Wan-AI
/

Wan2.1-VACE-1.3B

video generation

video-to-video editing

refernce-to-video

Model card Files Files and versions

Improve model card: Update pipeline tag, add library name, tags, and link NABLA paper

#5

by nielsr HF Staff - opened Jul 21, 2025

base: refs/heads/main

←

from: refs/pr/5

Discussion Files changed

This PR enhances the model card for Wan2.1 by:

Updating the pipeline_tag from image-to-video to any-to-any to accurately reflect the model's versatile capabilities (Text-to-Video, Image-to-Video, Video Editing, Text-to-Image, and Video-to-Audio generation). This will improve discoverability on the Hugging Face Hub.
Adding library_name: diffusers to the metadata. This enables the "Use in Diffusers" button and provides a seamless user experience, aligning with the provided code examples.
Adding relevant tags (diffusion, dit) to further describe the model's architecture.
Adding a prominent link to the paper $\nabla$NABLA: Neighborhood Adaptive Block-Level Attention, which details a key architectural innovation incorporated into this model.
Updating the citation section to refer to the NABLA paper as the primary scientific reference for this model.

Please review and merge this pull request.

Improve model card: Update pipeline tag, add library name, tags, and link NABLA papera1226c1d

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment