datacte/proteus-v0.3

ProteusV0.3: The Anime Update

ProteusV0.1 uses OpenDalleV1.1 as a base and further refines prompt adherence and stylistic capabilities to a measurable degree

Proteus v0.2 shows subtle yet significant improvements over Version 0.1. It demonstrates enhanced prompt understanding that surpasses MJ6, while also approaching its stylistic capabilities.

ProteusV0.4: The Style Update - enhances stylistic capabilities, similar to Midjourney's approach, rather than advancing prompt comprehension

ProteusV0.4: The Style Update

ProteusV0.5 is the latest full release built as a sophisticated enhancement over OpenDalleV1.1

PrometheusV1 is presumed to be the first full rank finetune of Playground v2.5

Flux lora, trained on the unique style and aesthetic of ghibli retro anime

Flux lora, use "1980s anime screengrab", "VHS quality", or "syntheticanime" to trigger image generation

Mobius: Redefining State-of-the-Art in Debiased Diffusion Models
Prediction
datacte/proteus-v0.3:b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48IDvx4zotdbs3bcllpxese2nqnpteStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- Anime full body portrait of a swordsman holding his weapon in front of him. He is facing the camera with a fierce look on his face. Anime key visual (best quality, HD, ~+~aesthetic~+~:1.2)
- scheduler
- DPM++2MSDE
- num_outputs
- 1
- guidance_scale
- 7.5
- apply_watermark
- negative_prompt
- worst quality, low quality
- prompt_strength
- 0.8
- num_inference_steps
- 30
{ "width": 1024, "height": 1024, "prompt": "Anime full body portrait of a swordsman holding his weapon in front of him. He is facing the camera with a fierce look on his face. Anime key visual (best quality, HD, ~+~aesthetic~+~:1.2)", "scheduler": "DPM++2MSDE", "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "negative_prompt": "worst quality, low quality", "prompt_strength": 0.8, "num_inference_steps": 30 }
Install Replicate’s Node.js client library:npm install replicate
Import 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 datacte/proteus-v0.3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "datacte/proteus-v0.3:b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48", { input: { width: 1024, height: 1024, prompt: "Anime full body portrait of a swordsman holding his weapon in front of him. He is facing the camera with a fierce look on his face. Anime key visual (best quality, HD, ~+~aesthetic~+~:1.2)", scheduler: "DPM++2MSDE", num_outputs: 1, guidance_scale: 7.5, apply_watermark: true, negative_prompt: "worst quality, low quality", prompt_strength: 0.8, num_inference_steps: 30 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Import the client:import replicate
Run datacte/proteus-v0.3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "datacte/proteus-v0.3:b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48", input={ "width": 1024, "height": 1024, "prompt": "Anime full body portrait of a swordsman holding his weapon in front of him. He is facing the camera with a fierce look on his face. Anime key visual (best quality, HD, ~+~aesthetic~+~:1.2)", "scheduler": "DPM++2MSDE", "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": True, "negative_prompt": "worst quality, low quality", "prompt_strength": 0.8, "num_inference_steps": 30 } ) # 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 datacte/proteus-v0.3 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": "datacte/proteus-v0.3:b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48", "input": { "width": 1024, "height": 1024, "prompt": "Anime full body portrait of a swordsman holding his weapon in front of him. He is facing the camera with a fierce look on his face. Anime key visual (best quality, HD, ~+~aesthetic~+~:1.2)", "scheduler": "DPM++2MSDE", "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "negative_prompt": "worst quality, low quality", "prompt_strength": 0.8, "num_inference_steps": 30 } }' \ https://api.replicate.com/v1/predictions
To 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 cog
If 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/datacte/proteus-v0.3@sha256:b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48 \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="Anime full body portrait of a swordsman holding his weapon in front of him. He is facing the camera with a fierce look on his face. Anime key visual (best quality, HD, ~+~aesthetic~+~:1.2)"' \ -i 'scheduler="DPM++2MSDE"' \ -i 'num_outputs=1' \ -i 'guidance_scale=7.5' \ -i 'apply_watermark=true' \ -i 'negative_prompt="worst quality, low quality"' \ -i 'prompt_strength=0.8' \ -i 'num_inference_steps=30'
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/datacte/proteus-v0.3@sha256:b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "Anime full body portrait of a swordsman holding his weapon in front of him. He is facing the camera with a fierce look on his face. Anime key visual (best quality, HD, ~+~aesthetic~+~:1.2)", "scheduler": "DPM++2MSDE", "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "negative_prompt": "worst quality, low quality", "prompt_strength": 0.8, "num_inference_steps": 30 } }' \ http://localhost:5000/predictions
To learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2024-02-14T20:05:46.002402Z", "created_at": "2024-02-14T20:03:34.936592Z", "data_removed": false, "error": null, "id": "vx4zotdbs3bcllpxese2nqnpte", "input": { "width": 1024, "height": 1024, "prompt": "Anime full body portrait of a swordsman holding his weapon in front of him. He is facing the camera with a fierce look on his face. Anime key visual (best quality, HD, ~+~aesthetic~+~:1.2)", "scheduler": "DPM++2MSDE", "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "negative_prompt": "worst quality, low quality", "prompt_strength": 0.8, "num_inference_steps": 30 }, "logs": "Using seed: 3937703446\nPrompt: Anime full body portrait of a swordsman holding his weapon in front of him. He is facing the camera with a fierce look on his face. Anime key visual (best quality, HD, ~+~aesthetic~+~:1.2)\ntxt2img mode\n 0%| | 0/30 [00:00<?, ?it/s]\n 3%|▎ | 1/30 [00:00<00:14, 2.05it/s]\n 7%|▋ | 2/30 [00:00<00:12, 2.30it/s]\n 10%|█ | 3/30 [00:01<00:11, 2.38it/s]\n 13%|█▎ | 4/30 [00:01<00:10, 2.42it/s]\n 17%|█▋ | 5/30 [00:02<00:10, 2.45it/s]\n 20%|██ | 6/30 [00:02<00:09, 2.46it/s]\n 23%|██▎ | 7/30 [00:02<00:09, 2.46it/s]\n 27%|██▋ | 8/30 [00:03<00:08, 2.47it/s]\n 30%|███ | 9/30 [00:03<00:08, 2.47it/s]\n 33%|███▎ | 10/30 [00:04<00:08, 2.48it/s]\n 37%|███▋ | 11/30 [00:04<00:07, 2.48it/s]\n 40%|████ | 12/30 [00:04<00:07, 2.48it/s]\n 43%|████▎ | 13/30 [00:05<00:06, 2.48it/s]\n 47%|████▋ | 14/30 [00:05<00:06, 2.48it/s]\n 50%|█████ | 15/30 [00:06<00:06, 2.48it/s]\n 53%|█████▎ | 16/30 [00:06<00:05, 2.48it/s]\n 57%|█████▋ | 17/30 [00:06<00:05, 2.48it/s]\n 60%|██████ | 18/30 [00:07<00:04, 2.48it/s]\n 63%|██████▎ | 19/30 [00:07<00:04, 2.48it/s]\n 67%|██████▋ | 20/30 [00:08<00:04, 2.47it/s]\n 70%|███████ | 21/30 [00:08<00:03, 2.47it/s]\n 73%|███████▎ | 22/30 [00:08<00:03, 2.47it/s]\n 77%|███████▋ | 23/30 [00:09<00:02, 2.47it/s]\n 80%|████████ | 24/30 [00:09<00:02, 2.47it/s]\n 83%|████████▎ | 25/30 [00:10<00:02, 2.47it/s]\n 87%|████████▋ | 26/30 [00:10<00:01, 2.47it/s]\n 90%|█████████ | 27/30 [00:10<00:01, 2.47it/s]\n 93%|█████████▎| 28/30 [00:11<00:00, 2.47it/s]\n 97%|█████████▋| 29/30 [00:11<00:00, 2.47it/s]\n100%|██████████| 30/30 [00:11<00:00, 2.90it/s]\n100%|██████████| 30/30 [00:11<00:00, 2.50it/s]", "metrics": { "predict_time": 14.601853, "total_time": 131.06581 }, "output": [ "https://replicate.delivery/pbxt/YQA6VCqkKV5mAVN7O69zBQfAOtvxoIkSTFJ6dfDoMaaY8sWSA/out-0.png" ], "started_at": "2024-02-14T20:05:31.400549Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/vx4zotdbs3bcllpxese2nqnpte", "cancel": "https://api.replicate.com/v1/predictions/vx4zotdbs3bcllpxese2nqnpte/cancel" }, "version": "b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48" }
