Instructions to use MDFJ/stable-art-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use MDFJ/stable-art-1 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("MDFJ/stable-art-1", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
metadata
license: apache-2.0
pipeline_tag: text-to-image
datasets:
- MDFJ/japku
library_name: diffusers
What is Stable Art?
Stable Art is an image model where:
CC BY, CC BY-SA, CC0 images and public domain images are used.
image licenses that are NOT used:
CC BY-NC-ND
CC BY-NC-SA
CC BY-NC
CC BY-ND
Why aren't NC-SA, NC, and ND used?
Here are some explanations:
- NC: You can't use the material for commercial purposes.
- ND: You can't make derivative versions.
For more information in version 4.0:
Stable Art doesn't use just one dataset. It uses multiple datasets per category, for example:
- anime
- realistic
- others