Skip to content
Agents tracked: 492 Releases (7d): 545 Agent status: 1 with issuesSince last limit reset: Claude 9d · Codex 7d For AI agents: Markdown Updated Nov 20, 2026

CogVideo / CogVideoX

by THUDM

Open-source text-to-video and image-to-video generation models (CogVideo, CogVideoX) with inference and fine-tuning code.

AI video generators and platforms Open source

GitHub repo

2. Commercial use: github.com/zai-org/CogVideo

“The CogVideoX-5B model (Transformers module, include I2V and T2V) is released under”

2B model and code are Apache 2.0; 5B models need the free commercial registration and stay under 1 million visits a month.

github.com/zai-org/CogVideo

License checked Nov 10, 2026 against 3 official pages. Tap a verdict to see its source. How we checked Report an error

CogVideoX: short AI video clips on your own machine

CogVideoX is a family of free AI models that make short video clips from a text description or from a still picture. You run it yourself on a computer or rented server with a strong graphics card, so no outside video service is needed. The small model is free for any use; the larger ones need a free sign-up before commercial use.

Where you can use it

A clip from a text description

Describe a scene in English, such as a panda playing guitar in a forest. You get a clip of about six seconds to use as a draft or a short loop.

Bring a still picture to life

Start from your own photo or drawing and add a short description of the motion; the picture becomes the first frame of the clip.

Turn a short idea into a full prompt

The models work best with long, detailed descriptions. A helper script lets a chat AI expand a one-line idea into such a description first.

Teach it your own style

Train the model a little further on your own short clips, for example product shots or interior scenes, so new clips follow that look.

Moving backgrounds for a landing page Idea

Make a few calm, wordless clips, such as clouds or water, and play them muted behind a page header instead of buying stock footage.

Quick previews for a video script Idea

Turn each scene of an ad or explainer script into a rough clip, so the team can judge the order and mood before real filming.

As reported by THUDM: The larger model takes about 180 seconds per clip on a single A100 card; The smallest model can run with about 4GB of graphics memory when all memory savings are on.

CogVideo / CogVideoX popularity

36 / 100
Gid Score, same scale as developer tools
13,214
GitHub stars
CogVideo / CogVideoX: GitHub starszai-org/CogVideo 13,214

How the Gid Score is calculated

How to start

Tell your AI assistant

“Write a Python script that uses diffusers CogVideoXPipeline with THUDM/CogVideoX-2b (Apache 2.0) to turn a long English prompt into a 49-frame MP4 at 8 fps, with CPU offload and VAE tiling turned on to save graphics memory.”

Or install it yourself. Use a machine with an NVIDIA graphics card and Python 3.10 to 3.12, then install the libraries the model card lists.

pip install --upgrade transformers accelerate diffusers imageio-ffmpeg
Show code

Load the model by its name and give it a long English description; the first run downloads the model files.

pipe = CogVideoXPipeline.from_pretrained(
    "THUDM/CogVideoX-5b",
    torch_dtype=torch.bfloat16
)

Mistakes to avoid

Asking for any number of frames, such as 60
Use 8N+1 frames (default 49) for CogVideoX-2B/5B and 16N+1 (default 81) for CogVideoX1.5

The model table fixes the frame counts per model family.

Passing a short or non-English prompt straight to the model
Expand the idea into a long English description first (convert_demo.py or any chat model)

The models were trained on long English prompts.

Keeping enable_sequential_cpu_offload() on when running on several GPUs
Turn that option off for multi-GPU runs; keep it for single small GPUs

The README says that optimization must be disabled for multi-GPU inference.

Running the 2B model in BF16 like the 5B models
Use torch.float16 for CogVideoX-2B and torch.bfloat16 for the 5B models

Each model should run in the precision it was trained in.

Shipping a commercial product on CogVideoX-5B because "the code is Apache 2.0"
Use CogVideoX-2B for Apache 2.0 terms, or register for the 5B commercial license first

Only the code and the 2B weights are Apache 2.0; the 5B weights have their own license.

License

Apache-2.0 (code and CogVideoX-2B); CogVideoX LICENSE (CogVideoX-5B). The code and the small 2B model are Apache 2.0, free for paid products. The 5B models use their own license, which is free for research. Commercial use needs a free sign-up and is capped at one million visits a month.

