datacte/mobius

Mobius: Redefining State-of-the-Art in Debiased Diffusion Models

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.

ProteusV0.3: The Anime Update

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
Prediction
datacte/mobius:197f2145583f80c7c3ec520d2a1080aa7986601e1612e417ccd6e4f50fe0624fIDs1kkmbgf19rj00cjd1ar3c1dg0StatusSucceededSourceWebHardwareA100 (80GB)Total durationCreatedby @datacteInput
- width
- 1024
- height
- 1024
- prompt
- The image features an older man, a long white beard and mustache, He has a stern expression, giving the impression of a wise and experienced individual. The mans beard and mustache are prominent, adding to his distinguished appearance. The close-up shot of the mans face emphasizes his facial features and the intensity of his gaze.
- scheduler
- DPMSolverMultistep
- num_outputs
- 1
- guidance_scale
- 3
- num_inference_steps
- 50
{ "width": 1024, "height": 1024, "prompt": "The image features an older man, a long white beard and mustache, He has a stern expression, giving the impression of a wise and experienced individual. The mans beard and mustache are prominent, adding to his distinguished appearance. The close-up shot of the mans face emphasizes his facial features and the intensity of his gaze.", "scheduler": "DPMSolverMultistep", "num_outputs": 1, "guidance_scale": 3, "num_inference_steps": 50 }
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/mobius using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "datacte/mobius:197f2145583f80c7c3ec520d2a1080aa7986601e1612e417ccd6e4f50fe0624f", { input: { width: 1024, height: 1024, prompt: "The image features an older man, a long white beard and mustache, He has a stern expression, giving the impression of a wise and experienced individual. The mans beard and mustache are prominent, adding to his distinguished appearance. The close-up shot of the mans face emphasizes his facial features and the intensity of his gaze.", scheduler: "DPMSolverMultistep", num_outputs: 1, guidance_scale: 3, num_inference_steps: 50 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Import the client:import replicate
Run datacte/mobius using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "datacte/mobius:197f2145583f80c7c3ec520d2a1080aa7986601e1612e417ccd6e4f50fe0624f", input={ "width": 1024, "height": 1024, "prompt": "The image features an older man, a long white beard and mustache, He has a stern expression, giving the impression of a wise and experienced individual. The mans beard and mustache are prominent, adding to his distinguished appearance. The close-up shot of the mans face emphasizes his facial features and the intensity of his gaze.", "scheduler": "DPMSolverMultistep", "num_outputs": 1, "guidance_scale": 3, "num_inference_steps": 50 } ) # To access the file URL: print(output[0].url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output[0].read())
To learn more, take a look at the guide on getting started with Python.
