Wan 2.5
Latest video generation model by Alibaba with improved quality and speed.
About
Wan 2.5 is the newest generation in Alibaba's Wan family of large-scale video generation models, following the openly released Wan 2.1 and Wan 2.2. The version advances the line on visual fidelity, motion coherence, and instruction following, and its preview introduced capabilities beyond its predecessors, including native audio generation synchronized with the video track, 1080p output, and clips around ten seconds long, covering both text-to-video and image-to-video workflows. One important difference from earlier releases: while Wan 2.1 and 2.2 shipped Apache 2.0 weights on Hugging Face and ModelScope with self-hosted inference code, Wan 2.5 debuted as a preview served through Alibaba's hosted platforms and partner APIs, and no open weights repository had been published at the time of writing. Creators evaluating it typically access it through those services or through third-party generation platforms that integrated the model, while teams that need self-hosted, license-free deployment generally stay on Wan 2.2 until weights for newer versions appear.
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)
- License
- Apache-2.0
- Minimum VRAM
- 16 GB
- Added
- Apr 3, 2026
Related Tools
Open-source video generation model by Tencent with text and image conditioning.
Image-to-video generation model by Alibaba DAMO Academy.
Updated CogVideo model by Zhipu AI with improved video quality.
Infinite-length music-driven video generation with visual conditioning.
Text-to-video generation framework with cascaded latent diffusion.
Open-source text-to-video model by Zhipu AI/Tsinghua with 2B and 5B variants.