genmoai/mochi
An open-source state-of-the-art video generation model that converts text prompts into high-fidelity motion videos using a diffusion-based architecture with VAE.
Not currently ranked — collecting fresh signals.
star history
Mochi 1 preview is a foundation model for text-to-video generation released by Genmo under an Apache 2.0 license. The model employs a diffusion architecture combined with a VAE (variational autoencoder) for video synthesis, achieving high-fidelity motion and strong prompt adherence. It supports consumer GPU inference, integration with ComfyUI, and LoRA fine-tuning for customization. Users can interact via a Gradio UI or programmatically via inference scripts.
Frequently asked
- What is genmoai/mochi?
- An open-source state-of-the-art video generation model that converts text prompts into high-fidelity motion videos using a diffusion-based architecture with VAE.
- Is mochi open source?
- Yes — genmoai/mochi is open source, released under the Apache-2.0 license.
- What language is mochi written in?
- genmoai/mochi is primarily written in Python.
- How popular is mochi?
- genmoai/mochi has 3.7k stars on GitHub.
- Where can I find mochi?
- genmoai/mochi is on GitHub at https://github.com/genmoai/mochi.