lucataco
/
pixart-sigma-900m
PixArt Sigma 900M is a text-to-image generation model based on the PixArt Sigma architecture
Prediction
lucataco/pixart-sigma-900m:c9e6b6f8IDbde5w23yysrgm0cgn8r8j6n3wrStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- high quality pixel art, a pixel art silhouette of an anime space-themed girl in a space-punk steampunk style, lying in her bed by the window of a spaceship, smoking, with a rustic feel. The image should embody epic portraiture and double exposure, featuring an isolated landscape visible through the window. The colors should primarily be dynamic and action-packed, with a strong use of negative space. The entire artwork should be in pixel art style, emphasizing the characters shape and set against a white background. Silhouette
- guidance_scale
- 3
- negative_prompt
- num_inference_steps
- 20
{ "width": 1024, "height": 1024, "prompt": "high quality pixel art, a pixel art silhouette of an anime space-themed girl in a space-punk steampunk style, lying in her bed by the window of a spaceship, smoking, with a rustic feel. The image should embody epic portraiture and double exposure, featuring an isolated landscape visible through the window. The colors should primarily be dynamic and action-packed, with a strong use of negative space. The entire artwork should be in pixel art style, emphasizing the characters shape and set against a white background. Silhouette", "guidance_scale": 3, "negative_prompt": "", "num_inference_steps": 20 }
Install Replicate’s Node.js client library:npm install replicate
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run lucataco/pixart-sigma-900m using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/pixart-sigma-900m:c9e6b6f85c8ef629e088031cb85d9918c0cfdc3a11c8a9fb4ca3c16b78a8f9d5", { input: { width: 1024, height: 1024, prompt: "high quality pixel art, a pixel art silhouette of an anime space-themed girl in a space-punk steampunk style, lying in her bed by the window of a spaceship, smoking, with a rustic feel. The image should embody epic portraiture and double exposure, featuring an isolated landscape visible through the window. The colors should primarily be dynamic and action-packed, with a strong use of negative space. The entire artwork should be in pixel art style, emphasizing the characters shape and set against a white background. Silhouette", guidance_scale: 3, negative_prompt: "", num_inference_steps: 20 } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the client:import replicate
Run lucataco/pixart-sigma-900m using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/pixart-sigma-900m:c9e6b6f85c8ef629e088031cb85d9918c0cfdc3a11c8a9fb4ca3c16b78a8f9d5", input={ "width": 1024, "height": 1024, "prompt": "high quality pixel art, a pixel art silhouette of an anime space-themed girl in a space-punk steampunk style, lying in her bed by the window of a spaceship, smoking, with a rustic feel. The image should embody epic portraiture and double exposure, featuring an isolated landscape visible through the window. The colors should primarily be dynamic and action-packed, with a strong use of negative space. The entire artwork should be in pixel art style, emphasizing the characters shape and set against a white background. Silhouette", "guidance_scale": 3, "negative_prompt": "", "num_inference_steps": 20 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run lucataco/pixart-sigma-900m 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": "c9e6b6f85c8ef629e088031cb85d9918c0cfdc3a11c8a9fb4ca3c16b78a8f9d5", "input": { "width": 1024, "height": 1024, "prompt": "high quality pixel art, a pixel art silhouette of an anime space-themed girl in a space-punk steampunk style, lying in her bed by the window of a spaceship, smoking, with a rustic feel. The image should embody epic portraiture and double exposure, featuring an isolated landscape visible through the window. The colors should primarily be dynamic and action-packed, with a strong use of negative space. The entire artwork should be in pixel art style, emphasizing the characters shape and set against a white background. Silhouette", "guidance_scale": 3, "negative_prompt": "", "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/lucataco/pixart-sigma-900m@sha256:c9e6b6f85c8ef629e088031cb85d9918c0cfdc3a11c8a9fb4ca3c16b78a8f9d5 \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="high quality pixel art, a pixel art silhouette of an anime space-themed girl in a space-punk steampunk style, lying in her bed by the window of a spaceship, smoking, with a rustic feel. The image should embody epic portraiture and double exposure, featuring an isolated landscape visible through the window. The colors should primarily be dynamic and action-packed, with a strong use of negative space. The entire artwork should be in pixel art style, emphasizing the characters shape and set against a white background. Silhouette"' \ -i 'guidance_scale=3' \ -i 'negative_prompt=""' \ -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/lucataco/pixart-sigma-900m@sha256:c9e6b6f85c8ef629e088031cb85d9918c0cfdc3a11c8a9fb4ca3c16b78a8f9d5
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "high quality pixel art, a pixel art silhouette of an anime space-themed girl in a space-punk steampunk style, lying in her bed by the window of a spaceship, smoking, with a rustic feel. The image should embody epic portraiture and double exposure, featuring an isolated landscape visible through the window. The colors should primarily be dynamic and action-packed, with a strong use of negative space. The entire artwork should be in pixel art style, emphasizing the characters shape and set against a white background. Silhouette", "guidance_scale": 3, "negative_prompt": "", "num_inference_steps": 20 } }' \ http://localhost:5000/predictions
To learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2024-07-13T03:47:15.757661Z", "created_at": "2024-07-13T03:43:43.350000Z", "data_removed": false, "error": null, "id": "bde5w23yysrgm0cgn8r8j6n3wr", "input": { "width": 1024, "height": 1024, "prompt": "high quality pixel art, a pixel art silhouette of an anime space-themed girl in a space-punk steampunk style, lying in her bed by the window of a spaceship, smoking, with a rustic feel. The image should embody epic portraiture and double exposure, featuring an isolated landscape visible through the window. The colors should primarily be dynamic and action-packed, with a strong use of negative space. The entire artwork should be in pixel art style, emphasizing the characters shape and set against a white background. Silhouette", "guidance_scale": 3, "negative_prompt": "", "num_inference_steps": 20 }, "logs": "Using seed: 16147\nSetting `clean_caption=True` requires the Beautiful Soup library but it was not found in your environment. You can install it with pip:\n`pip install beautifulsoup4`. Please note that you may need to restart your runtime after installation.\nSetting `clean_caption` to False...\nSetting `clean_caption=True` requires the Beautiful Soup library but it was not found in your environment. You can install it with pip:\n`pip install beautifulsoup4`. Please note that you may need to restart your runtime after installation.\nSetting `clean_caption` to False...\n 0%| | 0/20 [00:00<?, ?it/s]\n 5%|▌ | 1/20 [00:00<00:07, 2.57it/s]\n 15%|█▌ | 3/20 [00:00<00:04, 4.21it/s]\n 20%|██ | 4/20 [00:01<00:04, 3.92it/s]\n 25%|██▌ | 5/20 [00:01<00:03, 3.75it/s]\n 30%|███ | 6/20 [00:01<00:03, 3.66it/s]\n 35%|███▌ | 7/20 [00:01<00:03, 3.59it/s]\n 40%|████ | 8/20 [00:02<00:03, 3.55it/s]\n 45%|████▌ | 9/20 [00:02<00:03, 3.52it/s]\n 50%|█████ | 10/20 [00:02<00:02, 3.50it/s]\n 55%|█████▌ | 11/20 [00:03<00:02, 3.48it/s]\n 60%|██████ | 12/20 [00:03<00:02, 3.47it/s]\n 65%|██████▌ | 13/20 [00:03<00:02, 3.47it/s]\n 70%|███████ | 14/20 [00:03<00:01, 3.46it/s]\n 75%|███████▌ | 15/20 [00:04<00:01, 3.46it/s]\n 80%|████████ | 16/20 [00:04<00:01, 3.45it/s]\n 85%|████████▌ | 17/20 [00:04<00:00, 3.45it/s]\n 90%|█████████ | 18/20 [00:05<00:00, 3.45it/s]\n 95%|█████████▌| 19/20 [00:05<00:00, 3.45it/s]\n100%|██████████| 20/20 [00:05<00:00, 3.45it/s]\n100%|██████████| 20/20 [00:05<00:00, 3.52it/s]", "metrics": { "predict_time": 8.002685324, "total_time": 212.407661 }, "output": "https://replicate.delivery/pbxt/slwBMxLHvjqOHJZZmIITSryscVBFEMTHIpBccxW99QkwqejJA/output.jpg", "started_at": "2024-07-13T03:47:07.754976Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/bde5w23yysrgm0cgn8r8j6n3wr", "cancel": "https://api.replicate.com/v1/predictions/bde5w23yysrgm0cgn8r8j6n3wr/cancel" }, "version": "c9e6b6f85c8ef629e088031cb85d9918c0cfdc3a11c8a9fb4ca3c16b78a8f9d5" }
Generated inUsing seed: 16147 Setting `clean_caption=True` requires the Beautiful Soup library but it was not found in your environment. You can install it with pip: `pip install beautifulsoup4`. Please note that you may need to restart your runtime after installation. Setting `clean_caption` to False... Setting `clean_caption=True` requires the Beautiful Soup library but it was not found in your environment. You can install it with pip: `pip install beautifulsoup4`. Please note that you may need to restart your runtime after installation. Setting `clean_caption` to False... 0%| | 0/20 [00:00<?, ?it/s] 5%|▌ | 1/20 [00:00<00:07, 2.57it/s] 15%|█▌ | 3/20 [00:00<00:04, 4.21it/s] 20%|██ | 4/20 [00:01<00:04, 3.92it/s] 25%|██▌ | 5/20 [00:01<00:03, 3.75it/s] 30%|███ | 6/20 [00:01<00:03, 3.66it/s] 35%|███▌ | 7/20 [00:01<00:03, 3.59it/s] 40%|████ | 8/20 [00:02<00:03, 3.55it/s] 45%|████▌ | 9/20 [00:02<00:03, 3.52it/s] 50%|█████ | 10/20 [00:02<00:02, 3.50it/s] 55%|█████▌ | 11/20 [00:03<00:02, 3.48it/s] 60%|██████ | 12/20 [00:03<00:02, 3.47it/s] 65%|██████▌ | 13/20 [00:03<00:02, 3.47it/s] 70%|███████ | 14/20 [00:03<00:01, 3.46it/s] 75%|███████▌ | 15/20 [00:04<00:01, 3.46it/s] 80%|████████ | 16/20 [00:04<00:01, 3.45it/s] 85%|████████▌ | 17/20 [00:04<00:00, 3.45it/s] 90%|█████████ | 18/20 [00:05<00:00, 3.45it/s] 95%|█████████▌| 19/20 [00:05<00:00, 3.45it/s] 100%|██████████| 20/20 [00:05<00:00, 3.45it/s] 100%|██████████| 20/20 [00:05<00:00, 3.52it/s]
Prediction
lucataco/pixart-sigma-900m:c9e6b6f8IDwb5d0yvsynrgm0cgn8t9n9hs14StatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- black fluffy gorgeous dangerous cat animal creature, large orange eyes, big fluffy ears, piercing gaze, full moon, dark ambiance, best quality, extremely detailed
- guidance_scale
- 5
- negative_prompt
- num_inference_steps
- 20
{ "width": 1024, "height": 1024, "prompt": "black fluffy gorgeous dangerous cat animal creature, large orange eyes, big fluffy ears, piercing gaze, full moon, dark ambiance, best quality, extremely detailed", "guidance_scale": 5, "negative_prompt": "", "num_inference_steps": 20 }
Install Replicate’s Node.js client library:npm install replicate
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run lucataco/pixart-sigma-900m using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/pixart-sigma-900m:c9e6b6f85c8ef629e088031cb85d9918c0cfdc3a11c8a9fb4ca3c16b78a8f9d5", { input: { width: 1024, height: 1024, prompt: "black fluffy gorgeous dangerous cat animal creature, large orange eyes, big fluffy ears, piercing gaze, full moon, dark ambiance, best quality, extremely detailed", guidance_scale: 5, negative_prompt: "", num_inference_steps: 20 } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the client:import replicate
