Wan (Alibaba)
Alibaba's Apache-licensed open video models for T2V, I2V, speech and animation
About Wan (Alibaba)
Wan is a family of open-weight video generation models from Alibaba. The Wan2.2 release includes 14B mixture-of-experts text-to-video and image-to-video models, a compact 5B model that does both, a speech-to-video model, and Wan-Animate for character animation and replacement. It is aimed at developers, researchers and ComfyUI/Diffusers users who want to run or fine-tune video models themselves.
Specs
| Pricing | Open source |
|---|---|
| Free tier | Free to download and run locally (Apache 2.0) |
| Max clip length | |
| Max resolution | 720p |
| Watermark on free plan | |
| Commercial use | Apache 2.0 license |
| Developer API | |
| Open source | Yes |
Last verified 2026-10-23. A dash means we couldn't confirm it from an official source — we leave it blank rather than guess.
Pros
- Permissive Apache 2.0 license, and the team claims no rights over generated content
- Broad task coverage: T2V, I2V, speech-to-video and character animation/replacement
- Integrated into Hugging Face Diffusers, with Hugging Face/ModelScope demo spaces
Cons
- 14B models need a GPU with at least 80GB VRAM for single-GPU inference
- 5B TI2V model needs at least 24GB VRAM (e.g. RTX 4090)
- Open models output at most 720P (480P/720P)
Wan (Alibaba) alternatives
Compare all →HunyuanVideo
Open source
Tencent's open-weight 8.3B video model that runs on consumer GPUs
Mochi 1 (Genmo)
Open source
Genmo's Apache-licensed 10B open text-to-video model
Kling AI
Free plan · from $8.8/mo
Kuaishou's video generator with native 4K, audio and up to 15s clips
LTX Studio
Free plan · from $15/mo
Lightricks' storyboard-to-video studio powered by the open LTX-2.5 model
Hailuo AI (MiniMax)
Free plan · from $14.99/mo
MiniMax's video app running the H3 model with reference-driven generation
Adobe Firefly Video
Free plan · from $9.99/mo
Adobe's commercially safe video model plus partner models inside Firefly