Generated inUsing seed: 3937703446 Prompt: Anime full body portrait of a swordsman holding his weapon in front of him. He is facing the camera with a fierce look on his face. Anime key visual (best quality, HD, ~+~aesthetic~+~:1.2) txt2img mode 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:00<00:14, 2.05it/s] 7%|▋ | 2/30 [00:00<00:12, 2.30it/s] 10%|█ | 3/30 [00:01<00:11, 2.38it/s] 13%|█▎ | 4/30 [00:01<00:10, 2.42it/s] 17%|█▋ | 5/30 [00:02<00:10, 2.45it/s] 20%|██ | 6/30 [00:02<00:09, 2.46it/s] 23%|██▎ | 7/30 [00:02<00:09, 2.46it/s] 27%|██▋ | 8/30 [00:03<00:08, 2.47it/s] 30%|███ | 9/30 [00:03<00:08, 2.47it/s] 33%|███▎ | 10/30 [00:04<00:08, 2.48it/s] 37%|███▋ | 11/30 [00:04<00:07, 2.48it/s] 40%|████ | 12/30 [00:04<00:07, 2.48it/s] 43%|████▎ | 13/30 [00:05<00:06, 2.48it/s] 47%|████▋ | 14/30 [00:05<00:06, 2.48it/s] 50%|█████ | 15/30 [00:06<00:06, 2.48it/s] 53%|█████▎ | 16/30 [00:06<00:05, 2.48it/s] 57%|█████▋ | 17/30 [00:06<00:05, 2.48it/s] 60%|██████ | 18/30 [00:07<00:04, 2.48it/s] 63%|██████▎ | 19/30 [00:07<00:04, 2.48it/s] 67%|██████▋ | 20/30 [00:08<00:04, 2.47it/s] 70%|███████ | 21/30 [00:08<00:03, 2.47it/s] 73%|███████▎ | 22/30 [00:08<00:03, 2.47it/s] 77%|███████▋ | 23/30 [00:09<00:02, 2.47it/s] 80%|████████ | 24/30 [00:09<00:02, 2.47it/s] 83%|████████▎ | 25/30 [00:10<00:02, 2.47it/s] 87%|████████▋ | 26/30 [00:10<00:01, 2.47it/s] 90%|█████████ | 27/30 [00:10<00:01, 2.47it/s] 93%|█████████▎| 28/30 [00:11<00:00, 2.47it/s] 97%|█████████▋| 29/30 [00:11<00:00, 2.47it/s] 100%|██████████| 30/30 [00:11<00:00, 2.90it/s] 100%|██████████| 30/30 [00:11<00:00, 2.50it/s]
Prediction
datacte/proteus-v0.3:b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48IDaobq2r3b6m3fvdkaizg6jj77qeStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- spacious,circular underground room,{dirtied white tiles},amalgamation,flesh,plastic,dark fabric,core,pulsating heart,limbs,human-like arms,twisted angelic wings,arms,covered in skin,feathers,scales,undulate slowly,unseen current,convulsing,head area,chaotic,mass of eyes,mouths,no human features,smaller forms,cherubs,demons,golden wires,surround,holy light,tv static effect,golden glow,shadows,terrifying essence,overwhelming presence,nightmarish,landscape,sparse,cavernous,eerie,dynamic,motion,striking,awe-inspiring,nightmarish,nightmarish,nightmare,horrifying,bio-mechanical,body horror,amalgamation
- scheduler
- DPM++2MSDE
- num_outputs
- 1
- guidance_scale
- 7.5
- apply_watermark
- negative_prompt
- nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image
- prompt_strength
- 0.8
- num_inference_steps
- 20
{ "width": 1024, "height": 1024, "prompt": "spacious,circular underground room,{dirtied white tiles},amalgamation,flesh,plastic,dark fabric,core,pulsating heart,limbs,human-like arms,twisted angelic wings,arms,covered in skin,feathers,scales,undulate slowly,unseen current,convulsing,head area,chaotic,mass of eyes,mouths,no human features,smaller forms,cherubs,demons,golden wires,surround,holy light,tv static effect,golden glow,shadows,terrifying essence,overwhelming presence,nightmarish,landscape,sparse,cavernous,eerie,dynamic,motion,striking,awe-inspiring,nightmarish,nightmarish,nightmare,horrifying,bio-mechanical,body horror,amalgamation", "scheduler": "DPM++2MSDE", "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "negative_prompt": "nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image", "prompt_strength": 0.8, "num_inference_steps": 20 }
Install Replicate’s Node.js client library:npm install replicate
Import 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 datacte/proteus-v0.3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "datacte/proteus-v0.3:b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48", { input: { width: 1024, height: 1024, prompt: "spacious,circular underground room,{dirtied white tiles},amalgamation,flesh,plastic,dark fabric,core,pulsating heart,limbs,human-like arms,twisted angelic wings,arms,covered in skin,feathers,scales,undulate slowly,unseen current,convulsing,head area,chaotic,mass of eyes,mouths,no human features,smaller forms,cherubs,demons,golden wires,surround,holy light,tv static effect,golden glow,shadows,terrifying essence,overwhelming presence,nightmarish,landscape,sparse,cavernous,eerie,dynamic,motion,striking,awe-inspiring,nightmarish,nightmarish,nightmare,horrifying,bio-mechanical,body horror,amalgamation", scheduler: "DPM++2MSDE", num_outputs: 1, guidance_scale: 7.5, apply_watermark: true, negative_prompt: "nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image", prompt_strength: 0.8, num_inference_steps: 20 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Import the client:import replicate
Run datacte/proteus-v0.3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "datacte/proteus-v0.3:b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48", input={ "width": 1024, "height": 1024, "prompt": "spacious,circular underground room,{dirtied white tiles},amalgamation,flesh,plastic,dark fabric,core,pulsating heart,limbs,human-like arms,twisted angelic wings,arms,covered in skin,feathers,scales,undulate slowly,unseen current,convulsing,head area,chaotic,mass of eyes,mouths,no human features,smaller forms,cherubs,demons,golden wires,surround,holy light,tv static effect,golden glow,shadows,terrifying essence,overwhelming presence,nightmarish,landscape,sparse,cavernous,eerie,dynamic,motion,striking,awe-inspiring,nightmarish,nightmarish,nightmare,horrifying,bio-mechanical,body horror,amalgamation", "scheduler": "DPM++2MSDE", "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": True, "negative_prompt": "nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image", "prompt_strength": 0.8, "num_inference_steps": 20 } ) # 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 datacte/proteus-v0.3 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": "datacte/proteus-v0.3:b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48", "input": { "width": 1024, "height": 1024, "prompt": "spacious,circular underground room,{dirtied white tiles},amalgamation,flesh,plastic,dark fabric,core,pulsating heart,limbs,human-like arms,twisted angelic wings,arms,covered in skin,feathers,scales,undulate slowly,unseen current,convulsing,head area,chaotic,mass of eyes,mouths,no human features,smaller forms,cherubs,demons,golden wires,surround,holy light,tv static effect,golden glow,shadows,terrifying essence,overwhelming presence,nightmarish,landscape,sparse,cavernous,eerie,dynamic,motion,striking,awe-inspiring,nightmarish,nightmarish,nightmare,horrifying,bio-mechanical,body horror,amalgamation", "scheduler": "DPM++2MSDE", "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "negative_prompt": "nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image", "prompt_strength": 0.8, "num_inference_steps": 20 } }' \ https://api.replicate.com/v1/predictions
To 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 cog
If 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/datacte/proteus-v0.3@sha256:b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48 \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="spacious,circular underground room,{dirtied white tiles},amalgamation,flesh,plastic,dark fabric,core,pulsating heart,limbs,human-like arms,twisted angelic wings,arms,covered in skin,feathers,scales,undulate slowly,unseen current,convulsing,head area,chaotic,mass of eyes,mouths,no human features,smaller forms,cherubs,demons,golden wires,surround,holy light,tv static effect,golden glow,shadows,terrifying essence,overwhelming presence,nightmarish,landscape,sparse,cavernous,eerie,dynamic,motion,striking,awe-inspiring,nightmarish,nightmarish,nightmare,horrifying,bio-mechanical,body horror,amalgamation"' \ -i 'scheduler="DPM++2MSDE"' \ -i 'num_outputs=1' \ -i 'guidance_scale=7.5' \ -i 'apply_watermark=true' \ -i 'negative_prompt="nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image"' \ -i 'prompt_strength=0.8' \ -i 'num_inference_steps=20'
