The model is released under a permissive CogVideoX license.
To get started with ComfyUI;
Update to the latest version of ComfyUI
Download CogVideoX model weights into
models/diffusion_modelsfolder, use "CogVideoXModelLoader" loadMake sure a text encoder [1] is in your
models/clipfolderDownload the VAE to:
ComfyUI/models/vae, use "CogVideoXVAELoader" load
CogVideoX has kijai ComfyUI support, and will run on 20GB+ or 9GB VRAM.
Github: https://github.com/THUDM/CogVideo
HuggingFace: https://huggingface.co/collections/THUDM/cogvideo-66c08e62f1685a3ade464cce
Description
sha256sum CogVideoX-VAE.safetensors
bd47d57ad948ff80da0af0cb2e4dcdef65073aba59bccfd383ada9a7d1c02024 CogVideoX-VAE.safetensors
CogVideoX is an open-source video generation model originating from Qingying. The table below presents information related to the video generation models we offer in this version.