Run datacte/mobius 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/mobius:197f2145583f80c7c3ec520d2a1080aa7986601e1612e417ccd6e4f50fe0624f", "input": { "width": 1024, "height": 1024, "prompt": "The image features an older man, a long white beard and mustache, He has a stern expression, giving the impression of a wise and experienced individual. The mans beard and mustache are prominent, adding to his distinguished appearance. The close-up shot of the mans face emphasizes his facial features and the intensity of his gaze.", "scheduler": "DPMSolverMultistep", "num_outputs": 1, "guidance_scale": 3, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-10-07T18:54:23.926538Z", "created_at": "2024-10-07T18:54:17.866000Z", "data_removed": false, "error": null, "id": "s1kkmbgf19rj00cjd1ar3c1dg0", "input": { "width": 1024, "height": 1024, "prompt": "The image features an older man, a long white beard and mustache, He has a stern expression, giving the impression of a wise and experienced individual. The mans beard and mustache are prominent, adding to his distinguished appearance. The close-up shot of the mans face emphasizes his facial features and the intensity of his gaze.", "scheduler": "DPMSolverMultistep", "num_outputs": 1, "guidance_scale": 3, "num_inference_steps": 50 }, "logs": "Using seed: 21520\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:05, 8.95it/s]\n 6%|▌ | 3/50 [00:00<00:04, 10.84it/s]\n 10%|█ | 5/50 [00:00<00:04, 9.83it/s]\n 12%|█▏ | 6/50 [00:00<00:04, 9.61it/s]\n 14%|█▍ | 7/50 [00:00<00:04, 9.44it/s]\n 16%|█▌ | 8/50 [00:00<00:04, 9.33it/s]\n 18%|█▊ | 9/50 [00:00<00:04, 9.24it/s]\n 20%|██ | 10/50 [00:01<00:04, 9.18it/s]\n 22%|██▏ | 11/50 [00:01<00:04, 9.14it/s]\n 24%|██▍ | 12/50 [00:01<00:04, 9.11it/s]\n 26%|██▌ | 13/50 [00:01<00:04, 9.09it/s]\n 28%|██▊ | 14/50 [00:01<00:03, 9.07it/s]\n 30%|███ | 15/50 [00:01<00:03, 9.06it/s]\n 32%|███▏ | 16/50 [00:01<00:03, 9.06it/s]\n 34%|███▍ | 17/50 [00:01<00:03, 9.05it/s]\n 36%|███▌ | 18/50 [00:01<00:03, 9.05it/s]\n 38%|███▊ | 19/50 [00:02<00:03, 9.05it/s]\n 40%|████ | 20/50 [00:02<00:03, 9.04it/s]\n 42%|████▏ | 21/50 [00:02<00:03, 9.04it/s]\n 44%|████▍ | 22/50 [00:02<00:03, 9.04it/s]\n 46%|████▌ | 23/50 [00:02<00:02, 9.04it/s]\n 48%|████▊ | 24/50 [00:02<00:02, 9.04it/s]\n 50%|█████ | 25/50 [00:02<00:02, 9.04it/s]\n 52%|█████▏ | 26/50 [00:02<00:02, 9.04it/s]\n 54%|█████▍ | 27/50 [00:02<00:02, 9.04it/s]\n 56%|█████▌ | 28/50 [00:03<00:02, 9.04it/s]\n 58%|█████▊ | 29/50 [00:03<00:02, 9.04it/s]\n 60%|██████ | 30/50 [00:03<00:02, 9.04it/s]\n 62%|██████▏ | 31/50 [00:03<00:02, 9.04it/s]\n 64%|██████▍ | 32/50 [00:03<00:01, 9.04it/s]\n 66%|██████▌ | 33/50 [00:03<00:01, 9.04it/s]\n 68%|██████▊ | 34/50 [00:03<00:01, 9.04it/s]\n 70%|███████ | 35/50 [00:03<00:01, 9.04it/s]\n 72%|███████▏ | 36/50 [00:03<00:01, 9.04it/s]\n 74%|███████▍ | 37/50 [00:04<00:01, 9.04it/s]\n 76%|███████▌ | 38/50 [00:04<00:01, 9.04it/s]\n 78%|███████▊ | 39/50 [00:04<00:01, 9.04it/s]\n 80%|████████ | 40/50 [00:04<00:01, 9.04it/s]\n 82%|████████▏ | 41/50 [00:04<00:00, 9.04it/s]\n 84%|████████▍ | 42/50 [00:04<00:00, 9.04it/s]\n 86%|████████▌ | 43/50 [00:04<00:00, 9.04it/s]\n 88%|████████▊ | 44/50 [00:04<00:00, 9.04it/s]\n 90%|█████████ | 45/50 [00:04<00:00, 9.04it/s]\n 92%|█████████▏| 46/50 [00:05<00:00, 9.04it/s]\n 94%|█████████▍| 47/50 [00:05<00:00, 9.04it/s]\n 96%|█████████▌| 48/50 [00:05<00:00, 9.04it/s]\n 98%|█████████▊| 49/50 [00:05<00:00, 9.04it/s]\n100%|██████████| 50/50 [00:05<00:00, 9.04it/s]\n100%|██████████| 50/50 [00:05<00:00, 9.12it/s]", "metrics": { "predict_time": 6.052366482, "total_time": 6.060538 }, "output": [ "https://replicate.delivery/yhqm/rSV3LUK0laYpHhoMCvIoaFGHlOHkixw8ShLW2WpQ8fwvAPyJA/out-0.png" ], "started_at": "2024-10-07T18:54:17.874172Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/s1kkmbgf19rj00cjd1ar3c1dg0", "cancel": "https://api.replicate.com/v1/predictions/s1kkmbgf19rj00cjd1ar3c1dg0/cancel" }, "version": "197f2145583f80c7c3ec520d2a1080aa7986601e1612e417ccd6e4f50fe0624f" }
Generated inUsing seed: 21520 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:05, 8.95it/s] 6%|▌ | 3/50 [00:00<00:04, 10.84it/s] 10%|█ | 5/50 [00:00<00:04, 9.83it/s] 12%|█▏ | 6/50 [00:00<00:04, 9.61it/s] 14%|█▍ | 7/50 [00:00<00:04, 9.44it/s] 16%|█▌ | 8/50 [00:00<00:04, 9.33it/s] 18%|█▊ | 9/50 [00:00<00:04, 9.24it/s] 20%|██ | 10/50 [00:01<00:04, 9.18it/s] 22%|██▏ | 11/50 [00:01<00:04, 9.14it/s] 24%|██▍ | 12/50 [00:01<00:04, 9.11it/s] 26%|██▌ | 13/50 [00:01<00:04, 9.09it/s] 28%|██▊ | 14/50 [00:01<00:03, 9.07it/s] 30%|███ | 15/50 [00:01<00:03, 9.06it/s] 32%|███▏ | 16/50 [00:01<00:03, 9.06it/s] 34%|███▍ | 17/50 [00:01<00:03, 9.05it/s] 36%|███▌ | 18/50 [00:01<00:03, 9.05it/s] 38%|███▊ | 19/50 [00:02<00:03, 9.05it/s] 40%|████ | 20/50 [00:02<00:03, 9.04it/s] 42%|████▏ | 21/50 [00:02<00:03, 9.04it/s] 44%|████▍ | 22/50 [00:02<00:03, 9.04it/s] 46%|████▌ | 23/50 [00:02<00:02, 9.04it/s] 48%|████▊ | 24/50 [00:02<00:02, 9.04it/s] 50%|█████ | 25/50 [00:02<00:02, 9.04it/s] 52%|█████▏ | 26/50 [00:02<00:02, 9.04it/s] 54%|█████▍ | 27/50 [00:02<00:02, 9.04it/s] 56%|█████▌ | 28/50 [00:03<00:02, 9.04it/s] 58%|█████▊ | 29/50 [00:03<00:02, 9.04it/s] 60%|██████ | 30/50 [00:03<00:02, 9.04it/s] 62%|██████▏ | 31/50 [00:03<00:02, 9.04it/s] 64%|██████▍ | 32/50 [00:03<00:01, 9.04it/s] 66%|██████▌ | 33/50 [00:03<00:01, 9.04it/s] 68%|██████▊ | 34/50 [00:03<00:01, 9.04it/s] 70%|███████ | 35/50 [00:03<00:01, 9.04it/s] 72%|███████▏ | 36/50 [00:03<00:01, 9.04it/s] 74%|███████▍ | 37/50 [00:04<00:01, 9.04it/s] 76%|███████▌ | 38/50 [00:04<00:01, 9.04it/s] 78%|███████▊ | 39/50 [00:04<00:01, 9.04it/s] 80%|████████ | 40/50 [00:04<00:01, 9.04it/s] 82%|████████▏ | 41/50 [00:04<00:00, 9.04it/s] 84%|████████▍ | 42/50 [00:04<00:00, 9.04it/s] 86%|████████▌ | 43/50 [00:04<00:00, 9.04it/s] 88%|████████▊ | 44/50 [00:04<00:00, 9.04it/s] 90%|█████████ | 45/50 [00:04<00:00, 9.04it/s] 92%|█████████▏| 46/50 [00:05<00:00, 9.04it/s] 94%|█████████▍| 47/50 [00:05<00:00, 9.04it/s] 96%|█████████▌| 48/50 [00:05<00:00, 9.04it/s] 98%|█████████▊| 49/50 [00:05<00:00, 9.04it/s] 100%|██████████| 50/50 [00:05<00:00, 9.04it/s] 100%|██████████| 50/50 [00:05<00:00, 9.12it/s]
Prediction
datacte/mobius:197f2145583f80c7c3ec520d2a1080aa7986601e1612e417ccd6e4f50fe0624fID8v4q89m6yhrj20cjd1b9y3sa4cStatusSucceededSourceWebHardwareA100 (80GB)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- Super Closeup Portrait, action shot, Profoundly dark whitish meadow, glass flowers, Stains, space grunge style, Jeanne d'Arc wearing White Olive green used styled Cotton frock, Wielding thin silver sword, Sci-fi vibe, dirty, noisy, Vintage monk style, very detailed, hd