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/datacte/proteus-v0.3@sha256:b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "spacious,circular underground room,{dirtied white tiles},amalgamation,flesh,plastic,dark fabric,core,pulsating heart,limbs,human-like arms,twisted angelic wings,arms,covered in skin,feathers,scales,undulate slowly,unseen current,convulsing,head area,chaotic,mass of eyes,mouths,no human features,smaller forms,cherubs,demons,golden wires,surround,holy light,tv static effect,golden glow,shadows,terrifying essence,overwhelming presence,nightmarish,landscape,sparse,cavernous,eerie,dynamic,motion,striking,awe-inspiring,nightmarish,nightmarish,nightmare,horrifying,bio-mechanical,body horror,amalgamation", "scheduler": "DPM++2MSDE", "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "negative_prompt": "nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image", "prompt_strength": 0.8, "num_inference_steps": 20 } }' \ http://localhost:5000/predictions
To learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2024-02-14T20:09:05.181383Z", "created_at": "2024-02-14T20:08:54.561449Z", "data_removed": false, "error": null, "id": "aobq2r3b6m3fvdkaizg6jj77qe", "input": { "width": 1024, "height": 1024, "prompt": "spacious,circular underground room,{dirtied white tiles},amalgamation,flesh,plastic,dark fabric,core,pulsating heart,limbs,human-like arms,twisted angelic wings,arms,covered in skin,feathers,scales,undulate slowly,unseen current,convulsing,head area,chaotic,mass of eyes,mouths,no human features,smaller forms,cherubs,demons,golden wires,surround,holy light,tv static effect,golden glow,shadows,terrifying essence,overwhelming presence,nightmarish,landscape,sparse,cavernous,eerie,dynamic,motion,striking,awe-inspiring,nightmarish,nightmarish,nightmare,horrifying,bio-mechanical,body horror,amalgamation", "scheduler": "DPM++2MSDE", "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "negative_prompt": "nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image", "prompt_strength": 0.8, "num_inference_steps": 20 }, "logs": "Using seed: 3758746546\nPrompt: spacious,circular underground room,{dirtied white tiles},amalgamation,flesh,plastic,dark fabric,core,pulsating heart,limbs,human-like arms,twisted angelic wings,arms,covered in skin,feathers,scales,undulate slowly,unseen current,convulsing,head area,chaotic,mass of eyes,mouths,no human features,smaller forms,cherubs,demons,golden wires,surround,holy light,tv static effect,golden glow,shadows,terrifying essence,overwhelming presence,nightmarish,landscape,sparse,cavernous,eerie,dynamic,motion,striking,awe-inspiring,nightmarish,nightmarish,nightmare,horrifying,bio-mechanical,body horror,amalgamation\ntxt2img mode\nThe following part of your input was truncated because CLIP can only handle sequences up to 77 tokens: ['no human features, smaller forms, cherubs, demons, golden wires, surround, holy light, tv static effect, golden glow, shadows, terrifying essence, overwhelming presence, nightmarish, landscape, sparse, cavernous, eerie, dynamic, motion, striking, awe - inspiring, nightmarish, nightmarish, nightmare, horrifying, bio - mechanical, body horror, amalgamation']\nThe following part of your input was truncated because CLIP can only handle sequences up to 77 tokens: ['no human features, smaller forms, cherubs, demons, golden wires, surround, holy light, tv static effect, golden glow, shadows, terrifying essence, overwhelming presence, nightmarish, landscape, sparse, cavernous, eerie, dynamic, motion, striking, awe - inspiring, nightmarish, nightmarish, nightmare, horrifying, bio - mechanical, body horror, amalgamation']\n 0%| | 0/20 [00:00<?, ?it/s]\n 5%|▌ | 1/20 [00:00<00:07, 2.48it/s]\n 10%|█ | 2/20 [00:00<00:07, 2.48it/s]\n 15%|█▌ | 3/20 [00:01<00:06, 2.47it/s]\n 20%|██ | 4/20 [00:01<00:06, 2.47it/s]\n 25%|██▌ | 5/20 [00:02<00:06, 2.47it/s]\n 30%|███ | 6/20 [00:02<00:05, 2.47it/s]\n 35%|███▌ | 7/20 [00:02<00:05, 2.47it/s]\n 40%|████ | 8/20 [00:03<00:04, 2.47it/s]\n 45%|████▌ | 9/20 [00:03<00:04, 2.47it/s]\n 50%|█████ | 10/20 [00:04<00:04, 2.47it/s]\n 55%|█████▌ | 11/20 [00:04<00:03, 2.47it/s]\n 60%|██████ | 12/20 [00:04<00:03, 2.47it/s]\n 65%|██████▌ | 13/20 [00:05<00:02, 2.46it/s]\n 70%|███████ | 14/20 [00:05<00:02, 2.46it/s]\n 75%|███████▌ | 15/20 [00:06<00:02, 2.46it/s]\n 80%|████████ | 16/20 [00:06<00:01, 2.46it/s]\n 85%|████████▌ | 17/20 [00:06<00:01, 2.46it/s]\n 90%|█████████ | 18/20 [00:07<00:00, 2.46it/s]\n 95%|█████████▌| 19/20 [00:07<00:00, 2.46it/s]\n100%|██████████| 20/20 [00:07<00:00, 2.89it/s]\n100%|██████████| 20/20 [00:07<00:00, 2.53it/s]", "metrics": { "predict_time": 10.583868, "total_time": 10.619934 }, "output": [ "https://replicate.delivery/pbxt/KLeR6H1freGlaIRwIOOgDaSSJCG3HHeqiaGY4z8RA1T99zaJB/out-0.png" ], "started_at": "2024-02-14T20:08:54.597515Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/aobq2r3b6m3fvdkaizg6jj77qe", "cancel": "https://api.replicate.com/v1/predictions/aobq2r3b6m3fvdkaizg6jj77qe/cancel" }, "version": "b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48" }
Generated inUsing seed: 3758746546 Prompt: spacious,circular underground room,{dirtied white tiles},amalgamation,flesh,plastic,dark fabric,core,pulsating heart,limbs,human-like arms,twisted angelic wings,arms,covered in skin,feathers,scales,undulate slowly,unseen current,convulsing,head area,chaotic,mass of eyes,mouths,no human features,smaller forms,cherubs,demons,golden wires,surround,holy light,tv static effect,golden glow,shadows,terrifying essence,overwhelming presence,nightmarish,landscape,sparse,cavernous,eerie,dynamic,motion,striking,awe-inspiring,nightmarish,nightmarish,nightmare,horrifying,bio-mechanical,body horror,amalgamation txt2img mode The following part of your input was truncated because CLIP can only handle sequences up to 77 tokens: ['no human features, smaller forms, cherubs, demons, golden wires, surround, holy light, tv static effect, golden glow, shadows, terrifying essence, overwhelming presence, nightmarish, landscape, sparse, cavernous, eerie, dynamic, motion, striking, awe - inspiring, nightmarish, nightmarish, nightmare, horrifying, bio - mechanical, body horror, amalgamation'] The following part of your input was truncated because CLIP can only handle sequences up to 77 tokens: ['no human features, smaller forms, cherubs, demons, golden wires, surround, holy light, tv static effect, golden glow, shadows, terrifying essence, overwhelming presence, nightmarish, landscape, sparse, cavernous, eerie, dynamic, motion, striking, awe - inspiring, nightmarish, nightmarish, nightmare, horrifying, bio - mechanical, body horror, amalgamation'] 0%| | 0/20 [00:00<?, ?it/s] 5%|▌ | 1/20 [00:00<00:07, 2.48it/s] 10%|█ | 2/20 [00:00<00:07, 2.48it/s] 15%|█▌ | 3/20 [00:01<00:06, 2.47it/s] 20%|██ | 4/20 [00:01<00:06, 2.47it/s] 25%|██▌ | 5/20 [00:02<00:06, 2.47it/s] 30%|███ | 6/20 [00:02<00:05, 2.47it/s] 35%|███▌ | 7/20 [00:02<00:05, 2.47it/s] 40%|████ | 8/20 [00:03<00:04, 2.47it/s] 45%|████▌ | 9/20 [00:03<00:04, 2.47it/s] 50%|█████ | 10/20 [00:04<00:04, 2.47it/s] 55%|█████▌ | 11/20 [00:04<00:03, 2.47it/s] 60%|██████ | 12/20 [00:04<00:03, 2.47it/s] 65%|██████▌ | 13/20 [00:05<00:02, 2.46it/s] 70%|███████ | 14/20 [00:05<00:02, 2.46it/s] 75%|███████▌ | 15/20 [00:06<00:02, 2.46it/s] 80%|████████ | 16/20 [00:06<00:01, 2.46it/s] 85%|████████▌ | 17/20 [00:06<00:01, 2.46it/s] 90%|█████████ | 18/20 [00:07<00:00, 2.46it/s] 95%|█████████▌| 19/20 [00:07<00:00, 2.46it/s] 100%|██████████| 20/20 [00:07<00:00, 2.89it/s] 100%|██████████| 20/20 [00:07<00:00, 2.53it/s]
Prediction
datacte/proteus-v0.3:b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48IDluizl43btallwanbemwncvmxzaStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- A robot holding a sign saying 'The Application did not respond' in red colors
- scheduler
- DPM++2MSDE
- num_outputs
- 1
- guidance_scale
- 7.5
- apply_watermark
- negative_prompt
- nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image
- prompt_strength
- 0.8
- num_inference_steps
- 30
