Instructions to use raman07/CheXGenBench-Models-Sana-e20 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use raman07/CheXGenBench-Models-Sana-e20 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("raman07/CheXGenBench-Models-Sana-e20", 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
Commit History
-
Add model card for Sana 0.6B (CheXGenBench)
Verified signatureHi! I'm Niels, part of the community science team at Hugging Face. I noticed that this repository was missing a model card. This PR adds a README.md that: - Links the model to its original paper: [CheXGenBench: A Unified Benchmark For Fidelity, Privacy and Utility of Synthetic Chest Radiographs](https://huggingface.co/papers/2505.10496). - Includes relevant metadata such as the `pipeline_tag` and `library_name`. - Provides links to the project page and official GitHub repository. - Adds proper citation information. This ensures the model is correctly indexed on the Hub and easier for researchers to discover and cite.f528750
-
Add files using upload-large-folder tool
Verified signature5889483 -
initial commit
Verified signature89ef276