Welcome to CogVideo Docs

CogVideo is an AI platform for turning your ideas into video. It brings together three ways to create: write a description and get a clip from text, animate a still image into motion, or transform an existing video. Everything runs in your browser, so there is nothing to install.

These docs explain what each tool does, when to reach for it, and how to get a good result on the first try. If you are brand new, start with the getting-started guide and make your first video in a few minutes.

What you can do with CogVideo

• Text to Video turns a written description into a short AI-generated clip. Best when you are starting from an idea rather than existing media.
• Image to Video animates a still image, bringing a photo or illustration to life with motion. Best when you already have the look you want and need movement.
• Video to Video transforms an existing clip with AI. Best when you want to restyle or enhance footage you already have.

Start here

How CogVideo works

Every tool follows the same shape: you provide an input (text, an image, or a video), optionally adjust a few settings, and start generation. Generation runs on GPU hardware in the cloud, and a progress indicator tracks the job while it works. When the clip is ready, it appears in the output panel where you can play and download it.

Ready to make something? Head to the getting-started guide or open the Text to Video tool directly.