{ "width": 1024, "height": 1024, "prompt": "A robot holding a sign saying 'The Application did not respond' in red colors", "scheduler": "DPM++2MSDE", "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "negative_prompt": "nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image", "prompt_strength": 0.8, "num_inference_steps": 30 }
Install Replicate’s Node.js client library:npm install replicate
Import 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 datacte/proteus-v0.3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "datacte/proteus-v0.3:b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48", { input: { width: 1024, height: 1024, prompt: "A robot holding a sign saying 'The Application did not respond' in red colors", scheduler: "DPM++2MSDE", num_outputs: 1, guidance_scale: 7.5, apply_watermark: true, negative_prompt: "nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image", prompt_strength: 0.8, num_inference_steps: 30 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Import the client:import replicate
Run datacte/proteus-v0.3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "datacte/proteus-v0.3:b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48", input={ "width": 1024, "height": 1024, "prompt": "A robot holding a sign saying 'The Application did not respond' in red colors", "scheduler": "DPM++2MSDE", "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": True, "negative_prompt": "nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image", "prompt_strength": 0.8, "num_inference_steps": 30 } ) # 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 datacte/proteus-v0.3 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": "datacte/proteus-v0.3:b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48", "input": { "width": 1024, "height": 1024, "prompt": "A robot holding a sign saying \'The Application did not respond\' in red colors", "scheduler": "DPM++2MSDE", "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "negative_prompt": "nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image", "prompt_strength": 0.8, "num_inference_steps": 30 } }' \ https://api.replicate.com/v1/predictions
To 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 cog
If 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/datacte/proteus-v0.3@sha256:b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48 \ -i 'width=1024' \ -i 'height=1024' \ -i $'prompt="A robot holding a sign saying \'The Application did not respond\' in red colors"' \ -i 'scheduler="DPM++2MSDE"' \ -i 'num_outputs=1' \ -i 'guidance_scale=7.5' \ -i 'apply_watermark=true' \ -i 'negative_prompt="nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image"' \ -i 'prompt_strength=0.8' \ -i 'num_inference_steps=30'
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/datacte/proteus-v0.3@sha256:b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "A robot holding a sign saying \'The Application did not respond\' in red colors", "scheduler": "DPM++2MSDE", "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "negative_prompt": "nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image", "prompt_strength": 0.8, "num_inference_steps": 30 } }' \ http://localhost:5000/predictions
To learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2024-02-14T20:13:25.931736Z", "created_at": "2024-02-14T20:13:11.527614Z", "data_removed": false, "error": null, "id": "luizl43btallwanbemwncvmxza", "input": { "width": 1024, "height": 1024, "prompt": "A robot holding a sign saying 'The Application did not respond' in red colors", "scheduler": "DPM++2MSDE", "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "negative_prompt": "nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image", "prompt_strength": 0.8, "num_inference_steps": 30 }, "logs": "Using seed: 3817601993\nPrompt: A robot holding a sign saying 'The Application did not respond' in red colors\ntxt2img mode\n 0%| | 0/30 [00:00<?, ?it/s]\n 3%|▎ | 1/30 [00:00<00:11, 2.48it/s]\n 7%|▋ | 2/30 [00:00<00:11, 2.48it/s]\n 10%|█ | 3/30 [00:01<00:10, 2.47it/s]\n 13%|█▎ | 4/30 [00:01<00:10, 2.47it/s]\n 17%|█▋ | 5/30 [00:02<00:10, 2.47it/s]\n 20%|██ | 6/30 [00:02<00:09, 2.47it/s]\n 23%|██▎ | 7/30 [00:02<00:09, 2.47it/s]\n 27%|██▋ | 8/30 [00:03<00:08, 2.47it/s]\n 30%|███ | 9/30 [00:03<00:08, 2.47it/s]\n 33%|███▎ | 10/30 [00:04<00:08, 2.47it/s]\n 37%|███▋ | 11/30 [00:04<00:07, 2.47it/s]\n 40%|████ | 12/30 [00:04<00:07, 2.47it/s]\n 43%|████▎ | 13/30 [00:05<00:06, 2.46it/s]\n 47%|████▋ | 14/30 [00:05<00:06, 2.46it/s]\n 50%|█████ | 15/30 [00:06<00:06, 2.46it/s]\n 53%|█████▎ | 16/30 [00:06<00:05, 2.46it/s]\n 57%|█████▋ | 17/30 [00:06<00:05, 2.46it/s]\n 60%|██████ | 18/30 [00:07<00:04, 2.46it/s]\n 63%|██████▎ | 19/30 [00:07<00:04, 2.46it/s]\n 67%|██████▋ | 20/30 [00:08<00:04, 2.46it/s]\n 70%|███████ | 21/30 [00:08<00:03, 2.46it/s]\n 73%|███████▎ | 22/30 [00:08<00:03, 2.46it/s]\n 77%|███████▋ | 23/30 [00:09<00:02, 2.46it/s]\n 80%|████████ | 24/30 [00:09<00:02, 2.46it/s]\n 83%|████████▎ | 25/30 [00:10<00:02, 2.46it/s]\n 87%|████████▋ | 26/30 [00:10<00:01, 2.46it/s]\n 90%|█████████ | 27/30 [00:10<00:01, 2.46it/s]\n 93%|█████████▎| 28/30 [00:11<00:00, 2.45it/s]\n 97%|█████████▋| 29/30 [00:11<00:00, 2.45it/s]\n100%|██████████| 30/30 [00:11<00:00, 2.89it/s]\n100%|██████████| 30/30 [00:11<00:00, 2.50it/s]", "metrics": { "predict_time": 14.370009, "total_time": 14.404122 }, "output": [ "https://replicate.delivery/pbxt/OFTWAMyFi4o2NlyeUy0rbUNMCmTl75iOrFNZ9UGVobbyhWLJA/out-0.png" ], "started_at": "2024-02-14T20:13:11.561727Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/luizl43btallwanbemwncvmxza", "cancel": "https://api.replicate.com/v1/predictions/luizl43btallwanbemwncvmxza/cancel" }, "version": "b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48" }
Generated inUsing seed: 3817601993 Prompt: A robot holding a sign saying 'The Application did not respond' in red colors txt2img mode 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:00<00:11, 2.48it/s] 7%|▋ | 2/30 [00:00<00:11, 2.48it/s] 10%|█ | 3/30 [00:01<00:10, 2.47it/s] 13%|█▎ | 4/30 [00:01<00:10, 2.47it/s] 17%|█▋ | 5/30 [00:02<00:10, 2.47it/s] 20%|██ | 6/30 [00:02<00:09, 2.47it/s] 23%|██▎ | 7/30 [00:02<00:09, 2.47it/s] 27%|██▋ | 8/30 [00:03<00:08, 2.47it/s] 30%|███ | 9/30 [00:03<00:08, 2.47it/s] 33%|███▎ | 10/30 [00:04<00:08, 2.47it/s] 37%|███▋ | 11/30 [00:04<00:07, 2.47it/s] 40%|████ | 12/30 [00:04<00:07, 2.47it/s] 43%|████▎ | 13/30 [00:05<00:06, 2.46it/s] 47%|████▋ | 14/30 [00:05<00:06, 2.46it/s] 50%|█████ | 15/30 [00:06<00:06, 2.46it/s] 53%|█████▎ | 16/30 [00:06<00:05, 2.46it/s] 57%|█████▋ | 17/30 [00:06<00:05, 2.46it/s] 60%|██████ | 18/30 [00:07<00:04, 2.46it/s] 63%|██████▎ | 19/30 [00:07<00:04, 2.46it/s] 67%|██████▋ | 20/30 [00:08<00:04, 2.46it/s] 70%|███████ | 21/30 [00:08<00:03, 2.46it/s] 73%|███████▎ | 22/30 [00:08<00:03, 2.46it/s] 77%|███████▋ | 23/30 [00:09<00:02, 2.46it/s] 80%|████████ | 24/30 [00:09<00:02, 2.46it/s] 83%|████████▎ | 25/30 [00:10<00:02, 2.46it/s] 87%|████████▋ | 26/30 [00:10<00:01, 2.46it/s] 90%|█████████ | 27/30 [00:10<00:01, 2.46it/s] 93%|█████████▎| 28/30 [00:11<00:00, 2.45it/s] 97%|█████████▋| 29/30 [00:11<00:00, 2.45it/s] 100%|██████████| 30/30 [00:11<00:00, 2.89it/s] 100%|██████████| 30/30 [00:11<00:00, 2.50it/s]
Prediction
datacte/proteus-v0.3:b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48IDulbmoudbfchn7qmesycscze6riStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- A photograph of Hughyen in his early twenties, (an inspiring artist whose art focuses on glitching images and vaporwave color gradients with unexpected conflicting compositions:0.5)
- scheduler
- DPM++2MSDE
- num_outputs
- 1
- guidance_scale
- 7.5
- apply_watermark
- negative_prompt
- nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image
- prompt_strength
- 0.8
- num_inference_steps
- 30