Commercial use
With conditions

“The CogVideoX-5B model (Transformers module, include I2V and T2V) is released under” github.com/zai-org/CogVideo

Credit
Not needed

“You must give any other recipients of the Work or Derivative Works a copy of this License” LICENSE on GitHub

Inside your app or game
With conditions

“The CogVideoX-5B model (Transformers module, include I2V and T2V) is released under” github.com/zai-org/CogVideo

Pass the files on to your users
With conditions

Apache 2.0 parts may be passed on with a copy of the license; the 5B license is non-transferable and non-sublicensable.

“Under the terms and conditions of this license, the licensor hereby grants you a non-exclusive, worldwide, non-transferable, non-sublicensable, revocable, royalty-free copyright license.” huggingface.co

AI training
Not stated
Bots and bulk downloads
Not stated

AllowedWith conditionsNot allowedNot stated or not checked yet

Is CogVideo / CogVideoX free for commercial use? The full answer Not legal advice. Check the license page before you ship.

For your agent

License rules tell your agent what it may do with CogVideo / CogVideoX. Paste them into your prompt or AGENTS.md.

License rules
- CogVideo / CogVideoX (AI video generators and platforms). Open-source text-to-video and image-to-video generation models (CogVideo, CogVideoX) with inference and fine-tuning code. Price: free; commercial use with conditions; no credit needed; ship inside your app with conditions.
  Connect: download from https://github.com/zai-org/CogVideo (no API).
  Rule: CogVideoX-5B weights follow the separate CogVideoX LICENSE on Hugging Face; read it before commercial use. The code and CogVideoX-2B are Apache-2.0.
  Rule: Keep a copy of the Apache 2.0 license and the copyright and NOTICE files when you redistribute the code.
  Rule: Mark modified files with a prominent notice that you changed them.
  Rule: The README says only the CogVideoX-2B weights are Apache 2.0, so check the model license for the other weights (e.g. 5B) before commercial use.
  Rule: Do not use THUDM trade names or trademarks beyond describing where the work came from.
  License: https://github.com/zai-org/CogVideo/blob/HEAD/LICENSE (checked 2026-11-10; details: https://agentgid.com/assets/cogvideo/)
Can an agent use it by itself?
No.
API, key or account
Not needed. Everything runs on your side.
MCP server
None found
Credit line, if you want one
Video made with CogVideoX (THUDM / Zhipu AI)
This card for machines

Alternatives

CogVideo / CogVideoX This page

Free With conditions Download

Wan 2.2

Pick Wan 2.2 for a newer open model family that also covers speech-to-video and character animation at 480p and 720p.

Free Commercial OK Download

LTX-2 (LTX-2.5)

Pick LTX-2 when you want clips with sound and a ready ComfyUI setup on your own machine.

Free With conditions Download

Stable Video Diffusion (SVD-XT)

Pick Stable Video Diffusion when you only need to animate one still picture into a short 25-frame clip.

Free With conditions Download

Hypit

Open-source video toolkit for AI agents that clones reference videos into variants, plus a hosted multi-model video API.

Free tier With conditions API, npm

Huobao Drama

Open-source platform that automates AI short-drama production from script and characters to storyboard and video compositing.

Free Non-commercial Download

All ai video generators and platforms

Agents that do the same job

video editing agent skill, open source, 31.3K GitHub stars
AI video creation platform, open source, 22.2K GitHub stars
agent skill, open source, 22K GitHub stars
agent skill, open source, 21.2K GitHub stars
agent, open source, 6,968 GitHub stars

From AgentGid's agent catalog, not yet checked as asset sources: their license and price are on their agent pages.

Questions

Can I use CogVideoX in a paid product?

The 2B model and the code, yes, under Apache 2.0. The 5B models need a free commercial sign-up, and above one million visits a month you must contact the team.

Who owns the videos I make?

The license says the rights to generated content belong to the user, as far as local law allows.

Can I try it without my own graphics card?

Yes. There is an online demo on Hugging Face, and the project links Colab notebooks that run on free T4 machines.

Why do short prompts give poor clips?

The models were trained on long descriptions, so the team suggests expanding a short idea with a chat AI first.

AgentGid articles about CogVideo / CogVideoX

All guides