CogVideoX

Open-source text-to-video model by Zhipu AI/Tsinghua with 2B and 5B variants.

Open SourceSelf HostedOffline CapableGPU Required (12GB+ VRAM)
0.0 (0)

About

CogVideoX is an open-source text-to-video generation model by Zhipu AI and Tsinghua University. Available in 2B and 5B parameter variants. Generates 6-second videos at 480p with good semantic understanding. Uses 3D causal VAE. Requires GPU with 12-24 GB VRAM. Apache 2.0 license.

Reviews (0)

Leave a Review

No reviews yet. Be the first to review!

Details

Price
Free
Platform
Local/Desktop
Difficulty
Advanced (4/5)
License
Apache-2.0
Minimum VRAM
12 GB
Added
Apr 3, 2026

Similar Tools

Featured

AI video generation model from Stability AI

Open SourceSelf HostedOfflineGPU 16GB+
Advanced
0.0 (0)

Turn text-to-image models into animation generators

Open SourceSelf HostedOfflineGPU 12GB+
Advanced
0.0 (0)

AI animation tool for creating dynamic video content

Open SourceSelf HostedOfflineGPU 8GB+
Advanced
0.0 (0)