Instructions to use Visualignment/safe-stable-diffusion-v2-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Visualignment/safe-stable-diffusion-v2-1 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Visualignment/safe-stable-diffusion-v2-1", 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
- Draw Things
- DiffusionBee
Add pipeline tag and update paper link/title
#1
by nielsr HF Staff - opened
This PR improves the model card by:
- Adding the
pipeline_tag: text-to-imageso the model can be discovered at https://huggingface.co/models?pipeline_tag=text-to-image. - Updating the model's description to accurately refer to the paper AlignGuard: Scalable Safety Alignment for Text-to-Image Generation.
- Aligning the display names of the project page and GitHub repository links with the paper's title.