- scheduler
- DPMSolverMultistep
- num_outputs
- 1
- guidance_scale
- 7
- num_inference_steps
- 50
{ "width": 1024, "height": 1024, "prompt": "Super Closeup Portrait, action shot, Profoundly dark whitish meadow, glass flowers, Stains, space grunge style, Jeanne d'Arc wearing White Olive green used styled Cotton frock, Wielding thin silver sword, Sci-fi vibe, dirty, noisy, Vintage monk style, very detailed, hd", "scheduler": "DPMSolverMultistep", "num_outputs": 1, "guidance_scale": 7, "num_inference_steps": 50 }
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/mobius using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "datacte/mobius:197f2145583f80c7c3ec520d2a1080aa7986601e1612e417ccd6e4f50fe0624f", { input: { width: 1024, height: 1024, prompt: "Super Closeup Portrait, action shot, Profoundly dark whitish meadow, glass flowers, Stains, space grunge style, Jeanne d'Arc wearing White Olive green used styled Cotton frock, Wielding thin silver sword, Sci-fi vibe, dirty, noisy, Vintage monk style, very detailed, hd", scheduler: "DPMSolverMultistep", num_outputs: 1, guidance_scale: 7, num_inference_steps: 50 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Import the client:import replicate
Run datacte/mobius using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "datacte/mobius:197f2145583f80c7c3ec520d2a1080aa7986601e1612e417ccd6e4f50fe0624f", input={ "width": 1024, "height": 1024, "prompt": "Super Closeup Portrait, action shot, Profoundly dark whitish meadow, glass flowers, Stains, space grunge style, Jeanne d'Arc wearing White Olive green used styled Cotton frock, Wielding thin silver sword, Sci-fi vibe, dirty, noisy, Vintage monk style, very detailed, hd", "scheduler": "DPMSolverMultistep", "num_outputs": 1, "guidance_scale": 7, "num_inference_steps": 50 } ) # To access the file URL: print(output[0].url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output[0].read())
To learn more, take a look at the guide on getting started with Python.
Run datacte/mobius 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/mobius:197f2145583f80c7c3ec520d2a1080aa7986601e1612e417ccd6e4f50fe0624f", "input": { "width": 1024, "height": 1024, "prompt": "Super Closeup Portrait, action shot, Profoundly dark whitish meadow, glass flowers, Stains, space grunge style, Jeanne d\'Arc wearing White Olive green used styled Cotton frock, Wielding thin silver sword, Sci-fi vibe, dirty, noisy, Vintage monk style, very detailed, hd", "scheduler": "DPMSolverMultistep", "num_outputs": 1, "guidance_scale": 7, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-10-07T18:56:00.183735Z", "created_at": "2024-10-07T18:55:54.100000Z", "data_removed": false, "error": null, "id": "8v4q89m6yhrj20cjd1b9y3sa4c", "input": { "width": 1024, "height": 1024, "prompt": "Super Closeup Portrait, action shot, Profoundly dark whitish meadow, glass flowers, Stains, space grunge style, Jeanne d'Arc wearing White Olive green used styled Cotton frock, Wielding thin silver sword, Sci-fi vibe, dirty, noisy, Vintage monk style, very detailed, hd", "scheduler": "DPMSolverMultistep", "num_outputs": 1, "guidance_scale": 7, "num_inference_steps": 50 }, "logs": "Using