Wan 2.5

Latest video generation model by Alibaba with improved quality and speed.

Open SourceSelf HostedOffline CapableGPU Required (16GB+ VRAM)
0.0 (0)

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

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

Related Tools

Featured

Open-source video generation model by Tencent with text and image conditioning.

Open SourceSelf HostedOfflineGPU 24GB+
Advanced
0.0 (0)

Image-to-video generation model by Alibaba DAMO Academy.

Open SourceSelf HostedOfflineGPU 12GB+
Advanced
0.0 (0)

Updated CogVideo model by Zhipu AI with improved video quality.

Open SourceSelf HostedOfflineGPU 16GB+
Advanced
0.0 (0)

Infinite-length music-driven video generation with visual conditioning.

Open SourceSelf HostedOfflineGPU 12GB+
Advanced
0.0 (0)

Text-to-video generation framework with cascaded latent diffusion.

Open SourceSelf HostedOfflineGPU 16GB+
Advanced
0.0 (0)

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

Open SourceSelf HostedOfflineGPU 12GB+
Advanced
0.0 (0)
Browse all Video Generation tools