Mochi 1 preview, by creators https://www.genmo.ai, 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;

1. Update to the latest version of ComfyUI

2. Download Mochi model weights into models/diffusion_models folder

3. Make sure a text encoder [1][2] is in your models/clip folder

4. Download the VAE to: ComfyUI/models/vae

Mochi has native ComfyUI support, and will run on 12GB+ VRAM.

If you don't want to run it locally, you can try it out for free, here https://www.genmo.ai/play

Github: https://github.com/genmoai/models

HuggingFace: https://huggingface.co/genmo/mochi-1-preview