seed: 58492\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:05, 8.95it/s]\n 6%|▌ | 3/50 [00:00<00:04, 10.82it/s]\n 10%|█ | 5/50 [00:00<00:04, 9.81it/s]\n 12%|█▏ | 6/50 [00:00<00:04, 9.59it/s]\n 14%|█▍ | 7/50 [00:00<00:04, 9.43it/s]\n 16%|█▌ | 8/50 [00:00<00:04, 9.32it/s]\n 18%|█▊ | 9/50 [00:00<00:04, 9.24it/s]\n 20%|██ | 10/50 [00:01<00:04, 9.18it/s]\n 22%|██▏ | 11/50 [00:01<00:04, 9.14it/s]\n 24%|██▍ | 12/50 [00:01<00:04, 9.11it/s]\n 26%|██▌ | 13/50 [00:01<00:04, 9.09it/s]\n 28%|██▊ | 14/50 [00:01<00:03, 9.07it/s]\n 30%|███ | 15/50 [00:01<00:03, 9.06it/s]\n 32%|███▏ | 16/50 [00:01<00:03, 9.05it/s]\n 34%|███▍ | 17/50 [00:01<00:03, 9.05it/s]\n 36%|███▌ | 18/50 [00:01<00:03, 9.04it/s]\n 38%|███▊ | 19/50 [00:02<00:03, 9.04it/s]\n 40%|████ | 20/50 [00:02<00:03, 9.04it/s]\n 42%|████▏ | 21/50 [00:02<00:03, 9.04it/s]\n 44%|████▍ | 22/50 [00:02<00:03, 9.04it/s]\n 46%|████▌ | 23/50 [00:02<00:02, 9.04it/s]\n 48%|████▊ | 24/50 [00:02<00:02, 9.04it/s]\n 50%|█████ | 25/50 [00:02<00:02, 9.04it/s]\n 52%|█████▏ | 26/50 [00:02<00:02, 9.04it/s]\n 54%|█████▍ | 27/50 [00:02<00:02, 9.04it/s]\n 56%|█████▌ | 28/50 [00:03<00:02, 9.03it/s]\n 58%|█████▊ | 29/50 [00:03<00:02, 9.04it/s]\n 60%|██████ | 30/50 [00:03<00:02, 9.03it/s]\n 62%|██████▏ | 31/50 [00:03<00:02, 9.03it/s]\n 64%|██████▍ | 32/50 [00:03<00:01, 9.03it/s]\n 66%|██████▌ | 33/50 [00:03<00:01, 9.04it/s]\n 68%|██████▊ | 34/50 [00:03<00:01, 9.03it/s]\n 70%|███████ | 35/50 [00:03<00:01, 9.03it/s]\n 72%|███████▏ | 36/50 [00:03<00:01, 9.03it/s]\n 74%|███████▍ | 37/50 [00:04<00:01, 9.03it/s]\n 76%|███████▌ | 38/50 [00:04<00:01, 9.03it/s]\n 78%|███████▊ | 39/50 [00:04<00:01, 9.03it/s]\n 80%|████████ | 40/50 [00:04<00:01, 9.03it/s]\n 82%|████████▏ | 41/50 [00:04<00:00, 9.03it/s]\n 84%|████████▍ | 42/50 [00:04<00:00, 9.03it/s]\n 86%|████████▌ | 43/50 [00:04<00:00, 9.03it/s]\n 88%|████████▊ | 44/50 [00:04<00:00, 9.03it/s]\n 90%|█████████ | 45/50 [00:04<00:00, 9.02it/s]\n 92%|█████████▏| 46/50 [00:05<00:00, 9.02it/s]\n 94%|█████████▍| 47/50 [00:05<00:00, 9.02it/s]\n 96%|█████████▌| 48/50 [00:05<00:00, 9.03it/s]\n 98%|█████████▊| 49/50 [00:05<00:00, 9.03it/s]\n100%|██████████| 50/50 [00:05<00:00, 9.03it/s]\n100%|██████████| 50/50 [00:05<00:00, 9.11it/s]", "metrics": { "predict_time": 6.074515758, "total_time": 6.083735 }, "output": [ "https://replicate.delivery/yhqm/wryLK772h15bJJ0FmDYTJHOcAQHRwIyVz3BnE3eeftUBG8InA/out-0.png" ], "started_at": "2024-10-07T18:55:54.109219Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/8v4q89m6yhrj20cjd1b9y3sa4c", "cancel": "https://api.replicate.com/v1/predictions/8v4q89m6yhrj20cjd1b9y3sa4c/cancel" }, "version": "197f2145583f80c7c3ec520d2a1080aa7986601e1612e417ccd6e4f50fe0624f" }
Generated inUsing seed: 58492 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:05, 8.95it/s] 6%|▌ | 3/50 [00:00<00:04, 10.82it/s] 10%|█ | 5/50 [00:00<00:04, 9.81it/s] 12%|█▏ | 6/50 [00:00<00:04, 9.59it/s] 14%|█▍ | 7/50 [00:00<00:04, 9.43it/s] 16%|█▌ | 8/50 [00:00<00:04, 9.32it/s] 18%|█▊ | 9/50 [00:00<00:04, 9.24it/s] 20%|██ | 10/50 [00:01<00:04, 9.18it/s] 22%|██▏ | 11/50 [00:01<00:04, 9.14it/s] 24%|██▍ | 12/50 [00:01<00:04, 9.11it/s] 26%|██▌ | 13/50 [00:01<00:04, 9.09it/s] 28%|██▊ | 