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_modelsfolderMake sure a text encoder [1] is in your
models/clipfolderDownload the VAE to:
ComfyUI/models/vae
CogVideoX has kijai ComfyUI support, and will run on 20GB+ or 9GB VRAM.
Github: https://github.com/THUDM/CogVideo
HuggingFace: https://huggingface.co/THUDM/CogVideoX-5b-I2V
Description
sha256sum CogVideoX-5b-I2V_model.safetensors
ffa42f98baa354a04e445af43492562622df2c0bd9c4653b30d9251e732f8fe3 CogVideoX-5b-I2V_model.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.
FAQ
Comments (5)
can it be made to work in automatic1111 sd webui?
I just spent an hour looking on how to make this one and others work with ForgeUI. Gave up and downloaded Comfy.
lo mismo por mi lado, estuve 3 dias investigando, e investigando, pero nada de nada :c
instal comfyui, pero no logre hacerlo funcionar.
What folder does this go into comfyui?
I can't find the model weights on the github directory. Where do I go for them?
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.