Model · Video
CogVideoX
A downloadable video model from the Z.ai (Zhipu) CogVideoX team that makes 5-10 second clips from a description or a photo. Smaller versions run on a home graphics card. Business use needs a free registration and has a usage cap.
At a glance
- Open or closed
- Downloadable, with conditionsYou can download and run it, but the licence limits useDownloadable under the CogVideoX Licence, which restricts commercial use.source · checked 12 Oct 2026 · checked on the maker's own page
- Licence
- CogVideoX License (Community licence with conditions (e.g. revenue cap))The 2B model may be under Apache 2.0; not checked this run.source · checked 12 Oct 2026 · checked on the maker's own page
- Can I sell what I make?
- Yes, with conditions
- Only below a revenue limit
- You must credit the maker
Must register for a free basic commercial licence; free up to 1 million visits a month to your service (a usage cap, mapped to revenue_cap); keep licence text with copies. No military/illegal use.source · checked 12 Oct 2026 · checked on the maker's own page - Cost
- Free option: Free to download and run yourselfPlans below.
- How you use it
- On your own computer, Through another serviceLow figures need CPU offload and VAE tiling, which slow generation 3-4x. I2V sizes not listed separately.source · checked 12 Oct 2026 · checked on the maker's own page
- Skill needed
- TechnicalOur judgement: Python/Diffusers setup.source · checked 12 Oct 2026 · checked, but the page was unclear or partial
- Made by
- Z.ai (Zhipu AI) CogVideoX Model TeamHF org is Z.ai; links also name THUDM and ZhipuAI. Licence is governed by PRC law, but no address is stated, so no country set.source · checked 12 Oct 2026 · checked, but the page was unclear or partial
- Status
- AvailableWeights still published; no deprecation notice seen.source · checked 12 Oct 2026 · checked, but the page was unclear or partial
What you can make with it
- A video, from a description (main use)
- A video, by bringing a photo to life
text to videoimage to video
Text-to-video: 2B, 5B, 1.5-5B; image-to-video: 5B-I2V, 1.5-5B-I2V.
source · checked 12 Oct 2026 · checked on the maker's own page
Plans and prices
No paid plans listed.
source · checked 12 Oct 2026 · checked on the maker's own page
Rights and safety
- Limits
- max video seconds: 10; note: 1.5 models: 5 or 10 s at 16 fps, up to 1360x768. 2B: 6 s at 8 fps, 720x480.source · checked 12 Oct 2026 · checked on the maker's own page
Related
Where you can run it
Other options for “A video, from a description”
Adobe Express, Adobe Firefly, Adobe Premiere, Akool, Animoto, Arcads, Canva AI (Magic Studio), CapCut, Civitai, ComfyUI, Creatify, DeeVid AI, DomoAI, Dreamina, Dzine, fal, Filmora, FlexClip, Fliki, Fotor, Genmo, getimg.ai, Google Flow, Hailuo AI
About this entry
Facts last checked 12 Oct 2026 against the maker’s own pages (each fact links to its source). Entry status: draft. Plain-English summary written by Plainly.