32 lines
1.0 KiB
Markdown
32 lines
1.0 KiB
Markdown
# ComfyUI wrapper nodes for [HunyuanVideo](https://github.com/Tencent/HunyuanVideo)
|
|
|
|
## WORK IN PROGRESS
|
|
|
|
|
|
https://github.com/user-attachments/assets/3750da65-9753-4bd2-aae2-a688d2b86115
|
|
|
|
|
|
**Currently seems to require flash_attn (default) or sageattn, spda is not working**
|
|
|
|
Transformer and VAE (single files, no autodownload):
|
|
|
|
https://huggingface.co/Kijai/HunyuanVideo_comfy/tree/main
|
|
|
|
Go to the usual ComfyUI folders (diffusion_models and vae)
|
|
|
|
LLM text encoder (has autodownload):
|
|
|
|
https://huggingface.co/Kijai/llava-llama-3-8b-text-encoder-tokenizer
|
|
|
|
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.
|