CogVideo 1.5
Updated CogVideo model by Zhipu AI with improved video quality.
About
CogVideoX 1.5 from Zhipu AI and Tsinghua KEG is an updated open text-to-video and image-to-video diffusion model that extends earlier CogVideoX releases. The 5B series supports clips up to roughly ten seconds at higher resolution, and the I2V variant can generate from an input image at arbitrary resolution. The repository ships the SAT-based training and inference code, with a diffusers-based path being adapted in parallel.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- Video Generation
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Advanced (4/5)
- Minimum VRAM
- 16 GB
- Added
- Apr 3, 2026
Related Tools
Turn text-to-image models into animation generators
AI animation tool for creating dynamic video content
Latest Open-Sora release with improved video generation quality.
AI video generation model from Stability AI
Open video generation model by Genmo focused on motion quality.
Text-to-video generation framework with cascaded latent diffusion.