Instructions to use htdong/Wan-Alpha_ComfyUI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use htdong/Wan-Alpha_ComfyUI with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("htdong/Wan-Alpha_ComfyUI", 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
Add `library_name: diffusers` and comprehensive usage instructions
#3
by nielsr HF Staff - opened
This PR improves the model card for Wan-Alpha by:
- Adding the
library_name: diffusersmetadata tag. This enables the automated "how to use" widget on the model page, improving user experience and model discoverability. (This decision is based on a majority vote from colleague analyses, acknowledging potential evidence beyond the directly provided text snippets). - Incorporating comprehensive "Quick Start" and "Official ComfyUI Version" instructions, including code snippets and model download links, directly from the GitHub repository's README. This significantly enhances the model's usability by providing immediate, detailed usage guidance on the Hugging Face Hub page, replacing the previous generic link to GitHub.
- Adding the paper title and abstract at the top of the model card for better context.
- Preserving existing relevant information such as project page, GitHub, and arXiv links, as well as the model's overall structure and visual elements.
htdong changed pull request status to merged