{ "width": 1024, "height": 1024, "prompt": "A photograph of Hughyen in his early twenties, (an inspiring artist whose art focuses on glitching images and vaporwave color gradients with unexpected conflicting compositions:0.5)", "scheduler": "DPM++2MSDE", "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "negative_prompt": "nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image", "prompt_strength": 0.8, "num_inference_steps": 30 }
Install Replicate’s Node.js client library:npm install replicate
Import 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 datacte/proteus-v0.3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "datacte/proteus-v0.3:b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48", { input: { width: 1024, height: 1024, prompt: "A photograph of Hughyen in his early twenties, (an inspiring artist whose art focuses on glitching images and vaporwave color gradients with unexpected conflicting compositions:0.5)", scheduler: "DPM++2MSDE", num_outputs: 1, guidance_scale: 7.5, apply_watermark: true, negative_prompt: "nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image", prompt_strength: 0.8, num_inference_steps: 30 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Import the client:import replicate
Run datacte/proteus-v0.3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "datacte/proteus-v0.3:b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48", input={ "width": 1024, "height": 1024, "prompt": "A photograph of Hughyen in his early twenties, (an inspiring artist whose art focuses on glitching images and vaporwave color gradients with unexpected conflicting compositions:0.5)", "scheduler": "DPM++2MSDE", "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": True, "negative_prompt": "nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image", "prompt_strength": 0.8, "num_inference_steps": 30 } ) # 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 datacte/proteus-v0.3 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": "datacte/proteus-v0.3:b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48", "input": { "width": 1024, "height": 1024, "prompt": "A photograph of Hughyen in his early twenties, (an inspiring artist whose art focuses on glitching images and vaporwave color gradients with unexpected conflicting compositions:0.5)", "scheduler": "DPM++2MSDE", "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "negative_prompt": "nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image", "prompt_strength": 0.8, "num_inference_steps": 30 } }' \ https://api.replicate.com/v1/predictions
To 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 cog
If 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/datacte/proteus-v0.3@sha256:b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48 \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="A photograph of Hughyen in his early twenties, (an inspiring artist whose art focuses on glitching images and vaporwave color gradients with unexpected conflicting compositions:0.5)"' \ -i 'scheduler="DPM++2MSDE"' \ -i 'num_outputs=1' \ -i 'guidance_scale=7.5' \ -i 'apply_watermark=true' \ -i 'negative_prompt="nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image"' \ -i 'prompt_strength=0.8' \ -i 'num_inference_steps=30'
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/datacte/proteus-v0.3@sha256:b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "A photograph of Hughyen in his early twenties, (an inspiring artist whose art focuses on glitching images and vaporwave color gradients with unexpected conflicting compositions:0.5)", "scheduler": "DPM++2MSDE", "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "negative_prompt": "nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image", "prompt_strength": 0.8, "num_inference_steps": 30 } }' \ http://localhost:5000/predictions
To learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2024-02-14T20:13:59.015368Z", "created_at": "2024-02-14T20:13:44.405207Z", "data_removed": false, "error": null, "id": "ulbmoudbfchn7qmesycscze6ri", "input": { "width": 1024, "height": 1024, "prompt": "A photograph of Hughyen in his early twenties, (an inspiring artist whose art focuses on glitching images and vaporwave color gradients with unexpected conflicting compositions:0.5)", "scheduler": "DPM++2MSDE", "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "negative_prompt": "nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image", "prompt_strength": 0.8, "num_inference_steps": 30 }, "logs": "Using seed: 760119535\nPrompt: A photograph of Hughyen in his early twenties, (an inspiring artist whose art focuses on glitching images and vaporwave color gradients with unexpected conflicting compositions:0.5)\ntxt2img mode\n 0%| | 0/30 [00:00<?, ?it/s]\n 3%|▎ | 1/30 [00:00<00:11, 2.49it/s]\n 7%|▋ | 2/30 [00:00<00:11, 2.48it/s]\n 10%|█ | 3/30 [00:01<00:10, 2.46it/s]\n 13%|█▎ | 4/30 [00:01<00:10, 2.47it/s]\n 17%|█▋ | 5/30 [00:02<00:10, 2.48it/s]\n 20%|██ | 6/30 [00:02<00:09, 2.47it/s]\n 23%|██▎ | 7/30 [00:02<00:09, 2.48it/s]\n 27%|██▋ | 8/30 [00:03<00:08, 2.47it/s]\n 30%|███ | 9/30 [00:03<00:08, 2.47it/s]\n 33%|███▎ | 10/30 [00:04<00:08, 2.47it/s]\n 37%|███▋ | 11/30 [00:04<00:07, 2.47it/s]\n 40%|████ | 12/30 [00:04<00:07, 2.47it/s]\n 43%|████▎ | 13/30 [00:05<00:06, 2.47it/s]\n 47%|████▋ | 14/30 [00:05<00:06, 2.47it/s]\n 50%|█████ | 15/30 [00:06<00:06, 2.47it/s]\n 53%|█████▎ | 16/30 [00:06<00:05, 2.47it/s]\n 57%|█████▋ | 17/30 [00:06<00:05, 2.47it/s]\n 60%|██████ | 18/30 [00:07<00:04, 2.47it/s]\n 63%|██████▎ | 19/30 [00:07<00:04, 2.47it/s]\n 67%|██████▋ | 20/30 [00:08<00:04, 2.47it/s]\n 70%|███████ | 21/30 [00:08<00:03, 2.46it/s]\n 73%|███████▎ | 22/30 [00:08<00:03, 2.46it/s]\n 77%|███████▋ | 23/30 [00:09<00:02, 2.47it/s]\n 80%|████████ | 24/30 [00:09<00:02, 2.47it/s]\n 83%|████████▎ | 25/30 [00:10<00:02, 2.46it/s]\n 87%|████████▋ | 26/30 [00:10<00:01, 2.47it/s]\n 90%|█████████ | 27/30 [00:10<00:01, 2.47it/s]\n 93%|█████████▎| 28/30 [00:11<00:00, 2.46it/s]\n 97%|█████████▋| 29/30 [00:11<00:00, 2.46it/s]\n100%|██████████| 30/30 [00:11<00:00, 2.90it/s]\n100%|██████████| 30/30 [00:11<00:00, 2.51it/s]", "metrics": { "predict_time": 14.571392, "total_time": 14.610161 }, "output": [ "https://replicate.delivery/pbxt/wNNmrQXcTHYRKFGqKDr5pYiQ3BZWJGjvbpzBTUCxQBeCiWLJA/out-0.png" ], "started_at": "2024-02-14T20:13:44.443976Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/ulbmoudbfchn7qmesycscze6ri", "cancel": "https://api.replicate.com/v1/predictions/ulbmoudbfchn7qmesycscze6ri/cancel" }, "version": "b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48" }
Generated inUsing seed: 760119535 Prompt: A photograph of Hughyen in his early twenties, (an inspiring artist whose art focuses on glitching images and vaporwave color gradients with unexpected conflicting compositions:0.5) txt2img mode 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:00<00:11, 2.49it/s] 7%|▋ | 2/30 [00:00<00:11, 2.48it/s] 10%|█ | 3/30 [00:01<00:10, 2.46it/s] 13%|█▎ | 4/30 [00:01<00:10, 2.47it/s] 17%|█▋ | 5/30 [00:02<00:10, 2.48it/s] 20%|██ | 6/30 [00:02<00:09, 2.47it/s] 23%|██▎ | 7/30 [00:02<00:09, 2.48it/s] 27%|██▋ | 8/30 [00:03<00:08, 2.47it/s] 30%|███ | 9/30 [00:03<00:08, 2.47it/s] 33%|███▎ | 10/30 [00:04<00:08, 2.47it/s] 37%|███▋ | 11/30 [00:04<00:07, 2.47it/s] 40%|████ | 12/30 [00:04<00:07, 2.47it/s] 43%|████▎ | 13/30 [00:05<00:06, 2.47it/s] 47%|████▋ | 14/30 [00:05<00:06, 2.47it/s] 50%|█████ | 15/30 [00:06<00:06, 2.47it/s] 53%|█████▎ | 16/30 [00:06<00:05, 2.47it/s] 57%|█████▋ | 17/30 [00:06<00:05, 2.47it/s] 60%|██████ | 18/30 [00:07<00:04, 2.47it/s] 63%|██████▎ | 19/30 [00:07<00:04, 2.47it/s] 67%|██████▋ | 20/30 [00:08<00:04, 2.47it/s] 70%|███████ | 21/30 [00:08<00:03, 2.46it/s] 73%|███████▎ | 22/30 [00:08<00:03, 2.46it/s] 77%|███████▋ | 23/30 [00:09<00:02, 2.47it/s] 80%|████████ | 24/30 [00:09<00:02, 2.47it/s] 83%|████████▎ | 25/30 [00:10<00:02, 2.46it/s] 87%|████████▋ | 26/30 [00:10<00:01, 2.47it/s] 90%|█████████ | 27/30 [00:10<00:01, 2.47it/s] 93%|█████████▎| 28/30 [00:11<00:00, 2.46it/s] 97%|█████████▋| 29/30 [00:11<00:00, 2.46it/s] 100%|██████████| 30/30 [00:11<00:00, 2.90it/s] 100%|██████████| 30/30 [00:11<00:00, 2.51it/s]
Prediction
