Read our <a target="_blank" rel="ugc" href="https://education.civitai.com/civitais-quickstart-guide-to-mochi-1-text2video/">Quickstart Guide to Mochi</a> on the Civitai Education Hub!If you don't want to run it locally, you can try it out now on the Civitai Generator! Read the <a rel="ugc" href="https://education.civitai.com/civitais-guide-to-video-in-the-civitai-generator/">Guide to Video Generation in the Civitai Generator</a>!Mochi 1 preview, by creators <a target="_blank" rel="ugc" href="https://www.genmo.ai">https://www.genmo.ai</a>, is an open state-of-the-art video generation model with high-fidelity motion and strong prompt adherence in preliminary evaluation.This model dramatically closes the gap between closed and open video generation systems.The model is released under a permissive Apache 2.0 license.To get started with ComfyUI;<ol><li>Update to the latest version of ComfyUI</li><li>Download Mochi model weights into <code>models/diffusion_models</code> folder</li><li>Make sure a text encoder [<a target="_blank" rel="ugc" href="https://civarchive.com/models/497255?modelVersionId=568405">1</a>][<a target="_blank" rel="ugc" href="https://civarchive.com/models/497255?modelVersionId=568485">2</a>] is in your <code>models/clip</code> folder</li><li>Download the VAE to: <code>ComfyUI/models/vae</code></li></ol> Mochi has <a target="_blank" rel="ugc" href="https://blog.comfy.org/mochi-1/">native ComfyUI support</a>, and will run on 12GB+ VRAM.Github: <a target="_blank" rel="ugc" href="https://github.com/genmoai/models">https://github.com/genmoai/models</a>HuggingFace: <a target="_blank" rel="ugc" href="https://huggingface.co/genmo/mochi-1-preview">https://huggingface.co/genmo/mochi-1-preview</a>

Mochi 1 Preview - Video Model

Scaled Text Encoder for lower vram usage

Files with SHA256: a498f0485dc9536735258018417c3fd7758dc3bccc0a645feaa472b34955557a