Open video models.

We're developing the world's best video models that understand the world just as we do.

Generate

Generate Random Prompt✦A slow-motion shot of a glass shattering on the floor, pieces scattering. The camera captures the intricate details of the breaking glass.✦A time-lapse of a city street artist creating a chalk mural on the sidewalk. The camera shows the artwork coming to life.✦A wide-angle shot of a theater stage from behind the curtains, actors preparing. The camera reveals the anticipation before the performance.

Explore Genmo

\
\
Research \
\
Mochi 1 is our cutting-edge open-source text-to-video model, crafted to turn your written concepts into engaging visual stories. \
\
Open Source \
\
You can run and customize Mochi using our open-source repository or ComfyUI, providing a tailored experience to meet your needs. \
\
Playground \
\
Explore the world of Mochi today in our interactive playground, where you can test its features and capabilities.

Research

Read All

\
\
Mochi 1: A new SOTA in open text-to-video \
\
Read More

Open Source

Mochi 1 is our cutting-edge open-source text-to-video model, crafted to turn your written concepts into engaging visual stories. Run it locally, customize it for your needs, or contribute to the future of AI video generation.

Download

quickstart.sh

ReplayCopy

# Clone Mochi
git clone https://github.com/genmoai/mochi

# Install dependencies
pip install -e .

# Generate your first video
python demos/cli.py

Github HuggingFace

Careers

We're hiring across research, engineering, and design. Explore the roles below and help build the future of generative media.

View All 9 Open Roles

Founding Product Designer GPU Performance Engineer ML Systems Engineer Research Scientist (diffusion)