Skip to content
SPECIFICTION
Get listed

CogVideoX

github.com

WebWindowsLinuxSelf-hosted
Visit github.com
Spec score 8.0 #10 of 23 in Text-to-Video Generators

Spec sheet

What it does
CogVideoX is an open-source model for text-to-video and image-to-video generation.Read 12 Oct 2026 · github.com
Purpose
CogVideoX is an open-source video-generation model family for text-to-video and image-to-video generation.Read 13 Oct 2026 · github.com
Deployment
The repository provides inference and fine-tuning code through SAT and Diffusers, plus a simple Gradio web application.Read 12 Oct 2026 · github.com
Integrations
The project lists community integrations including ComfyUI-CogVideoXWrapper, CogStudio, and Xorbits Inference.Read 13 Oct 2026 · github.com
License
The code and CogVideoX-2B are released under Apache 2.0, while CogVideoX-5B model weights use the CogVideoX License.Read 13 Oct 2026 · github.com
Maker
Zhipu’s about page lists its founding year as 2019 and its address in Haidian District, Beijing, China.Read 13 Oct 2026 · zhipuai.cn
Commercial use
The CogVideoX License requires commercial users to register for a basic commercial license and limits service visits to one million per month under that license.Read 13 Oct 2026 · github.com
Commercial use limit
The model license permits registered basic-license commercial activities up to 1 million service visits per month; higher usage requires contacting the business team for more licenses.Read 12 Oct 2026 · github.com
Free Colab examples
The repository provides Colab examples described as runnable on free T4 instances, including text-to-video and image-to-video notebooks.Read 13 Oct 2026 · github.com
Generation tasks
The project lists text-to-video generation, video continuation, and image-to-video generation as supported tasks.Read 13 Oct 2026 · github.com
Hardware limits
The README lists minimum Diffusers memory usage of 4 GB for CogVideoX1.5-5B-I2V and 5 GB for CogVideoX-5B, with quantized configurations listed lower.Read 13 Oct 2026 · github.com
Hardware requirements
The repository lists minimum Diffusers memory figures as low as 4 GB for CogVideoX-2B and notes that INT8 can reduce memory needs while slowing inference.Read 12 Oct 2026 · github.com
Image-to-video
YesRead 19 Sep 2026 · github.com
License restrictions
The model license prohibits use for military or illegal purposes and certain acts described in the license, and provides the software without warranty.Read 12 Oct 2026 · github.com
Licensing
The code is released under Apache 2.0, while model weights have a separate license that allows academic research use and requires a basic commercial license for commercial use.Read 12 Oct 2026 · github.com
Maximum video length
0.1666666667Read 19 Sep 2026 · github.com
Models
The repository lists CogVideoX1.5-5B, CogVideoX1.5-5B-I2V, CogVideoX-2B, CogVideoX-5B, and CogVideoX-5B-I2V.Read 13 Oct 2026 · github.com
Online access
The repository links online CogVideoX-5B demos on Hugging Face Spaces and ModelScope Spaces.Read 12 Oct 2026 · github.com
Online demo
The project links to Hugging Face and ModelScope Spaces to try CogVideoX-5B online.Read 13 Oct 2026 · github.com
Prompt language
The model supports English input, and the README says other languages can be translated into English for use.Read 13 Oct 2026 · github.com
Resolution
CogVideoX1.5-5B is listed at 1360 × 768, while CogVideoX1.5-5B-I2V supports specified variable resolutions up to 1360 pixels on the longer side.Read 12 Oct 2026 · github.com
Setup
The project provides SAT and Diffusers setup paths and specifies Python versions 3.10 through 3.12 for both.Read 13 Oct 2026 · github.com
Support and community
The repository invites users to join its WeChat and Discord communities and provides a user guide link.Read 13 Oct 2026 · github.com
Text-to-video
YesRead 19 Sep 2026 · github.com
Video length
The repository lists 5- or 10-second video lengths for CogVideoX1.5-5B models and 6 seconds for the listed earlier models.Read 12 Oct 2026 · github.com
Video output
The README lists CogVideoX1.5-5B as supporting 5- or 10-second videos at 16 frames per second.Read 13 Oct 2026 · github.com
Video tasks
The model series supports text-to-video generation, video continuation, and image-to-video generation.Read 12 Oct 2026 · github.com

Where Specifiction places it

Alternatives to CogVideoXAll alternatives →