14/50 [00:01<00:03, 9.07it/s] 30%|███ | 15/50 [00:01<00:03, 9.06it/s] 32%|███▏ | 16/50 [00:01<00:03, 9.05it/s] 34%|███▍ | 17/50 [00:01<00:03, 9.05it/s] 36%|███▌ | 18/50 [00:01<00:03, 9.04it/s] 38%|███▊ | 19/50 [00:02<00:03, 9.04it/s] 40%|████ | 20/50 [00:02<00:03, 9.04it/s] 42%|████▏ | 21/50 [00:02<00:03, 9.04it/s] 44%|████▍ | 22/50 [00:02<00:03, 9.04it/s] 46%|████▌ | 23/50 [00:02<00:02, 9.04it/s] 48%|████▊ | 24/50 [00:02<00:02, 9.04it/s] 50%|█████ | 25/50 [00:02<00:02, 9.04it/s] 52%|█████▏ | 26/50 [00:02<00:02, 9.04it/s] 54%|█████▍ | 27/50 [00:02<00:02, 9.04it/s] 56%|█████▌ | 28/50 [00:03<00:02, 9.03it/s] 58%|█████▊ | 29/50 [00:03<00:02, 9.04it/s] 60%|██████ | 30/50 [00:03<00:02, 9.03it/s] 62%|██████▏ | 31/50 [00:03<00:02, 9.03it/s] 64%|██████▍ | 32/50 [00:03<00:01, 9.03it/s] 66%|██████▌ | 33/50 [00:03<00:01, 9.04it/s] 68%|██████▊ | 34/50 [00:03<00:01, 9.03it/s] 70%|███████ | 35/50 [00:03<00:01, 9.03it/s] 72%|███████▏ | 36/50 [00:03<00:01, 9.03it/s] 74%|███████▍ | 37/50 [00:04<00:01, 9.03it/s] 76%|███████▌ | 38/50 [00:04<00:01, 9.03it/s] 78%|███████▊ | 39/50 [00:04<00:01, 9.03it/s] 80%|████████ | 40/50 [00:04<00:01, 9.03it/s] 82%|████████▏ | 41/50 [00:04<00:00, 9.03it/s] 84%|████████▍ | 42/50 [00:04<00:00, 9.03it/s] 86%|████████▌ | 43/50 [00:04<00:00, 9.03it/s] 88%|████████▊ | 44/50 [00:04<00:00, 9.03it/s] 90%|█████████ | 45/50 [00:04<00:00, 9.02it/s] 92%|█████████▏| 46/50 [00:05<00:00, 9.02it/s] 94%|█████████▍| 47/50 [00:05<00:00, 9.02it/s] 96%|█████████▌| 48/50 [00:05<00:00, 9.03it/s] 98%|█████████▊| 49/50 [00:05<00:00, 9.03it/s] 100%|██████████| 50/50 [00:05<00:00, 9.03it/s] 100%|██████████| 50/50 [00:05<00:00, 9.11it/s]
Prediction
datacte/mobius:197f2145583f80c7c3ec520d2a1080aa7986601e1612e417ccd6e4f50fe0624fID78hp15tfndrj20cjd1cssnyj7cStatusSucceededSourceWebHardwareA100 (80GB)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- anime boy, protagonist, best quality
- scheduler
- DPMSolverMultistep
- num_outputs
- 1
- guidance_scale
- 7
- num_inference_steps
- 50
{ "width": 1024, "height": 1024, "prompt": "anime boy, protagonist, best quality", "scheduler": "DPMSolverMultistep", "num_outputs": 1, "guidance_scale": 7, "num_inference_steps": 50 }
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/mobius using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "datacte/mobius:197f2145583f80c7c3ec520d2a1080aa7986601e1612e417ccd6e4f50fe0624f", { input: { width: 1024, height: 1024, prompt: "anime boy, protagonist, best quality", scheduler: "DPMSolverMultistep", num_outputs: 1, guidance_scale: 7, num_inference_steps: 50 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Import the client:import replicate
Run datacte/mobius using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "datacte/mobius:197f2145583f80c7c3ec520d2a1080aa7986601e1612e417ccd6e4f50fe0624f", input={ "width": 1024, "height": 1024, "prompt": "anime boy, protagonist, best quality", "scheduler": "DPMSolverMultistep", "num_outputs": 1, "guidance_scale": 7, "num_inference_steps": 50 } ) # To access the file URL: print(output[0].url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output[0].read())
To learn more, take a look at the guide on getting started with Python.
