CogVideo Online

Use CogVideo online, free

Generate video from text, images or existing clips with CogVideoX. No GPU, no install, nothing to download. It all runs in your browser.

Free to start. No GPU required. Built on the open source CogVideoX.

Made with CogVideo

See what CogVideo creates

Every clip below was made on CogVideo, from a short prompt or a single image.

A mother gently rocks her baby to sleep in a quiet nursery.
A lifelike portrait rendered with photoreal detail and soft light.
A garden comes alive as butterflies drift between the blossoms.
A golden retriever in sunglasses sprints across a rooftop terrace.
An astronaut shakes hands with an alien under a pink Mars sky.
A warrior in a red cape stands wrapped in swirling magical energy.

Why CogVideo Online

Everything runs in your browser

The full CogVideoX model, without the local setup that normally gets in the way.

No GPU needed

CogVideoX normally needs an NVIDIA GPU with 5 GB or more of VRAM. Online, generation runs on our servers, so any laptop works.

No install, no setup

Skip Python, CUDA and diffusers. Open the page, type a prompt or upload an image, and generate.

Free to start

Create your first videos for free. No credit card and no subscription just to try it.

Open source model

Built on CogVideoX, the open source text to video model from THUDM. The same technology, without the local build.

Three ways to create

Text to Video, Image to Video and Video to Video, all from one place.

Works everywhere

Runs in any modern browser on Windows, macOS, Linux, iOS and Android.

Three ways to create

Pick how you want to start

Text, image or an existing clip. Each opens its own tool, all free in the browser.

Text to Video

Describe a scene in words and generate a clip straight from the prompt.

Open Text to Video

Image to Video

Upload a still image and bring it to life with natural motion.

Open Image to Video

Video to Video

Restyle or transform an existing clip into something new.

Open Video to Video

How it works

From idea to video in three steps

01

Describe or upload

Write a text prompt, or upload an image or a short clip as your starting point.

02

Generate

CogVideoX renders your video on our servers in a minute or two. No GPU on your side.

03

Download

Preview the result and download your MP4, ready to post or edit.

What people make

Made for creators, marketers and teams

Marketing and ads

Spin up short product and promo videos for campaigns without a production crew.

Social content

Feed TikTok, Reels and Shorts with fresh AI clips on a daily cadence.

Ecommerce

Turn product photos into motion for listings, ads and landing pages.

Education and explainers

Illustrate concepts and lessons with generated video instead of stock footage.

Concept and pre-viz

Sketch scenes and moodboards in motion before committing to a full shoot.

Prototyping

Test creative ideas fast, then iterate on the prompts that land.

FAQ

Questions about CogVideo Online

Yes. You can generate your first videos for free with no credit card. Text to Video, Image to Video and Video to Video are all available online.

No. Running CogVideoX locally needs an NVIDIA GPU with at least 5 GB of VRAM, but the online version runs the model on our servers, so any computer or phone with a browser works.

No. There is nothing to download or configure. No Python, CUDA or diffusers. Everything happens in your browser.

Three things: video from a text prompt, video from a still image, and a restyled video from an existing clip.

Yes. CogVideo Online is built on CogVideoX, the open source text to video model from THUDM. You get the same technology without setting up a local environment.

You download a standard MP4 that you can post, edit or use in other tools.

Start creating with CogVideo online

No GPU, no install. Generate your first AI video free, right in your browser.