Run lucataco/pixart-sigma-900m using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/pixart-sigma-900m:c9e6b6f85c8ef629e088031cb85d9918c0cfdc3a11c8a9fb4ca3c16b78a8f9d5", input={ "width": 1024, "height": 1024, "prompt": "black fluffy gorgeous dangerous cat animal creature, large orange eyes, big fluffy ears, piercing gaze, full moon, dark ambiance, best quality, extremely detailed", "guidance_scale": 5, "negative_prompt": "", "num_inference_steps": 20 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run lucataco/pixart-sigma-900m 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": "c9e6b6f85c8ef629e088031cb85d9918c0cfdc3a11c8a9fb4ca3c16b78a8f9d5", "input": { "width": 1024, "height": 1024, "prompt": "black fluffy gorgeous dangerous cat animal creature, large orange eyes, big fluffy ears, piercing gaze, full moon, dark ambiance, best quality, extremely detailed", "guidance_scale": 5, "negative_prompt": "", "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/lucataco/pixart-sigma-900m@sha256:c9e6b6f85c8ef629e088031cb85d9918c0cfdc3a11c8a9fb4ca3c16b78a8f9d5 \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="black fluffy gorgeous dangerous cat animal creature, large orange eyes, big fluffy ears, piercing gaze, full moon, dark ambiance, best quality, extremely detailed"' \ -i 'guidance_scale=5' \ -i 'negative_prompt=""' \ -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/lucataco/pixart-sigma-900m@sha256:c9e6b6f85c8ef629e088031cb85d9918c0cfdc3a11c8a9fb4ca3c16b78a8f9d5
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "black fluffy gorgeous dangerous cat animal creature, large orange eyes, big fluffy ears, piercing gaze, full moon, dark ambiance, best quality, extremely detailed", "guidance_scale": 5, "negative_prompt": "", "num_inference_steps": 20 } }' \ http://localhost:5000/predictions
To learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2024-07-13T03:48:11.639825Z", "created_at": "2024-07-13T03:48:04.213000Z", "data_removed": false, "error": null, "id": "wb5d0yvsynrgm0cgn8t9n9hs14", "input": { "width": 1024, "height": 1024, "prompt": "black fluffy gorgeous dangerous cat animal creature, large orange eyes, big fluffy ears, piercing gaze, full moon, dark ambiance, best quality, extremely detailed", "guidance_scale": 5, "negative_prompt": "", "num_inference_steps": 20 }, "logs": "Using seed: 23753\nSetting `clean_caption=True` requires the Beautiful Soup library but it was not found in your environment. You can install it with pip:\n`pip install beautifulsoup4`. Please note that you may need to restart your runtime after installation.\nSetting `clean_caption` to False...\nSetting `clean_caption=True` requires the Beautiful Soup library but it was not found in your environment. You can install it with pip:\n`pip install beautifulsoup4`. Please note that you may need to restart your runtime after installation.\nSetting `clean_caption` to False...\n 0%| | 0/20 [00:00<?, ?it/s]\n 5%|▌ | 1/20 [00:00<00:05, 3.44it/s]\n 15%|█▌ | 3/20 [00:00<00:03, 4.71it/s]\n 20%|██ | 4/20 [00:00<00:03, 4.19it/s]\n 25%|██▌ | 5/20 [00:01<00:03, 3.92it/s]\n 30%|███ | 6/20 [00:01<00:03, 3.76it/s]\n 35%|███▌ | 7/20 [00:01<00:03, 3.66it/s]\n 40%|████ | 8/20 [00:02<00:03, 3.59it/s]\n 45%|████▌ | 9/20 [00:02<00:03, 3.55it/s]\n 50%|█████ | 10/20 [00:02<00:02, 3.51it/s]\n 55%|█████▌ | 11/20 [00:02<00:02, 3.49it/s]\n 60%|██████ | 12/20 [00:03<00:02, 3.47it/s]\n 65%|██████▌ | 13/20 [00:03<00:02, 3.46it/s]\n 70%|███████ | 14/20 [00:03<00:01, 3.46it/s]\n 75%|███████▌ | 15/20 [00:04<00:01, 3.45it/s]\n 80%|████████ | 16/20 [00:04<00:01, 3.45it/s]\n 85%|████████▌ | 17/20 [00:04<00:00, 3.44it/s]\n 90%|█████████ | 18/20 [00:05<00:00, 3.44it/s]\n 95%|█████████▌| 19/20 [00:05<00:00, 3.44it/s]\n100%|██████████| 20/20 [00:05<00:00, 3.44it/s]\n100%|██████████| 20/20 [00:05<00:00, 3.57it/s]", "metrics": { "predict_time": 7.388063615, "total_time": 7.426825 }, "output": "https://replicate.delivery/pbxt/tRHyxYUqu8L5EpGajFP9MXB8ezSLQEFYpOrUueChzKp6r6HTA/output.jpg", "started_at": "2024-07-13T03:48:04.251762Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/wb5d0yvsynrgm0cgn8t9n9hs14", "cancel": "https://api.replicate.com/v1/predictions/wb5d0yvsynrgm0cgn8t9n9hs14/cancel" }, "version": "c9e6b6f85c8ef629e088031cb85d9918c0cfdc3a11c8a9fb4ca3c16b78a8f9d5" }
Generated inUsing seed: 23753 Setting `clean_caption=True` requires the Beautiful Soup library but it was not found in your environment. You can install it with pip: `pip install beautifulsoup4`. Please note that you may need to restart your runtime after installation. Setting `clean_caption` to False... Setting `clean_caption=True` requires the Beautiful Soup library but it was not found in your environment. You can install it with pip: `pip install beautifulsoup4`. Please note that you may need to restart your runtime after installation. Setting `clean_caption` to False... 0%| | 0/20 [00:00<?, ?it/s] 5%|▌ | 1/20 [00:00<00:05, 3.44it/s] 15%|█▌ | 3/20 [00:00<00:03, 4.71it/s] 20%|██ | 4/20 [00:00<00:03, 4.19it/s] 25%|██▌ | 5/20 [00:01<00:03, 3.92it/s] 30%|███ | 6/20 [00:01<00:03, 3.76it/s] 35%|███▌ | 7/20 [00:01<00:03, 3.66it/s] 40%|████ | 8/20 [00:02<00:03, 3.59it/s] 45%|████▌ | 9/20 [00:02<00:03, 3.55it/s] 50%|█████ | 10/20 [00:02<00:02, 3.51it/s] 55%|█████▌ | 11/20 [00:02<00:02, 3.49it/s] 60%|██████ | 12/20 [00:03<00:02, 3.47it/s] 65%|██████▌ | 13/20 [00:03<00:02, 3.46it/s] 70%|███████ | 14/20 [00:03<00:01, 3.46it/s] 75%|███████▌ | 15/20 [00:04<00:01, 3.45it/s] 80%|████████ | 16/20 [00:04<00:01, 3.45it/s] 85%|████████▌ | 17/20 [00:04<00:00, 3.44it/s] 90%|█████████ | 18/20 [00:05<00:00, 3.44it/s] 95%|█████████▌| 19/20 [00:05<00:00, 3.44it/s] 100%|██████████| 20/20 [00:05<00:00, 3.44it/s] 100%|██████████| 20/20 [00:05<00:00, 3.57it/s]
Prediction
lucataco/pixart-sigma-900m:c9e6b6f8IDzwwjqrps95rgg0cgn8tvsrxg1cStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- Super Closeup Portrait, action shot, Profoundly dark whitish meadow, glass flowers, Stains, space grunge style, Jeanne dArc wearing White Olive green used styled Cotton frock, Wielding thin silver sword, Sci-fi vibe, dirty, noisy, Vintage monk style, very detailed, hd
- guidance_scale
- 5
- negative_prompt
- worst, artifacts, deformed, distorted
- num_inference_steps
- 20
{ "width": 1024, "height": 1024, "prompt": "Super Closeup Portrait, action shot, Profoundly dark whitish meadow, glass flowers, Stains, space grunge style, Jeanne dArc wearing White Olive green used styled Cotton frock, Wielding thin silver sword, Sci-fi vibe, dirty, noisy, Vintage monk style, very detailed, hd", "guidance_scale": 5, "negative_prompt": "worst, artifacts, deformed, distorted ", "num_inference_steps": 20 }
