Plain-AyI
← All projects
Images & video

SANA

NVIDIA research models that create high-resolution images and videos from text descriptions, built for speed.

Research-backedNew this week

What it does

SANA is a family of image and video generation models from NVIDIA's research lab. You describe a picture or scene in words, and the model creates it. The focus is on making high-resolution results quickly and efficiently.

The project has grown to include fast one-step image models, text-to-video models, real-time long video generation and editing, and a "world model" that makes videos with camera control.

It includes everything needed to run and train the models. Online demos are available, and some versions also work in the popular ComfyUI image tool.

Who it's for

AI researchers and developers working on image and video generation, and creators comfortable with tools like ComfyUI.

Can I use it without coding?

Developers only. Mostly research code; online demos let anyone try it without installing. New to this? Start here.

Can I run it?

Cost
FreeNothing to pay or sign up for.
Computer
Works best on a powerful computer or one with a graphics card (GPU)
Privacy
Runs on your own device: your data stays with you
API key
Not needed

Try it

Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?

Before you install

  • Only download from the official GitHub page. Copies with similar names exist for many popular projects.
  • License (Apache-2.0): Permissive: free to use, change and share, including for business.
  • More on staying safe

Where people are talking about it