Set the pipeline tag back to image-to-video

Set the pipeline tag to text-to-video; the model does both t2v and i2v

Document the text-to-video entry point

Trim the model card to capabilities, benchmarks and usage

Add UMT5-xxl text encoder

Add Wan2.2 VAE

Add UMT5 tokenizer

Add backbone module definition

Update model card from the 1.0 technical report; add HF metadata

Update README.md

Upload model-00003-of-00003.safetensors with huggingface_hub

Upload model-00002-of-00003.safetensors with huggingface_hub

Upload model-00001-of-00003.safetensors with huggingface_hub

Upload model.safetensors.index.json with huggingface_hub

Upload config.json with huggingface_hub

Upload README.md with huggingface_hub

Upload LICENSE with huggingface_hub

initial commit