Install Replicate’s Node.js client library:npm install replicate
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run lucataco/pixart-sigma-900m using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/pixart-sigma-900m:c9e6b6f85c8ef629e088031cb85d9918c0cfdc3a11c8a9fb4ca3c16b78a8f9d5", { input: { width: 1024, height: 1024, prompt: "Super Closeup Portrait, action shot, Profoundly dark whitish meadow, glass flowers, Stains, space grunge style, Jeanne dArc wearing White Olive green used styled Cotton frock, Wielding thin silver sword, Sci-fi vibe, dirty, noisy, Vintage monk style, very detailed, hd", guidance_scale: 5, negative_prompt: "worst, artifacts, deformed, distorted ", num_inference_steps: 20 } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the client:import replicate
Run lucataco/pixart-sigma-900m using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/pixart-sigma-900m:c9e6b6f85c8ef629e088031cb85d9918c0cfdc3a11c8a9fb4ca3c16b78a8f9d5", input={ "width": 1024, "height": 1024, "prompt": "Super Closeup Portrait, action shot, Profoundly dark whitish meadow, glass flowers, Stains, space grunge style, Jeanne dArc wearing White Olive green used styled Cotton frock, Wielding thin silver sword, Sci-fi vibe, dirty, noisy, Vintage monk style, very detailed, hd", "guidance_scale": 5, "negative_prompt": "worst, artifacts, deformed, distorted ", "num_inference_steps": 20 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run lucataco/pixart-sigma-900m 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": "c9e6b6f85c8ef629e088031cb85d9918c0cfdc3a11c8a9fb4ca3c16b78a8f9d5", "input": { "width": 1024, "height": 1024, "prompt": "Super Closeup Portrait, action shot, Profoundly dark whitish meadow, glass flowers, Stains, space grunge style, Jeanne dArc wearing White Olive green used styled Cotton frock, Wielding thin silver sword, Sci-fi vibe, dirty, noisy, Vintage monk style, very detailed, hd", "guidance_scale": 5, "negative_prompt": "worst, artifacts, deformed, distorted ", "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/lucataco/pixart-sigma-900m@sha256:c9e6b6f85c8ef629e088031cb85d9918c0cfdc3a11c8a9fb4ca3c16b78a8f9d5 \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="Super Closeup Portrait, action shot, Profoundly dark whitish meadow, glass flowers, Stains, space grunge style, Jeanne dArc wearing White Olive green used styled Cotton frock, Wielding thin silver sword, Sci-fi vibe, dirty, noisy, Vintage monk style, very detailed, hd"' \ -i 'guidance_scale=5' \ -i 'negative_prompt="worst, artifacts, deformed, distorted "' \ -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/lucataco/pixart-sigma-900m@sha256:c9e6b6f85c8ef629e088031cb85d9918c0cfdc3a11c8a9fb4ca3c16b78a8f9d5
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "Super Closeup Portrait, action shot, Profoundly dark whitish meadow, glass flowers, Stains, space grunge style, Jeanne dArc wearing White Olive green used styled Cotton frock, Wielding thin silver sword, Sci-fi vibe, dirty, noisy, Vintage monk style, very detailed, hd", "guidance_scale": 5, "negative_prompt": "worst, artifacts, deformed, distorted ", "num_inference_steps": 20 } }' \ http://localhost:5000/predictions
To learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2024-07-13T03:49:41.637583Z", "created_at": "2024-07-13T03:49:34.153000Z", "data_removed": false, "error": null, "id": "zwwjqrps95rgg0cgn8tvsrxg1c", "input": { "width": 1024, "height": 1024, "prompt": "Super Closeup Portrait, action shot, Profoundly dark whitish meadow, glass flowers, Stains, space grunge style, Jeanne dArc wearing White Olive green used styled Cotton frock, Wielding thin silver sword, Sci-fi vibe, dirty, noisy, Vintage monk style, very detailed, hd", "guidance_scale": 5, "negative_prompt": "worst, artifacts, deformed, distorted ", "num_inference_steps": 20 }, "logs": "Using seed: 43292\nSetting `clean_caption=True` requires the Beautiful Soup library but it was not found in your environment. You can install it with pip:\n`pip install beautifulsoup4`. Please note that you may need to restart your runtime after installation.\nSetting `clean_caption` to False...\nSetting `clean_caption=True` requires the Beautiful Soup library but it was not found in your environment. You can install it with pip:\n`pip install beautifulsoup4`. Please note that you may need to restart your runtime after installation.\nSetting `clean_caption` to False...\n 0%| | 0/20 [00:00<?, ?it/s]\n 5%|▌ | 1/20 [00:00<00:05, 3.43it/s]\n 15%|█▌ | 3/20 [00:00<00:03, 4.68it/s]\n 20%|██ | 4/20 [00:00<00:03, 4.10it/s]\n 25%|██▌ | 5/20 [00:01<00:03, 3.84it/s]\n 30%|███ | 6/20 [00:01<00:03, 3.70it/s]\n 35%|███▌ | 7/20 [00:01<00:03, 3.60it/s]\n 40%|████ | 8/20 [00:02<00:03, 3.55it/s]\n 45%|████▌ | 9/20 [00:02<00:03, 3.51it/s]\n 50%|█████ | 10/20 [00:02<00:02, 3.48it/s]\n 55%|█████▌ | 11/20 [00:03<00:02, 3.46it/s]\n 60%|██████ | 12/20 [00:03<00:02, 3.45it/s]\n 65%|██████▌ | 13/20 [00:03<00:02, 3.44it/s]\n 70%|███████ | 14/20 [00:03<00:01, 3.43it/s]\n 75%|███████▌ | 15/20 [00:04<00:01, 3.43it/s]\n 80%|████████ | 16/20 [00:04<00:01, 3.42it/s]\n 85%|████████▌ | 17/20 [00:04<00:00, 3.42it/s]\n 90%|█████████ | 18/20 [00:05<00:00, 3.41it/s]\n 95%|█████████▌| 19/20 [00:05<00:00, 3.41it/s]\n100%|██████████| 20/20 [00:05<00:00, 3.42it/s]\n100%|██████████| 20/20 [00:05<00:00, 3.54it/s]", "metrics": { "predict_time": 7.446382185, "total_time": 7.484583 }, "output": "https://replicate.delivery/pbxt/R3K2fhfEyXu5cElLLRrf1i0ZfROhPjSfCqSmFDqkAU3nqVfxE/output.jpg", "started_at": "2024-07-13T03:49:34.191201Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/zwwjqrps95rgg0cgn8tvsrxg1c", "cancel": "https://api.replicate.com/v1/predictions/zwwjqrps95rgg0cgn8tvsrxg1c/cancel" }, "version": "c9e6b6f85c8ef629e088031cb85d9918c0cfdc3a11c8a9fb4ca3c16b78a8f9d5" }
Generated inUsing seed: 43292 Setting `clean_caption=True` requires the Beautiful Soup library but it was not found in your environment. You can install it with pip: `pip install beautifulsoup4`. Please note that you may need to restart your runtime after installation. Setting `clean_caption` to False... Setting `clean_caption=True` requires the Beautiful Soup library but it was not found in your environment. You can install it with pip: `pip install beautifulsoup4`. Please note that you may need to restart your runtime after installation. Setting `clean_caption` to False... 0%| | 0/20 [00:00<?, ?it/s] 5%|▌ | 1/20 [00:00<00:05, 3.43it/s] 15%|█▌ | 3/20 [00:00<00:03, 4.68it/s] 20%|██ | 4/20 [00:00<00:03, 4.10it/s] 25%|██▌ | 5/20 [00:01<00:03, 3.84it/s] 30%|███ | 6/20 [00:01<00:03, 3.70it/s] 35%|███▌ | 7/20 [00:01<00:03, 3.60it/s] 40%|████ | 8/20 [00:02<00:03, 3.55it/s] 45%|████▌ | 9/20 [00:02<00:03, 3.51it/s] 50%|█████ | 10/20 [00:02<00:02, 3.48it/s] 55%|█████▌ | 11/20 [00:03<00:02, 3.46it/s] 60%|██████ | 12/20 [00:03<00:02, 3.45it/s] 65%|██████▌ | 13/20 [00:03<00:02, 3.44it/s] 70%|███████ | 14/20 [00:03<00:01, 3.43it/s] 75%|███████▌ | 15/20 [00:04<00:01, 3.43it/s] 80%|████████ | 16/20 [00:04<00:01, 3.42it/s] 85%|████████▌ | 17/20 [00:04<00:00, 3.42it/s] 90%|█████████ | 18/20 [00:05<00:00, 3.41it/s] 95%|█████████▌| 19/20 [00:05<00:00, 3.41it/s] 100%|██████████| 20/20 [00:05<00:00, 3.42it/s] 100%|██████████| 20/20 [00:05<00:00, 3.54it/s]
Prediction
lucataco/pixart-sigma-900m:c9e6b6f8ID08k5rfh2cxrgm0cgn8vamjmrawStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- cinematic film still of Kodak Motion Picture Film (Sharp Detailed Image) An Oscar winning movie for Best Cinematography a woman in a kimono standing on a subway train in Japan Kodak Motion Picture Film Style, shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy
- guidance_scale
- 5
- negative_prompt
- worst, artifacts, deformed, distorted
- num_inference_steps
- 20
{ "width": 1024, "height": 1024, "prompt": "cinematic film still of Kodak Motion Picture Film (Sharp Detailed Image) An Oscar winning movie for Best Cinematography a woman in a kimono standing on a subway train in Japan Kodak Motion Picture Film Style, shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy", "guidance_scale": 5, "negative_prompt": "worst, artifacts, deformed, distorted ", "num_inference_steps": 20 }
Install Replicate’s Node.js client library:npm install replicate
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run lucataco/pixart-sigma-900m using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/pixart-sigma-900m:c9e6b6f85c8ef629e088031cb85d9918c0cfdc3a11c8a9fb4ca3c16b78a8f9d5", { input: { width: 1024, height: 1024, prompt: "cinematic film still of Kodak Motion Picture Film (Sharp Detailed Image) An Oscar winning movie for Best Cinematography a woman in a kimono standing on a subway train in Japan Kodak Motion Picture Film Style, shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy", guidance_scale: 5, negative_prompt: "worst, artifacts, deformed, distorted ", num_inference_steps: 20 } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the client:import replicate
Run lucataco/pixart-sigma-900m using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/pixart-sigma-900m:c9e6b6f85c8ef629e088031cb85d9918c0cfdc3a11c8a9fb4ca3c16b78a8f9d5", input={ "width": 1024, "height": 1024, "prompt": "cinematic film still of Kodak Motion Picture Film (Sharp Detailed Image) An Oscar winning movie for Best Cinematography a woman in a kimono standing on a subway train in Japan Kodak Motion Picture Film Style, shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy", "guidance_scale": 5, "negative_prompt": "worst, artifacts, deformed, distorted ", "num_inference_steps": 20 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run lucataco/pixart-sigma-900m 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": "c9e6b6f85c8ef629e088031cb85d9918c0cfdc3a11c8a9fb4ca3c16b78a8f9d5", "input": { "width": 1024, "height": 1024, "prompt": "cinematic film still of Kodak Motion Picture Film (Sharp Detailed Image) An Oscar winning movie for Best Cinematography a woman in a kimono standing on a subway train in Japan Kodak Motion Picture Film Style, shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy", "guidance_scale": 5, "negative_prompt": "worst, artifacts, deformed, distorted ", "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/lucataco/pixart-sigma-900m@sha256:c9e6b6f85c8ef629e088031cb85d9918c0cfdc3a11c8a9fb4ca3c16b78a8f9d5 \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="cinematic film still of Kodak Motion Picture Film (Sharp Detailed Image) An Oscar winning movie for Best Cinematography a woman in a kimono standing on a subway train in Japan Kodak Motion Picture Film Style, shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy"' \ -i 'guidance_scale=5' \ -i 'negative_prompt="worst, artifacts, deformed, distorted "' \ -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/lucataco/pixart-sigma-900m@sha256:c9e6b6f85c8ef629e088031cb85d9918c0cfdc3a11c8a9fb4ca3c16b78a8f9d5
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "cinematic film still of Kodak Motion Picture Film (Sharp Detailed Image) An Oscar winning movie for Best Cinematography a woman in a kimono standing on a subway train in Japan Kodak Motion Picture Film Style, shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy", "guidance_scale": 5, "negative_prompt": "worst, artifacts, deformed, distorted ", "num_inference_steps": 20 } }' \ http://localhost:5000/predictions
To learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2024-07-13T03:50:00.328102Z", "created_at": "2024-07-13T03:49:52.871000Z", "data_removed": false, "error": null, "id": "08k5rfh2cxrgm0cgn8vamjmraw", "input": { "width": 1024, "height": 1024, "prompt": "cinematic film still of Kodak Motion Picture Film (Sharp Detailed Image) An Oscar winning movie for Best Cinematography a woman in a kimono standing on a subway train in Japan Kodak Motion Picture Film Style, shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy", "guidance_scale": 5, "negative_prompt": "worst, artifacts, deformed, distorted ", "num_inference_steps": 20 }, "logs": "Using seed: 28223\nSetting `clean_caption=True` requires the Beautiful Soup library but it was not found in your environment. You can install it with pip:\n`pip install beautifulsoup4`. Please note that you may need to restart your runtime after installation.\nSetting `clean_caption` to False...\nSetting `clean_caption=True` requires the Beautiful Soup library but it was not found in your environment. You can install it with pip:\n`pip install beautifulsoup4`. Please note that you may need to restart your runtime after installation.\nSetting `clean_caption` to False...\n 0%| | 0/20 [00:00<?, ?it/s]\n 5%|▌ | 1/20 [00:00<00:05, 3.44it/s]\n 15%|█▌ | 3/20 [00:00<00:03, 4.71it/s]\n 20%|██ | 4/20 [00:00<00:03, 4.17it/s]\n 25%|██▌ | 5/20 [00:01<00:03, 3.89it/s]\n 30%|███ | 6/20 [00:01<00:03, 3.73it/s]\n 35%|███▌ | 7/20 [00:01<00:03, 3.64it/s]\n 40%|████ | 8/20 [00:02<00:03, 3.56it/s]\n 45%|████▌ | 9/20 [00:02<00:03, 3.52it/s]\n 50%|█████ | 10/20 [00:02<00:02, 3.50it/s]\n 55%|█████▌ | 11/20 [00:02<00:02, 3.47it/s]\n 60%|██████ | 12/20 [00:03<00:02, 3.46it/s]\n 65%|██████▌ | 13/20 [00:03<00:02, 3.45it/s]\n 70%|███████ | 14/20 [00:03<00:01, 3.44it/s]\n 75%|███████▌ | 15/20 [00:04<00:01, 3.43it/s]\n 80%|████████ | 16/20 [00:04<00:01, 3.43it/s]\n 85%|████████▌ | 17/20 [00:04<00:00, 3.43it/s]\n 90%|█████████ | 18/20 [00:05<00:00, 3.42it/s]\n 95%|█████████▌| 19/20 [00:05<00:00, 3.42it/s]\n100%|██████████| 20/20 [00:05<00:00, 3.43it/s]\n100%|██████████| 20/20 [00:05<00:00, 3.56it/s]", "metrics": { "predict_time": 7.420112041, "total_time": 7.457102 }, "output": "https://replicate.delivery/pbxt/f6zMKKPFdd2gIqOwDCbkfURIbbQfeWHfjvXcRNimwu8eZrejJA/output.jpg", "started_at": "2024-07-13T03:49:52.907990Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/08k5rfh2cxrgm0cgn8vamjmraw", "cancel": "https://api.replicate.com/v1/predictions/08k5rfh2cxrgm0cgn8vamjmraw/cancel" }, "version": "c9e6b6f85c8ef629e088031cb85d9918c0cfdc3a11c8a9fb4ca3c16b78a8f9d5" }
Generated inUsing seed: 28223 Setting `clean_caption=True` requires the Beautiful Soup library but it was not found in your environment. You can install it with pip: `pip install beautifulsoup4`. Please note that you may need to restart your runtime after installation. Setting `clean_caption` to False... Setting `clean_caption=True` requires the Beautiful Soup library but it was not found in your environment. You can install it with pip: `pip install beautifulsoup4`. Please note that you may need to restart your runtime after installation. Setting `clean_caption` to False... 0%| | 0/20 [00:00<?, ?it/s] 5%|▌ | 1/20 [00:00<00:05, 3.44it/s] 15%|█▌ | 3/20 [00:00<00:03, 4.71it/s] 20%|██ | 4/20 [00:00<00:03, 4.17it/s] 25%|██▌ | 5/20 [00:01<00:03, 3.89it/s] 30%|███ | 6/20 [00:01<00:03, 3.73it/s] 35%|███▌ | 7/20 [00:01<00:03, 3.64it/s] 40%|████ | 8/20 [00:02<00:03, 3.56it/s] 45%|████▌ | 9/20 [00:02<00:03, 3.52it/s] 50%|█████ | 10/20 [00:02<00:02, 3.50it/s] 55%|█████▌ | 11/20 [00:02<00:02, 3.47it/s] 60%|██████ | 12/20 [00:03<00:02, 3.46it/s] 65%|██████▌ | 13/20 [00:03<00:02, 3.45it/s] 70%|███████ | 14/20 [00:03<00:01, 3.44it/s] 75%|███████▌ | 15/20 [00:04<00:01, 3.43it/s] 80%|████████ | 16/20 [00:04<00:01, 3.43it/s] 85%|████████▌ | 17/20 [00:04<00:00, 3.43it/s] 90%|█████████ | 18/20 [00:05<00:00, 3.42it/s] 95%|█████████▌| 19/20 [00:05<00:00, 3.42it/s] 100%|██████████| 20/20 [00:05<00:00, 3.43it/s] 100%|██████████| 20/20 [00:05<00:00, 3.56it/s]
Prediction
lucataco/pixart-sigma-900m:c9e6b6f8IDemce305005rgm0cgn8v92mm5vgStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- 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.cinematic film still of Kodak Motion Picture Film (Sharp Detailed Image) An Oscar winning movie for Best Cinematography a woman in a kimono standing on a subway train in Japan Kodak Motion Picture Film Style, shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy
- guidance_scale
- 5
- negative_prompt
- worst, artifacts, deformed, distorted
- num_inference_steps
- 20
{ "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.cinematic film still of Kodak Motion Picture Film (Sharp Detailed Image) An Oscar winning movie for Best Cinematography a woman in a kimono standing on a subway train in Japan Kodak Motion Picture Film Style, shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy", "guidance_scale": 5, "negative_prompt": "worst, artifacts, deformed, distorted ", "num_inference_steps": 20 }
Install Replicate’s Node.js client library:npm install replicate
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run lucataco/pixart-sigma-900m using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/pixart-sigma-900m:c9e6b6f85c8ef629e088031cb85d9918c0cfdc3a11c8a9fb4ca3c16b78a8f9d5", { 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.cinematic film still of Kodak Motion Picture Film (Sharp Detailed Image) An Oscar winning movie for Best Cinematography a woman in a kimono standing on a subway train in Japan Kodak Motion Picture Film Style, shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy", guidance_scale: 5, negative_prompt: "worst, artifacts, deformed, distorted ", num_inference_steps: 20 } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the client:import replicate
