ComfyUI wrapper nodes for HunyuanVideo

WORK IN PROGRESS

Currently seems to require flash_attn (default) or sageattn, spda is not working

Transformer and VAE (single files, no autodownload):

Go to the usual ComfyUI folders (diffusion_models and vae)

LLM text encoder (has autodownload):

Files go to ComfyUI/models/LLM/llava-llama-3-8b-text-encoder-tokenizer

Clip text encoder (has autodownload)

For now using the original https://huggingface.co/openai/clip-vit-large-patch14, files (only need the .safetensor from the weights) go to:

ComfyUI/models/clip/clip-vit-large-patch14

Memory use is entirely dependant on resolution and frame count, don't expect to be able to go very high even on 24GB.

Good news is that the model can do functional videos even at really low resolutions.