Run datacte/mobius 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/mobius:197f2145583f80c7c3ec520d2a1080aa7986601e1612e417ccd6e4f50fe0624f", "input": { "width": 1024, "height": 1024, "prompt": "anime boy, protagonist, best quality", "scheduler": "DPMSolverMultistep", "num_outputs": 1, "guidance_scale": 7, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-10-07T18:59:02.656586Z", "created_at": "2024-10-07T18:58:56.555000Z", "data_removed": false, "error": null, "id": "78hp15tfndrj20cjd1cssnyj7c", "input": { "width": 1024, "height": 1024, "prompt": "anime boy, protagonist, best quality", "scheduler": "DPMSolverMultistep", "num_outputs": 1, "guidance_scale": 7, "num_inference_steps": 50 }, "logs": "Using seed: 54551\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:05, 8.94it/s]\n 6%|▌ | 3/50 [00:00<00:04, 10.81it/s]\n 10%|█ | 5/50 [00:00<00:04, 9.82it/s]\n 12%|█▏ | 6/50 [00:00<00:04, 9.60it/s]\n 14%|█▍ | 7/50 [00:00<00:04, 9.44it/s]\n 16%|█▌ | 8/50 [00:00<00:04, 9.32it/s]\n 18%|█▊ | 9/50 [00:00<00:04, 9.23it/s]\n 20%|██ | 10/50 [00:01<00:04, 9.18it/s]\n 22%|██▏ | 11/50 [00:01<00:04, 9.14it/s]\n 24%|██▍ | 12/50 [00:01<00:04, 9.11it/s]\n 26%|██▌ | 13/50 [00:01<00:04, 9.09it/s]\n 28%|██▊ | 14/50 [00:01<00:03, 9.07it/s]\n 30%|███ | 15/50 [00:01<00:03, 9.06it/s]\n 32%|███▏ | 16/50 [00:01<00:03, 9.06it/s]\n 34%|███▍ | 17/50 [00:01<00:03, 9.05it/s]\n 36%|███▌ | 18/50 [00:01<00:03, 9.05it/s]\n 38%|███▊ | 19/50 [00:02<00:03, 9.04it/s]\n 40%|████ | 20/50 [00:02<00:03, 9.04it/s]\n 42%|████▏ | 21/50 [00:02<00:03, 9.04it/s]\n 44%|████▍ | 22/50 [00:02<00:03, 9.04it/s]\n 46%|████▌ | 23/50 [00:02<00:02, 9.04it/s]\n 48%|████▊ | 24/50 [00:02<00:02, 9.04it/s]\n 50%|█████ | 25/50 [00:02<00:02, 9.04it/s]\n 52%|█████▏ | 26/50 [00:02<00:02, 9.04it/s]\n 54%|█████▍ | 27/50 [00:02<00:02, 9.04it/s]\n 56%|█████▌ | 28/50 [00:03<00:02, 9.04it/s]\n 58%|█████▊ | 29/50 [00:03<00:02, 9.04it/s]\n 60%|██████ | 30/50 [00:03<00:02, 9.04it/s]\n 62%|██████▏ | 31/50 [00:03<00:02, 9.04it/s]\n 64%|██████▍ | 32/50 [00:03<00:01, 9.04it/s]\n 66%|██████▌ | 33/50 [00:03<00:01, 9.04it/s]\n 68%|██████▊ | 34/50 [00:03<00:01, 9.04it/s]\n 70%|███████ | 35/50 [00:03<00:01, 9.04it/s]\n 72%|███████▏ | 36/50 [00:03<00:01, 9.04it/s]\n 74%|███████▍ | 37/50 [00:04<00:01, 9.04it/s]\n 76%|███████▌ | 38/50 [00:04<00:01, 9.04it/s]\n 78%|███████▊ | 39/50 [00:04<00:01, 9.02it/s]\n 80%|████████ | 40/50 [00:04<00:01, 9.02it/s]\n 82%|████████▏ | 41/50 [00:04<00:00, 9.02it/s]\n 84%|████████▍ | 42/50 [00:04<00:00, 9.03it/s]\n 86%|████████▌ | 43/50 [00:04<00:00, 9.03it/s]\n 88%|████████▊ | 44/50 [00:04<00:00, 9.03it/s]\n 90%|█████████ | 45/50 [00:04<00:00, 9.03it/s]\n 92%|█████████▏| 46/50 [00:05<00:00, 9.03it/s]\n 94%|█████████▍| 47/50 [00:05<00:00, 9.04it/s]\n 96%|█████████▌| 48/50 [00:05<00:00, 9.04it/s]\n 98%|█████████▊| 49/50 [00:05<00:00, 9.02it/s]\n100%|██████████| 50/50 [00:05<00:00, 9.02it/s]\n100%|██████████| 50/50 [00:05<00:00, 9.12it/s]", "metrics": { "predict_time": 6.090890986, "total_time": 6.101586 }, "output": [ "https://replicate.delivery/yhqm/gLJoBFC2WfSNCqetVuD8vfUc72ExfcNM7WLVEsaSYTFbX4ROB/out-0.png" ], "started_at": "2024-10-07T18:58:56.565695Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/78hp15tfndrj20cjd1cssnyj7c", "cancel": "https://api.replicate.com/v1/predictions/78hp15tfndrj20cjd1cssnyj7c/cancel" }, "version": "197f2145583f80c7c3ec520d2a1080aa7986601e1612e417ccd6e4f50fe0624f" }
Generated inUsing seed: 54551 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:05, 8.94it/s] 6%|▌ | 3/50 [00:00<00:04, 10.81it/s] 10%|█ | 5/50 [00:00<00:04, 9.82it/s] 12%|█▏ | 6/50 [00:00<00:04, 9.60it/s] 14%|█▍ | 7/50 [00:00<00:04, 9.44it/s] 16%|█▌ | 8/50 [00:00<00:04, 9.32it/s] 18%|█▊ | 9/50 [00:00<00:04, 9.23it/s] 20%|██ | 10/50 [00:01<00:04, 9.18it/s] 22%|██▏ | 11/50 [00:01<00:04, 9.14it/s] 24%|██▍ | 12/50 [00:01<00:04, 9.11it/s] 26%|██▌ | 13/50 [00:01<00:04, 9.09it/s] 28%|██▊ | 14/50 [00:01<00:03, 9.07it/s] 30%|███ | 15/50 [00:01<00:03, 9.06it/s] 32%|███▏ | 16/50 [00:01<00:03, 9.06it/s] 34%|███▍ | 17/50 [00:01<00:03, 9.05it/s] 36%|███▌ | 18/50 [00:01<00:03, 9.05it/s] 38%|███▊ | 19/50 [00:02<00:03, 9.04it/s] 40%|████ | 20/50 [00:02<00:03, 9.04it/s] 42%|████▏ | 21/50 [00:02<00:03, 9.04it/s] 44%|████▍ | 22/50 [00:02<00:03, 9.04it/s] 46%|████▌ | 23/50 [00:02<00:02, 9.04it/s] 48%|████▊ | 24/50 [00:02<00:02, 9.04it/s] 50%|█████ | 25/50 [00:02<00:02, 9.04it/s] 52%|█████▏ | 26/50 [00:02<00:02, 9.04it/s] 54%|█████▍ | 27/50 [00:02<00:02, 9.04it/s] 56%|█████▌ | 28/50 [00:03<00:02, 9.04it/s] 58%|█████▊ | 29/50 [00:03<00:02, 9.04it/s] 60%|██████ | 30/50 [00:03<00:02, 9.04it/s] 62%|██████▏ | 31/50 [00:03<00:02, 9.04it/s] 64%|██████▍ | 32/50 [00:03<00:01, 9.04it/s] 66%|██████▌ | 33/50 [00:03<00:01, 9.04it/s] 68%|██████▊ | 34/50 [00:03<00:01, 9.04it/s] 70%|███████ | 35/50 [00:03<00:01, 9.04it/s] 72%|███████▏ | 36/50 [00:03<00:01, 9.04it/s] 74%|███████▍ | 37/50 [00:04<00:01, 9.04it/s] 76%|███████▌ | 38/50 [00:04<00:01, 9.04it/s] 78%|███████▊ | 39/50 [00:04<00:01, 9.02it/s] 80%|████████ | 40/50 [00:04<00:01, 9.02it/s] 82%|████████▏ | 41/50 [00:04<00:00, 9.02it/s] 84%|████████▍ | 42/50 [00:04<00:00, 9.03it/s] 86%|████████▌ | 43/50 [00:04<00:00, 9.03it/s] 88%|████████▊ | 44/50 [00:04<00:00, 9.03it/s] 90%|█████████ | 45/50 [00:04<00:00, 9.03it/s] 92%|█████████▏| 46/50 [00:05<00:00, 9.03it/s] 94%|█████████▍| 47/50 [00:05<00:00, 9.04it/s] 96%|█████████▌| 48/50 [00:05<00:00, 9.04it/s] 98%|█████████▊| 49/50 [00:05<00:00, 9.02it/s] 100%|██████████| 50/50 [00:05<00:00, 9.02it/s] 100%|██████████| 50/50 [00:05<00:00, 9.12it/s]
Want to make some of these yourself?
Run this model