Run lucataco/pixart-sigma-900m using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/pixart-sigma-900m:c9e6b6f85c8ef629e088031cb85d9918c0cfdc3a11c8a9fb4ca3c16b78a8f9d5", 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.cinematic film still of Kodak Motion Picture Film (Sharp Detailed Image) An Oscar winning movie for Best Cinematography a woman in a kimono standing on a subway train in Japan Kodak Motion Picture Film Style, shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy", "guidance_scale": 5, "negative_prompt": "worst, artifacts, deformed, distorted ", "num_inference_steps": 20 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run lucataco/pixart-sigma-900m 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": "c9e6b6f85c8ef629e088031cb85d9918c0cfdc3a11c8a9fb4ca3c16b78a8f9d5", "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.cinematic film still of Kodak Motion Picture Film (Sharp Detailed Image) An Oscar winning movie for Best Cinematography a woman in a kimono standing on a subway train in Japan Kodak Motion Picture Film Style, shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy", "guidance_scale": 5, "negative_prompt": "worst, artifacts, deformed, distorted ", "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/lucataco/pixart-sigma-900m@sha256:c9e6b6f85c8ef629e088031cb85d9918c0cfdc3a11c8a9fb4ca3c16b78a8f9d5 \ -i 'width=1024' \ -i 'height=1024' \ -i '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.cinematic film still of Kodak Motion Picture Film (Sharp Detailed Image) An Oscar winning movie for Best Cinematography a woman in a kimono standing on a subway train in Japan Kodak Motion Picture Film Style, shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy"' \ -i 'guidance_scale=5' \ -i 'negative_prompt="worst, artifacts, deformed, distorted "' \ -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/lucataco/pixart-sigma-900m@sha256:c9e6b6f85c8ef629e088031cb85d9918c0cfdc3a11c8a9fb4ca3c16b78a8f9d5
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "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.cinematic film still of Kodak Motion Picture Film (Sharp Detailed Image) An Oscar winning movie for Best Cinematography a woman in a kimono standing on a subway train in Japan Kodak Motion Picture Film Style, shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy", "guidance_scale": 5, "negative_prompt": "worst, artifacts, deformed, distorted ", "num_inference_steps": 20 } }' \ http://localhost:5000/predictions
To learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2024-07-13T03:50:32.443319Z", "created_at": "2024-07-13T03:50:25.025000Z", "data_removed": false, "error": null, "id": "emce305005rgm0cgn8v92mm5vg", "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.cinematic film still of Kodak Motion Picture Film (Sharp Detailed Image) An Oscar winning movie for Best Cinematography a woman in a kimono standing on a subway train in Japan Kodak Motion Picture Film Style, shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy", "guidance_scale": 5, "negative_prompt": "worst, artifacts, deformed, distorted ", "num_inference_steps": 20 }, "logs": "Using seed: 58754\nSetting `clean_caption=True` requires the Beautiful Soup library but it was not found in your environment. You can install it with pip:\n`pip install beautifulsoup4`. Please note that you may need to restart your runtime after installation.\nSetting `clean_caption` to False...\nSetting `clean_caption=True` requires the Beautiful Soup library but it was not found in your environment. You can install it with pip:\n`pip install beautifulsoup4`. Please note that you may need to restart your runtime after installation.\nSetting `clean_caption` to False...\n 0%| | 0/20 [00:00<?, ?it/s]\n 5%|▌ | 1/20 [00:00<00:05, 3.43it/s]\n 15%|█▌ | 3/20 [00:00<00:03, 4.69it/s]\n 20%|██ | 4/20 [00:00<00:03, 4.17it/s]\n 25%|██▌ | 5/20 [00:01<00:03, 3.89it/s]\n 30%|███ | 6/20 [00:01<00:03, 3.73it/s]\n 35%|███▌ | 7/20 [00:01<00:03, 3.63it/s]\n 40%|████ | 8/20 [00:02<00:03, 3.56it/s]\n 45%|████▌ | 9/20 [00:02<00:03, 3.52it/s]\n 50%|█████ | 10/20 [00:02<00:02, 3.49it/s]\n 55%|█████▌ | 11/20 [00:02<00:02, 3.47it/s]\n 60%|██████ | 12/20 [00:03<00:02, 3.46it/s]\n 65%|██████▌ | 13/20 [00:03<00:02, 3.44it/s]\n 70%|███████ | 14/20 [00:03<00:01, 3.44it/s]\n 75%|███████▌ | 15/20 [00:04<00:01, 3.43it/s]\n 80%|████████ | 16/20 [00:04<00:01, 3.43it/s]\n 85%|████████▌ | 17/20 [00:04<00:00, 3.42it/s]\n 90%|█████████ | 18/20 [00:05<00:00, 3.42it/s]\n 95%|█████████▌| 19/20 [00:05<00:00, 3.42it/s]\n100%|██████████| 20/20 [00:05<00:00, 3.42it/s]\n100%|██████████| 20/20 [00:05<00:00, 3.55it/s]", "metrics": { "predict_time": 7.380652278, "total_time": 7.418319 }, "output": "https://replicate.delivery/pbxt/XZAb1lpMWGZ8AVFYqBsx1CQLSvXjL3bNNiYZEYk7KP7hrejJA/output.jpg", "started_at": "2024-07-13T03:50:25.062667Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/emce305005rgm0cgn8v92mm5vg", "cancel": "https://api.replicate.com/v1/predictions/emce305005rgm0cgn8v92mm5vg/cancel" }, "version": "c9e6b6f85c8ef629e088031cb85d9918c0cfdc3a11c8a9fb4ca3c16b78a8f9d5" }
Generated inUsing seed: 58754 Setting `clean_caption=True` requires the Beautiful Soup library but it was not found in your environment. You can install it with pip: `pip install beautifulsoup4`. Please note that you may need to restart your runtime after installation. Setting `clean_caption` to False... Setting `clean_caption=True` requires the Beautiful Soup library but it was not found in your environment. You can install it with pip: `pip install beautifulsoup4`. Please note that you may need to restart your runtime after installation. Setting `clean_caption` to False... 0%| | 0/20 [00:00<?, ?it/s] 5%|▌ | 1/20 [00:00<00:05, 3.43it/s] 15%|█▌ | 3/20 [00:00<00:03, 4.69it/s] 20%|██ | 4/20 [00:00<00:03, 4.17it/s] 25%|██▌ | 5/20 [00:01<00:03, 3.89it/s] 30%|███ | 6/20 [00:01<00:03, 3.73it/s] 35%|███▌ | 7/20 [00:01<00:03, 3.63it/s] 40%|████ | 8/20 [00:02<00:03, 3.56it/s] 45%|████▌ | 9/20 [00:02<00:03, 3.52it/s] 50%|█████ | 10/20 [00:02<00:02, 3.49it/s] 55%|█████▌ | 11/20 [00:02<00:02, 3.47it/s] 60%|██████ | 12/20 [00:03<00:02, 3.46it/s] 65%|██████▌ | 13/20 [00:03<00:02, 3.44it/s] 70%|███████ | 14/20 [00:03<00:01, 3.44it/s] 75%|███████▌ | 15/20 [00:04<00:01, 3.43it/s] 80%|████████ | 16/20 [00:04<00:01, 3.43it/s] 85%|████████▌ | 17/20 [00:04<00:00, 3.42it/s] 90%|█████████ | 18/20 [00:05<00:00, 3.42it/s] 95%|█████████▌| 19/20 [00:05<00:00, 3.42it/s] 100%|██████████| 20/20 [00:05<00:00, 3.42it/s] 100%|██████████| 20/20 [00:05<00:00, 3.55it/s]
Prediction
lucataco/pixart-sigma-900m:c9e6b6f8ID8hatjkpr61rgp0cgn8v9wtp9rrStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- anime girl
- guidance_scale
- 5
- negative_prompt
