Sign In

CogVideoX-2b

10
195
6
Updated: Dec 5, 2024
base modelt2vcogvideox-2b
Verified:
SafeTensor
Type
Checkpoint Trained
Stats
195
Reviews
Published
Dec 5, 2024
Base Model
CogVideoX
Hash
AutoV2
8FBB6A5E67

The model is released under a permissive Apache2.0 license.

To get started with ComfyUI;

  1. Update to the latest version of ComfyUI

  2. Download CogVideoX model weights into models/diffusion_models folder, use "CogVideoXModelLoader" load

  3. Make sure a text encoder [1] is in your models/clip folder

  4. Download the VAE to: ComfyUI/models/vae, use "CogVideoXVAELoader" load


CogVideoX has kijai ComfyUI support, and will run on 12GB+ or 4GB VRAM.

Github: https://github.com/THUDM/CogVideo

HuggingFace: https://huggingface.co/THUDM/CogVideoX-2b