datacte/proteus-v0.3:b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48IDa27ybytbg6vejw5jujio5dciteStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- Glitch art. 1980s anime, vintage, analogue horror. ((static and noise)), chromatic aberration
- scheduler
- DPM++2MSDE
- num_outputs
- 1
- guidance_scale
- 7.5
- apply_watermark
- negative_prompt
- nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image
- prompt_strength
- 0.8
- num_inference_steps
- 30
{ "width": 1024, "height": 1024, "prompt": "Glitch art. 1980s anime, vintage, analogue horror. ((static and noise)), chromatic aberration", "scheduler": "DPM++2MSDE", "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "negative_prompt": "nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image", "prompt_strength": 0.8, "num_inference_steps": 30 }
Install Replicate’s Node.js client library:npm install replicate
Import 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 datacte/proteus-v0.3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "datacte/proteus-v0.3:b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48", { input: { width: 1024, height: 1024, prompt: "Glitch art. 1980s anime, vintage, analogue horror. ((static and noise)), chromatic aberration", scheduler: "DPM++2MSDE", num_outputs: 1, guidance_scale: 7.5, apply_watermark: true, negative_prompt: "nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image", prompt_strength: 0.8, num_inference_steps: 30 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Import the client:import replicate
Run datacte/proteus-v0.3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "datacte/proteus-v0.3:b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48", input={ "width": 1024, "height": 1024, "prompt": "Glitch art. 1980s anime, vintage, analogue horror. ((static and noise)), chromatic aberration", "scheduler": "DPM++2MSDE", "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": True, "negative_prompt": "nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image", "prompt_strength": 0.8, "num_inference_steps": 30 } ) # 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 datacte/proteus-v0.3 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": "datacte/proteus-v0.3:b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48", "input": { "width": 1024, "height": 1024, "prompt": "Glitch art. 1980s anime, vintage, analogue horror. ((static and noise)), chromatic aberration", "scheduler": "DPM++2MSDE", "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "negative_prompt": "nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image", "prompt_strength": 0.8, "num_inference_steps": 30 } }' \ https://api.replicate.com/v1/predictions
To 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 cog
If 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/datacte/proteus-v0.3@sha256:b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48 \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="Glitch art. 1980s anime, vintage, analogue horror. ((static and noise)), chromatic aberration"' \ -i 'scheduler="DPM++2MSDE"' \ -i 'num_outputs=1' \ -i 'guidance_scale=7.5' \ -i 'apply_watermark=true' \ -i 'negative_prompt="nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image"' \ -i 'prompt_strength=0.8' \ -i 'num_inference_steps=30'
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/datacte/proteus-v0.3@sha256:b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "Glitch art. 1980s anime, vintage, analogue horror. ((static and noise)), chromatic aberration", "scheduler": "DPM++2MSDE", "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "negative_prompt": "nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image", "prompt_strength": 0.8, "num_inference_steps": 30 } }' \ http://localhost:5000/predictions
To learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2024-02-14T20:15:30.928577Z", "created_at": "2024-02-14T20:15:16.084483Z", "data_removed": false, "error": null, "id": "a27ybytbg6vejw5jujio5dcite", "input": { "width": 1024, "height": 1024, "prompt": "Glitch art. 1980s anime, vintage, analogue horror. ((static and noise)), chromatic aberration", "scheduler": "DPM++2MSDE", "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "negative_prompt": "nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image", "prompt_strength": 0.8, "num_inference_steps": 30 }, "logs": "Using seed: 2603207358\nPrompt: Glitch art. 1980s anime, vintage, analogue horror. ((static and noise)), chromatic aberration\ntxt2img mode\n 0%| | 0/30 [00:00<?, ?it/s]\n 3%|▎ | 1/30 [00:00<00:11, 2.51it/s]\n 7%|▋ | 2/30 [00:00<00:11, 2.50it/s]\n 10%|█ | 3/30 [00:01<00:10, 2.48it/s]\n 13%|█▎ | 4/30 [00:01<00:10, 2.48it/s]\n 17%|█▋ | 5/30 [00:02<00:10, 2.48it/s]\n 20%|██ | 6/30 [00:02<00:09, 2.47it/s]\n 23%|██▎ | 7/30 [00:02<00:09, 2.47it/s]\n 27%|██▋ | 8/30 [00:03<00:08, 2.47it/s]\n 30%|███ | 9/30 [00:03<00:08, 2.47it/s]\n 33%|███▎ | 10/30 [00:04<00:08, 2.47it/s]\n 37%|███▋ | 11/30 [00:04<00:07, 2.47it/s]\n 40%|████ | 12/30 [00:04<00:07, 2.47it/s]\n 43%|████▎ | 13/30 [00:05<00:06, 2.47it/s]\n 47%|████▋ | 14/30 [00:05<00:06, 2.47it/s]\n 50%|█████ | 15/30 [00:06<00:06, 2.46it/s]\n 53%|█████▎ | 16/30 [00:06<00:05, 2.46it/s]\n 57%|█████▋ | 17/30 [00:06<00:05, 2.46it/s]\n 60%|██████ | 18/30 [00:07<00:04, 2.46it/s]\n 63%|██████▎ | 19/30 [00:07<00:04, 2.46it/s]\n 67%|██████▋ | 20/30 [00:08<00:04, 2.46it/s]\n 70%|███████ | 21/30 [00:08<00:03, 2.46it/s]\n 73%|███████▎ | 22/30 [00:08<00:03, 2.46it/s]\n 77%|███████▋ | 23/30 [00:09<00:02, 2.46it/s]\n 80%|████████ | 24/30 [00:09<00:02, 2.46it/s]\n 83%|████████▎ | 25/30 [00:10<00:02, 2.46it/s]\n 87%|████████▋ | 26/30 [00:10<00:01, 2.46it/s]\n 90%|█████████ | 27/30 [00:10<00:01, 2.46it/s]\n 93%|█████████▎| 28/30 [00:11<00:00, 2.46it/s]\n 97%|█████████▋| 29/30 [00:11<00:00, 2.45it/s]\n100%|██████████| 30/30 [00:11<00:00, 2.89it/s]\n100%|██████████| 30/30 [00:11<00:00, 2.51it/s]", "metrics": { "predict_time": 14.809923, "total_time": 14.844094 }, "output": [ "https://replicate.delivery/pbxt/ZQbJiK3yDiKoOpHwE7ytoFNjMZXaKCLfYQaU7FU4UWowiWLJA/out-0.png" ], "started_at": "2024-02-14T20:15:16.118654Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/a27ybytbg6vejw5jujio5dcite", "cancel": "https://api.replicate.com/v1/predictions/a27ybytbg6vejw5jujio5dcite/cancel" }, "version": "b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48" }
Generated inUsing seed: 2603207358 Prompt: Glitch art. 1980s anime, vintage, analogue horror. ((static and noise)), chromatic aberration txt2img mode 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:00<00:11, 2.51it/s] 7%|▋ | 2/30 [00:00<00:11, 2.50it/s] 10%|█ | 3/30 [00:01<00:10, 2.48it/s] 13%|█▎ | 4/30 [00:01<00:10, 2.48it/s] 17%|█▋ | 5/30 [00:02<00:10, 2.48it/s] 20%|██ | 6/30 [00:02<00:09, 2.47it/s] 23%|██▎ | 7/30 [00:02<00:09, 2.47it/s] 27%|██▋ | 8/30 [00:03<00:08, 2.47it/s] 30%|███ | 9/30 [00:03<00:08, 2.47it/s] 33%|███▎ | 10/30 [00:04<00:08, 2.47it/s] 37%|███▋ | 11/30 [00:04<00:07, 2.47it/s] 40%|████ | 12/30 [00:04<00:07, 2.47it/s] 43%|████▎ | 13/30 [00:05<00:06, 2.47it/s] 47%|████▋ | 14/30 [00:05<00:06, 2.47it/s] 50%|█████ | 15/30 [00:06<00:06, 2.46it/s] 53%|█████▎ | 16/30 [00:06<00:05, 2.46it/s] 57%|█████▋ | 17/30 [00:06<00:05, 2.46it/s] 60%|██████ | 18/30 [00:07<00:04, 2.46it/s] 63%|██████▎ | 19/30 [00:07<00:04, 2.46it/s] 67%|██████▋ | 20/30 [00:08<00:04, 2.46it/s] 70%|███████ | 21/30 [00:08<00:03, 2.46it/s] 73%|███████▎ | 22/30 [00:08<00:03, 2.46it/s] 77%|███████▋ | 23/30 [00:09<00:02, 2.46it/s] 80%|████████ | 24/30 [00:09<00:02, 2.46it/s] 83%|████████▎ | 25/30 [00:10<00:02, 2.46it/s] 87%|████████▋ | 26/30 [00:10<00:01, 2.46it/s] 90%|█████████ | 27/30 [00:10<00:01, 2.46it/s] 93%|█████████▎| 28/30 [00:11<00:00, 2.46it/s] 97%|█████████▋| 29/30 [00:11<00:00, 2.45it/s] 100%|██████████| 30/30 [00:11<00:00, 2.89it/s] 100%|██████████| 30/30 [00:11<00:00, 2.51it/s]
Prediction
datacte/proteus-v0.3:b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48IDjfskdbdbmalwtxrty3rmtlbyhyStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- Masterpiece, glitch, holy holy holy, fog, by DarkIncursio
