<h1 id="-j19muz68n"></h1>Fine-tuned on 10 million videos for exceptional image-to-video generation quality.The model is released under a permissive Apache2.0 license.To get started with ComfyUI;<ol><li>Update to the latest version of ComfyUI</li><li>Download CogVideoX model weights into <code>models/diffusion_models</code> folder, use "CogVideoXModelLoader" load</li><li>Make sure a text encoder [<a target="_blank" rel="ugc" href="https://civarchive.com/models/497255?modelVersionId=568405">1</a>] is in your <code>models/clip</code> folder</li><li>Download the VAE to: <code>ComfyUI/models/vae, use "</code>CogVideoXVAELoader<code>" load</code></li></ol> CogVideoX has <a target="_blank" rel="ugc" href="https://github.com/kijai/ComfyUI-CogVideoXWrapper">kijai ComfyUI support</a>, and will run on 6GB+ or 2GB VRAM.Github: <a target="_blank" rel="ugc" href="https://github.com/THUDM/CogVideo">https://github.com/THUDM/CogVideo</a>HuggingFace: <a target="_blank" rel="ugc" href="https://huggingface.co/NimVideo/cogvideox-2b-img2vid">https://huggingface.co/NimVideo/cogvideox-2b-img2vid</a>

CogVideox-2b-Img2Video

<ul><li>SHA256: 5c6a2b1ec65aab7a2004bfed5f1817861282d0cf50d6b10e92f09c27c78ca90b</li><li>Pointer size: 135 Bytes</li><li>Size of remote file: 3.39 GB</li></ul>

Files with SHA256: 5c6a2b1ec65aab7a2004bfed5f1817861282d0cf50d6b10e92f09c27c78ca90b