 54%|█████▍ | 54/100 [00:14<00:12, 3.64it/s] 55%|█████▌ | 55/100 [00:15<00:12, 3.64it/s] 56%|█████▌ | 56/100 [00:15<00:12, 3.64it/s] 57%|█████▋ | 57/100 [00:15<00:11, 3.64it/s] 58%|█████▊ | 58/100 [00:15<00:11, 3.63it/s] 59%|█████▉ | 59/100 [00:16<00:11, 3.64it/s] 60%|██████ | 60/100 [00:16<00:10, 3.64it/s] 61%|██████ | 61/100 [00:16<00:10, 3.64it/s] 62%|██████▏ | 62/100 [00:16<00:10, 3.63it/s] 63%|██████▎ | 63/100 [00:17<00:10, 3.64it/s] 64%|██████▍ | 64/100 [00:17<00:09, 3.63it/s] 65%|██████▌ | 65/100 [00:17<00:09, 3.63it/s] 66%|██████▌ | 66/100 [00:18<00:09, 3.63it/s] 67%|██████▋ | 67/100 [00:18<00:09, 3.63it/s] 68%|██████▊ | 68/100 [00:18<00:08, 3.64it/s] 69%|██████▉ | 69/100 [00:18<00:08, 3.64it/s] 70%|███████ | 70/100 [00:19<00:08, 3.64it/s] 71%|███████ | 71/100 [00:19<00:07, 3.64it/s] 72%|███████▏ | 72/100 [00:19<00:07, 3.64it/s] 73%|███████▎ | 73/100 [00:20<00:07, 3.64it/s] 74%|███████▍ | 74/100 [00:20<00:07, 3.63it/s] 75%|███████▌ | 75/100 [00:20<00:06, 3.64it/s] 76%|███████▌ | 76/100 [00:20<00:06, 3.64it/s] 77%|███████▋ | 77/100 [00:21<00:06, 3.64it/s] 78%|███████▊ | 78/100 [00:21<00:06, 3.64it/s] 79%|███████▉ | 79/100 [00:21<00:05, 3.64it/s] 80%|████████ | 80/100 [00:21<00:05, 3.64it/s] 81%|████████ | 81/100 [00:22<00:05, 3.64it/s] 82%|████████▏ | 82/100 [00:22<00:04, 3.64it/s] 83%|████████▎ | 83/100 [00:22<00:04, 3.64it/s] 84%|████████▍ | 84/100 [00:23<00:04, 3.64it/s] 85%|████████▌ | 85/100 [00:23<00:04, 3.64it/s] 86%|████████▌ | 86/100 [00:23<00:03, 3.64it/s] 87%|████████▋ | 87/100 [00:23<00:03, 3.64it/s] 88%|████████▊ | 88/100 [00:24<00:03, 3.64it/s] 89%|████████▉ | 89/100 [00:24<00:03, 3.64it/s] 90%|█████████ | 90/100 [00:24<00:02, 3.64it/s] 91%|█████████ | 91/100 [00:24<00:02, 3.63it/s] 92%|█████████▏| 92/100 [00:25<00:02, 3.64it/s] 93%|█████████▎| 93/100 [00:25<00:01, 3.64it/s] 94%|█████████▍| 94/100 [00:25<00:01, 3.63it/s] 95%|█████████▌| 95/100 [00:26<00:01, 3.64it/s] 96%|█████████▌| 96/100 [00:26<00:01, 3.63it/s] 97%|█████████▋| 97/100 [00:26<00:00, 3.63it/s] 98%|█████████▊| 98/100 [00:26<00:00, 3.63it/s] 99%|█████████▉| 99/100 [00:27<00:00, 3.64it/s] 100%|██████████| 100/100 [00:27<00:00, 3.64it/s] 100%|██████████| 100/100 [00:27<00:00, 3.64it/s]
Want to make some of these yourself?
Run this model