- scheduler
- DPM++2MSDE
- num_outputs
- 1
- guidance_scale
- 7.5
- apply_watermark
- negative_prompt
- nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image
- prompt_strength
- 0.8
- num_inference_steps
- 30
{ "width": 1024, "height": 1024, "prompt": "Masterpiece, glitch, holy holy holy, fog, by DarkIncursio", "scheduler": "DPM++2MSDE", "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "negative_prompt": "nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image", "prompt_strength": 0.8, "num_inference_steps": 30 }
Install Replicate’s Node.js client library:npm install replicate
Import 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 datacte/proteus-v0.3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "datacte/proteus-v0.3:b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48", { input: { width: 1024, height: 1024, prompt: "Masterpiece, glitch, holy holy holy, fog, by DarkIncursio", scheduler: "DPM++2MSDE", num_outputs: 1, guidance_scale: 7.5, apply_watermark: true, negative_prompt: "nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image", prompt_strength: 0.8, num_inference_steps: 30 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Import the client:import replicate
Run datacte/proteus-v0.3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "datacte/proteus-v0.3:b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48", input={ "width": 1024, "height": 1024, "prompt": "Masterpiece, glitch, holy holy holy, fog, by DarkIncursio", "scheduler": "DPM++2MSDE", "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": True, "negative_prompt": "nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image", "prompt_strength": 0.8, "num_inference_steps": 30 } ) # 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 datacte/proteus-v0.3 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": "datacte/proteus-v0.3:b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48", "input": { "width": 1024, "height": 1024, "prompt": "Masterpiece, glitch, holy holy holy, fog, by DarkIncursio", "scheduler": "DPM++2MSDE", "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "negative_prompt": "nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image", "prompt_strength": 0.8, "num_inference_steps": 30 } }' \ https://api.replicate.com/v1/predictions
To 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 cog
If 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/datacte/proteus-v0.3@sha256:b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48 \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="Masterpiece, glitch, holy holy holy, fog, by DarkIncursio"' \ -i 'scheduler="DPM++2MSDE"' \ -i 'num_outputs=1' \ -i 'guidance_scale=7.5' \ -i 'apply_watermark=true' \ -i 'negative_prompt="nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image"' \ -i 'prompt_strength=0.8' \ -i 'num_inference_steps=30'
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/datacte/proteus-v0.3@sha256:b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "Masterpiece, glitch, holy holy holy, fog, by DarkIncursio", "scheduler": "DPM++2MSDE", "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "negative_prompt": "nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image", "prompt_strength": 0.8, "num_inference_steps": 30 } }' \ http://localhost:5000/predictions
To learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2024-02-14T20:17:39.258901Z", "created_at": "2024-02-14T20:17:24.576320Z", "data_removed": false, "error": null, "id": "jfskdbdbmalwtxrty3rmtlbyhy", "input": { "width": 1024, "height": 1024, "prompt": "Masterpiece, glitch, holy holy holy, fog, by DarkIncursio", "scheduler": "DPM++2MSDE", "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "negative_prompt": "nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image", "prompt_strength": 0.8, "num_inference_steps": 30 }, "logs": "Using seed: 4016834622\nPrompt: Masterpiece, glitch, holy holy holy, fog, by DarkIncursio\ntxt2img mode\n 0%| | 0/30 [00:00<?, ?it/s]\n 3%|▎ | 1/30 [00:00<00:11, 2.51it/s]\n 7%|▋ | 2/30 [00:00<00:11, 2.50it/s]\n 10%|█ | 3/30 [00:01<00:10, 2.48it/s]\n 13%|█▎ | 4/30 [00:01<00:10, 2.48it/s]\n 17%|█▋ | 5/30 [00:02<00:10, 2.47it/s]\n 20%|██ | 6/30 [00:02<00:09, 2.47it/s]\n 23%|██▎ | 7/30 [00:02<00:09, 2.47it/s]\n 27%|██▋ | 8/30 [00:03<00:08, 2.47it/s]\n 30%|███ | 9/30 [00:03<00:08, 2.47it/s]\n 33%|███▎ | 10/30 [00:04<00:08, 2.47it/s]\n 37%|███▋ | 11/30 [00:04<00:07, 2.47it/s]\n 40%|████ | 12/30 [00:04<00:07, 2.47it/s]\n 43%|████▎ | 13/30 [00:05<00:06, 2.47it/s]\n 47%|████▋ | 14/30 [00:05<00:06, 2.47it/s]\n 50%|█████ | 15/30 [00:06<00:06, 2.47it/s]\n 53%|█████▎ | 16/30 [00:06<00:05, 2.47it/s]\n 57%|█████▋ | 17/30 [00:06<00:05, 2.47it/s]\n 60%|██████ | 18/30 [00:07<00:04, 2.46it/s]\n 63%|██████▎ | 19/30 [00:07<00:04, 2.47it/s]\n 67%|██████▋ | 20/30 [00:08<00:04, 2.47it/s]\n 70%|███████ | 21/30 [00:08<00:03, 2.46it/s]\n 73%|███████▎ | 22/30 [00:08<00:03, 2.46it/s]\n 77%|███████▋ | 23/30 [00:09<00:02, 2.46it/s]\n 80%|████████ | 24/30 [00:09<00:02, 2.46it/s]\n 83%|████████▎ | 25/30 [00:10<00:02, 2.46it/s]\n 87%|████████▋ | 26/30 [00:10<00:01, 2.46it/s]\n 90%|█████████ | 27/30 [00:10<00:01, 2.46it/s]\n 93%|█████████▎| 28/30 [00:11<00:00, 2.46it/s]\n 97%|█████████▋| 29/30 [00:11<00:00, 2.46it/s]\n100%|██████████| 30/30 [00:11<00:00, 2.90it/s]\n100%|██████████| 30/30 [00:11<00:00, 2.51it/s]", "metrics": { "predict_time": 14.617179, "total_time": 14.682581 }, "output": [ "https://replicate.delivery/pbxt/iL2qSzSFkJYKEFOQMZWwSHfYShN9ek3fgCffD42H15FO8o1SC/out-0.png" ], "started_at": "2024-02-14T20:17:24.641722Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/jfskdbdbmalwtxrty3rmtlbyhy", "cancel": "https://api.replicate.com/v1/predictions/jfskdbdbmalwtxrty3rmtlbyhy/cancel" }, "version": "b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48" }
Generated inUsing seed: 4016834622 Prompt: Masterpiece, glitch, holy holy holy, fog, by DarkIncursio txt2img mode 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:00<00:11, 2.51it/s] 7%|▋ | 2/30 [00:00<00:11, 2.50it/s] 10%|█ | 3/30 [00:01<00:10, 2.48it/s] 13%|█▎ | 4/30 [00:01<00:10, 2.48it/s] 17%|█▋ | 5/30 [00:02<00:10, 2.47it/s] 20%|██ | 6/30 [00:02<00:09, 2.47it/s] 23%|██▎ | 7/30 [00:02<00:09, 2.47it/s] 27%|██▋ | 8/30 [00:03<00:08, 2.47it/s] 30%|███ | 9/30 [00:03<00:08, 2.47it/s] 33%|███▎ | 10/30 [00:04<00:08, 2.47it/s] 37%|███▋ | 11/30 [00:04<00:07, 2.47it/s] 40%|████ | 12/30 [00:04<00:07, 2.47it/s] 43%|████▎ | 13/30 [00:05<00:06, 2.47it/s] 47%|████▋ | 14/30 [00:05<00:06, 2.47it/s] 50%|█████ | 15/30 [00:06<00:06, 2.47it/s] 53%|█████▎ | 16/30 [00:06<00:05, 2.47it/s] 57%|█████▋ | 17/30 [00:06<00:05, 2.47it/s] 60%|██████ | 18/30 [00:07<00:04, 2.46it/s] 63%|██████▎ | 19/30 [00:07<00:04, 2.47it/s] 67%|██████▋ | 20/30 [00:08<00:04, 2.47it/s] 70%|███████ | 21/30 [00:08<00:03, 2.46it/s] 73%|███████▎ | 22/30 [00:08<00:03, 2.46it/s] 77%|███████▋ | 23/30 [00:09<00:02, 2.46it/s] 80%|████████ | 24/30 [00:09<00:02, 2.46it/s] 83%|████████▎ | 25/30 [00:10<00:02, 2.46it/s] 87%|████████▋ | 26/30 [00:10<00:01, 2.46it/s] 90%|█████████ | 27/30 [00:10<00:01, 2.46it/s] 93%|█████████▎| 28/30 [00:11<00:00, 2.46it/s] 97%|█████████▋| 29/30 [00:11<00:00, 2.46it/s] 100%|██████████| 30/30 [00:11<00:00, 2.90it/s] 100%|██████████| 30/30 [00:11<00:00, 2.51it/s]
Prediction
datacte/proteus-v0.3:b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48IDpwcksmtb6g6un4xjjn6repaxt4StatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- Anime mugshot of a tough woman. She is holding a prison sign that reads "Proteus". Her face is censored. Anime key visual (best quality, HD, ~+~aesthetic~+~:1.2)
- scheduler
- DPM++2MSDE
- num_outputs
- 1
- guidance_scale
- 7.5
- apply_watermark
- negative_prompt
- nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image
- prompt_strength
- 0.8
- num_inference_steps
- 30