- worst, artifacts, deformed, distorted
- num_inference_steps
- 20
{ "width": 1024, "height": 1024, "prompt": "anime girl", "guidance_scale": 5, "negative_prompt": "worst, artifacts, deformed, distorted ", "num_inference_steps": 20 }
Install Replicate’s Node.js client library:npm install replicate
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run lucataco/pixart-sigma-900m using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/pixart-sigma-900m:c9e6b6f85c8ef629e088031cb85d9918c0cfdc3a11c8a9fb4ca3c16b78a8f9d5", { input: { width: 1024, height: 1024, prompt: "anime girl", guidance_scale: 5, negative_prompt: "worst, artifacts, deformed, distorted ", num_inference_steps: 20 } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the client:import replicate
Run lucataco/pixart-sigma-900m using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/pixart-sigma-900m:c9e6b6f85c8ef629e088031cb85d9918c0cfdc3a11c8a9fb4ca3c16b78a8f9d5", input={ "width": 1024, "height": 1024, "prompt": "anime girl", "guidance_scale": 5, "negative_prompt": "worst, artifacts, deformed, distorted ", "num_inference_steps": 20 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run lucataco/pixart-sigma-900m 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": "c9e6b6f85c8ef629e088031cb85d9918c0cfdc3a11c8a9fb4ca3c16b78a8f9d5", "input": { "width": 1024, "height": 1024, "prompt": "anime girl", "guidance_scale": 5, "negative_prompt": "worst, artifacts, deformed, distorted ", "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/lucataco/pixart-sigma-900m@sha256:c9e6b6f85c8ef629e088031cb85d9918c0cfdc3a11c8a9fb4ca3c16b78a8f9d5 \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="anime girl"' \ -i 'guidance_scale=5' \ -i 'negative_prompt="worst, artifacts, deformed, distorted "' \ -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/lucataco/pixart-sigma-900m@sha256:c9e6b6f85c8ef629e088031cb85d9918c0cfdc3a11c8a9fb4ca3c16b78a8f9d5
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "anime girl", "guidance_scale": 5, "negative_prompt": "worst, artifacts, deformed, distorted ", "num_inference_steps": 20 } }' \ http://localhost:5000/predictions
To learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2024-07-13T03:50:46.829379Z", "created_at": "2024-07-13T03:50:39.408000Z", "data_removed": false, "error": null, "id": "8hatjkpr61rgp0cgn8v9wtp9rr", "input": { "width": 1024, "height": 1024, "prompt": "anime girl", "guidance_scale": 5, "negative_prompt": "worst, artifacts, deformed, distorted ", "num_inference_steps": 20 }, "logs": "Using seed: 12225\nSetting `clean_caption=True` requires the Beautiful Soup library but it was not found in your environment. You can install it with pip:\n`pip install beautifulsoup4`. Please note that you may need to restart your runtime after installation.\nSetting `clean_caption` to False...\nSetting `clean_caption=True` requires the Beautiful Soup library but it was not found in your environment. You can install it with pip:\n`pip install beautifulsoup4`. Please note that you may need to restart your runtime after installation.\nSetting `clean_caption` to False...\n 0%| | 0/20 [00:00<?, ?it/s]\n 5%|▌ | 1/20 [00:00<00:05, 3.43it/s]\n 15%|█▌ | 3/20 [00:00<00:03, 4.69it/s]\n 20%|██ | 4/20 [00:00<00:03, 4.16it/s]\n 25%|██▌ | 5/20 [00:01<00:03, 3.88it/s]\n 30%|███ | 6/20 [00:01<00:03, 3.73it/s]\n 35%|███▌ | 7/20 [00:01<00:03, 3.63it/s]\n 40%|████ | 8/20 [00:02<00:03, 3.56it/s]\n 45%|████▌ | 9/20 [00:02<00:03, 3.52it/s]\n 50%|█████ | 10/20 [00:02<00:02, 3.49it/s]\n 55%|█████▌ | 11/20 [00:02<00:02, 3.47it/s]\n 60%|██████ | 12/20 [00:03<00:02, 3.45it/s]\n 65%|██████▌ | 13/20 [00:03<00:02, 3.44it/s]\n 70%|███████ | 14/20 [00:03<00:01, 3.44it/s]\n 75%|███████▌ | 15/20 [00:04<00:01, 3.43it/s]\n 80%|████████ | 16/20 [00:04<00:01, 3.43it/s]\n 85%|████████▌ | 17/20 [00:04<00:00, 3.42it/s]\n 90%|█████████ | 18/20 [00:05<00:00, 3.42it/s]\n 95%|█████████▌| 19/20 [00:05<00:00, 3.42it/s]\n100%|██████████| 20/20 [00:05<00:00, 3.42it/s]\n100%|██████████| 20/20 [00:05<00:00, 3.55it/s]", "metrics": { "predict_time": 7.383248017, "total_time": 7.421379 }, "output": "https://replicate.delivery/pbxt/267Mj8JNgirLFZ2EExlapfLfzbrVqj706FCGM9AwJhMVu6HTA/output.jpg", "started_at": "2024-07-13T03:50:39.446131Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/8hatjkpr61rgp0cgn8v9wtp9rr", "cancel": "https://api.replicate.com/v1/predictions/8hatjkpr61rgp0cgn8v9wtp9rr/cancel" }, "version": "c9e6b6f85c8ef629e088031cb85d9918c0cfdc3a11c8a9fb4ca3c16b78a8f9d5" }
Generated inUsing seed: 12225 Setting `clean_caption=True` requires the Beautiful Soup library but it was not found in your environment. You can install it with pip: `pip install beautifulsoup4`. Please note that you may need to restart your runtime after installation. Setting `clean_caption` to False... Setting `clean_caption=True` requires the Beautiful Soup library but it was not found in your environment. You can install it with pip: `pip install beautifulsoup4`. Please note that you may need to restart your runtime after installation. Setting `clean_caption` to False... 0%| | 0/20 [00:00<?, ?it/s] 5%|▌ | 1/20 [00:00<00:05, 3.43it/s] 15%|█▌ | 3/20 [00:00<00:03, 4.69it/s] 20%|██ | 4/20 [00:00<00:03, 4.16it/s] 25%|██▌ | 5/20 [00:01<00:03, 3.88it/s] 30%|███ | 6/20 [00:01<00:03, 3.73it/s] 35%|███▌ | 7/20 [00:01<00:03, 3.63it/s] 40%|████ | 8/20 [00:02<00:03, 3.56it/s] 45%|████▌ | 9/20 [00:02<00:03, 3.52it/s] 50%|█████ | 10/20 [00:02<00:02, 3.49it/s] 55%|█████▌ | 11/20 [00:02<00:02, 3.47it/s] 60%|██████ | 12/20 [00:03<00:02, 3.45it/s] 65%|██████▌ | 13/20 [00:03<00:02, 3.44it/s] 70%|███████ | 14/20 [00:03<00:01, 3.44it/s] 75%|███████▌ | 15/20 [00:04<00:01, 3.43it/s] 80%|████████ | 16/20 [00:04<00:01, 3.43it/s] 85%|████████▌ | 17/20 [00:04<00:00, 3.42it/s] 90%|█████████ | 18/20 [00:05<00:00, 3.42it/s] 95%|█████████▌| 19/20 [00:05<00:00, 3.42it/s] 100%|██████████| 20/20 [00:05<00:00, 3.42it/s] 100%|██████████| 20/20 [00:05<00:00, 3.55it/s]
Want to make some of these yourself?
Run this model