Instructions to use FastVideo/FastWan2.2-TI2V-5B-FullAttn-Diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use FastVideo/FastWan2.2-TI2V-5B-FullAttn-Diffusers with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("FastVideo/FastWan2.2-TI2V-5B-FullAttn-Diffusers", 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
Improve model card: Add pipeline tag, library name, and links
#2
by nielsr HF Staff - opened
This PR enhances the model card by:
- Adding the
pipeline_tag: text-to-videofor better model discoverability on the Hub. - Specifying
library_name: diffusersto enable the "Use in Diffusers" quickstart button and ensure proper integration. - Including the Hugging Face paper link alongside the existing arXiv link for the "VSA: Faster Video Diffusion with Trainable Sparse Attention" paper.
- Adding a link to the project's official documentation page for more context and resources.
BrianChen1129 changed pull request status to merged