{ "width": 1024, "height": 1024, "prompt": "Anime mugshot of a tough woman. She is holding a prison sign that reads \"Proteus\". Her face is censored. Anime key visual (best quality, HD, ~+~aesthetic~+~:1.2)", "scheduler": "DPM++2MSDE", "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "negative_prompt": "nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image", "prompt_strength": 0.8, "num_inference_steps": 30 }
Install Replicate’s Node.js client library:npm install replicate
Import 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 datacte/proteus-v0.3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "datacte/proteus-v0.3:b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48", { input: { width: 1024, height: 1024, prompt: "Anime mugshot of a tough woman. She is holding a prison sign that reads \"Proteus\". Her face is censored. Anime key visual (best quality, HD, ~+~aesthetic~+~:1.2)", scheduler: "DPM++2MSDE", num_outputs: 1, guidance_scale: 7.5, apply_watermark: true, negative_prompt: "nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image", prompt_strength: 0.8, num_inference_steps: 30 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Import the client:import replicate
Run datacte/proteus-v0.3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "datacte/proteus-v0.3:b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48", input={ "width": 1024, "height": 1024, "prompt": "Anime mugshot of a tough woman. She is holding a prison sign that reads \"Proteus\". Her face is censored. Anime key visual (best quality, HD, ~+~aesthetic~+~:1.2)", "scheduler": "DPM++2MSDE", "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": True, "negative_prompt": "nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image", "prompt_strength": 0.8, "num_inference_steps": 30 } ) # 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 datacte/proteus-v0.3 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": "datacte/proteus-v0.3:b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48", "input": { "width": 1024, "height": 1024, "prompt": "Anime mugshot of a tough woman. She is holding a prison sign that reads \\"Proteus\\". Her face is censored. Anime key visual (best quality, HD, ~+~aesthetic~+~:1.2)", "scheduler": "DPM++2MSDE", "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "negative_prompt": "nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image", "prompt_strength": 0.8, "num_inference_steps": 30 } }' \ https://api.replicate.com/v1/predictions
To 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 cog
If 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/datacte/proteus-v0.3@sha256:b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48 \ -i 'width=1024' \ -i 'height=1024' \ -i $'prompt="Anime mugshot of a tough woman. She is holding a prison sign that reads \\"Proteus\\". Her face is censored. Anime key visual (best quality, HD, ~+~aesthetic~+~:1.2)"' \ -i 'scheduler="DPM++2MSDE"' \ -i 'num_outputs=1' \ -i 'guidance_scale=7.5' \ -i 'apply_watermark=true' \ -i 'negative_prompt="nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image"' \ -i 'prompt_strength=0.8' \ -i 'num_inference_steps=30'
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/datacte/proteus-v0.3@sha256:b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "Anime mugshot of a tough woman. She is holding a prison sign that reads \\"Proteus\\". Her face is censored. Anime key visual (best quality, HD, ~+~aesthetic~+~:1.2)", "scheduler": "DPM++2MSDE", "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "negative_prompt": "nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image", "prompt_strength": 0.8, "num_inference_steps": 30 } }' \ http://localhost:5000/predictions
To learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2024-02-14T20:25:53.267290Z", "created_at": "2024-02-14T20:24:47.803025Z", "data_removed": false, "error": null, "id": "pwcksmtb6g6un4xjjn6repaxt4", "input": { "width": 1024, "height": 1024, "prompt": "Anime mugshot of a tough woman. She is holding a prison sign that reads \"Proteus\". Her face is censored. Anime key visual (best quality, HD, ~+~aesthetic~+~:1.2)", "scheduler": "DPM++2MSDE", "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "negative_prompt": "nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image", "prompt_strength": 0.8, "num_inference_steps": 30 }, "logs": "Using seed: 1185096284\nPrompt: Anime mugshot of a tough woman. She is holding a prison sign that reads \"Proteus\". Her face is censored. Anime key visual (best quality, HD, ~+~aesthetic~+~:1.2)\ntxt2img mode\n 0%| | 0/30 [00:00<?, ?it/s]\n 3%|▎ | 1/30 [00:00<00:15, 1.82it/s]\n 7%|▋ | 2/30 [00:00<00:12, 2.16it/s]\n 10%|█ | 3/30 [00:01<00:11, 2.30it/s]\n 13%|█▎ | 4/30 [00:01<00:10, 2.38it/s]\n 17%|█▋ | 5/30 [00:02<00:10, 2.41it/s]\n 20%|██ | 6/30 [00:02<00:09, 2.44it/s]\n 23%|██▎ | 7/30 [00:02<00:09, 2.45it/s]\n 27%|██▋ | 8/30 [00:03<00:08, 2.46it/s]\n 30%|███ | 9/30 [00:03<00:08, 2.47it/s]\n 33%|███▎ | 10/30 [00:04<00:08, 2.47it/s]\n 37%|███▋ | 11/30 [00:04<00:07, 2.47it/s]\n 40%|████ | 12/30 [00:04<00:07, 2.47it/s]\n 43%|████▎ | 13/30 [00:05<00:06, 2.47it/s]\n 47%|████▋ | 14/30 [00:05<00:06, 2.47it/s]\n 50%|█████ | 15/30 [00:06<00:06, 2.47it/s]\n 53%|█████▎ | 16/30 [00:06<00:05, 2.47it/s]\n 57%|█████▋ | 17/30 [00:06<00:05, 2.47it/s]\n 60%|██████ | 18/30 [00:07<00:04, 2.47it/s]\n 63%|██████▎ | 19/30 [00:07<00:04, 2.47it/s]\n 67%|██████▋ | 20/30 [00:08<00:04, 2.47it/s]\n 70%|███████ | 21/30 [00:08<00:03, 2.47it/s]\n 73%|███████▎ | 22/30 [00:09<00:03, 2.47it/s]\n 77%|███████▋ | 23/30 [00:09<00:02, 2.47it/s]\n 80%|████████ | 24/30 [00:09<00:02, 2.47it/s]\n 83%|████████▎ | 25/30 [00:10<00:02, 2.47it/s]\n 87%|████████▋ | 26/30 [00:10<00:01, 2.47it/s]\n 90%|█████████ | 27/30 [00:11<00:01, 2.47it/s]\n 93%|█████████▎| 28/30 [00:11<00:00, 2.46it/s]\n 97%|█████████▋| 29/30 [00:11<00:00, 2.47it/s]\n100%|██████████| 30/30 [00:12<00:00, 2.91it/s]\n100%|██████████| 30/30 [00:12<00:00, 2.49it/s]", "metrics": { "predict_time": 15.53602, "total_time": 65.464265 }, "output": [ "https://replicate.delivery/pbxt/C3LYYa30997dKRdeNDSXNjIK01CH5q8CSto12eWundnPPtWSA/out-0.png" ], "started_at": "2024-02-14T20:25:37.731270Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/pwcksmtb6g6un4xjjn6repaxt4", "cancel": "https://api.replicate.com/v1/predictions/pwcksmtb6g6un4xjjn6repaxt4/cancel" }, "version": "b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48" }
Generated inUsing seed: 1185096284 Prompt: Anime mugshot of a tough woman. She is holding a prison sign that reads "Proteus". Her face is censored. Anime key visual (best quality, HD, ~+~aesthetic~+~:1.2) txt2img mode 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:00<00:15, 1.82it/s] 7%|▋ | 2/30 [00:00<00:12, 2.16it/s] 10%|█ | 3/30 [00:01<00:11, 2.30it/s] 13%|█▎ | 4/30 [00:01<00:10, 2.38it/s] 17%|█▋ | 5/30 [00:02<00:10, 2.41it/s] 20%|██ | 6/30 [00:02<00:09, 2.44it/s] 23%|██▎ | 7/30 [00:02<00:09, 2.45it/s] 27%|██▋ | 8/30 [00:03<00:08, 2.46it/s] 30%|███ | 9/30 [00:03<00:08, 2.47it/s] 33%|███▎ | 10/30 [00:04<00:08, 2.47it/s] 37%|███▋ | 11/30 [00:04<00:07, 2.47it/s] 40%|████ | 12/30 [00:04<00:07, 2.47it/s] 43%|████▎ | 13/30 [00:05<00:06, 2.47it/s] 47%|████▋ | 14/30 [00:05<00:06, 2.47it/s] 50%|█████ | 15/30 [00:06<00:06, 2.47it/s] 53%|█████▎ | 16/30 [00:06<00:05, 2.47it/s] 57%|█████▋ | 17/30 [00:06<00:05, 2.47it/s] 60%|██████ | 18/30 [00:07<00:04, 2.47it/s] 63%|██████▎ | 19/30 [00:07<00:04, 2.47it/s] 67%|██████▋ | 20/30 [00:08<00:04, 2.47it/s] 70%|███████ | 21/30 [00:08<00:03, 2.47it/s] 73%|███████▎ | 22/30 [00:09<00:03, 2.47it/s] 77%|███████▋ | 23/30 [00:09<00:02, 2.47it/s] 80%|████████ | 24/30 [00:09<00:02, 2.47it/s] 83%|████████▎ | 25/30 [00:10<00:02, 2.47it/s] 87%|████████▋ | 26/30 [00:10<00:01, 2.47it/s] 90%|█████████ | 27/30 [00:11<00:01, 2.47it/s] 93%|█████████▎| 28/30 [00:11<00:00, 2.46it/s] 97%|█████████▋| 29/30 [00:11<00:00, 2.47it/s] 100%|██████████| 30/30 [00:12<00:00, 2.91it/s] 100%|██████████| 30/30 [00:12<00:00, 2.49it/s]
Want to make some of these yourself?
Run this model