# genmoai/mochi

The best OSS video generation models, created by Genmo

Repository: https://github.com/genmoai/mochi
Canonical: https://ross.abutalabs.com/products/mochi
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2025-11-14T01:17:56+00:00

## Health v2 (maintenance only)
Score: 46/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 52, release rhythm 35, longevity 51
- inputs: {"age_days": 721, "days_push": 293, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3713, forks 489 (observed 2026-08-28T04:08:15.287438+00:00)

## What it is
Mochi 1 is Genmo's open-source, state-of-the-art text-to-video generation model released under Apache 2.0, with a Python API, CLI, and Gradio UI for generating high-fidelity videos from prompts. It supports LoRA fine-tuning and consumer-GPU inference via ComfyUI.

## Use cases
- generate videos from text prompts
- run an open source text-to-video model locally
- fine-tune a video generation model with LoRA
- generate videos on a consumer GPU
- programmatically generate videos with a Python API
- self-host a video generation model

## When to choose
- you need an open-weights, permissively licensed video generation model
- you want to fine-tune video generation on your own data with LoRA
- you want a Python API or CLI for text-to-video generation

## When to avoid
- you need production video generation without managing GPU hardware and large model weights
- you only need image generation rather than video
- you lack a capable GPU or are unwilling to use CPU offloading

## Facets
- artifact type: library
- maturity: active
- function: video-processing, machine-learning, deep-learning, llm-inference
- domain: artificial-intelligence, machine-learning, deep-learning
- platform: python, cli
- tags: text-to-video, video-generation, diffusion-model, lora-fine-tuning, gradio, comfyui, open-weights, video, gpu, linux

## Member repositories
- genmoai/mochi (main) score 46

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:15.287438+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:30:52.759224+00:00, confidence not recorded.
  - readme: https://github.com/genmoai/mochi (fetched 2026-08-28T04:08:15.287438+00:00, sha 0b554c926aa4)
- Data as of 2026-08-30T08:39:29.467469+00:00.