Model · Alibaba · Video-Gen
Wan 2.2
Alibaba's open video model family from the Wan team, under Apache 2.0. The 5B TI2V model makes 720p, 24fps video from text or an image on a single 24 GB graphics card; the larger A14B Mixture-of-Experts models handle text-to-video and image-to-video at higher quality.
- Modality
- Video-Gen
- License
- Apache 2.0 (Open)
- Parameter size
- TI2V-5B (headline, consumer GPU); T2V-A14B and I2V-A14B (Mixture-of-Experts); S2V-14B and Animate-14B added later
- Released
- July 28, 2025
- Last verified
- October 28, 2026
- Runs locally
- Yes
What you need to run it
- Mac
- Yes, but slow. Any Apple Silicon Mac (M1 or newer) with at least 32 GB (64 GB recommended) of memory. It runs, but much slower than on an NVIDIA card.
- Windows / Linux PC
- NVIDIA works best. A graphics card with at least 24 GB (80 GB recommended) of video memory.
- No graphics card
- Not practical. Too slow without a graphics card or Apple Silicon.
The 5B model needs a 24 GB card on a PC and runs on a Mac only slowly (ComfyUI or Draw Things), so allow 32 GB or more.
Numbers are for: TI2V-5B for the minimum; the 14B models for recommended. Based on the maker’s own figures; where the maker gives only a graphics-card figure, the Mac memory is our estimate.
Strengths
- Apache 2.0 — no revenue cap or branding rules for commercial use
- TI2V-5B runs on a 24 GB graphics card such as an RTX 4090, at 720p and 24fps
- One 5B model does both text-to-video and image-to-video
- Wide tooling: ComfyUI and Hugging Face Diffusers support from launch day
- Family also covers speech-to-video (S2V-14B) and character animation (Animate-14B)
Weaknesses
- The A14B and 14B models need a data-centre GPU with at least 80 GB of VRAM for the standard commands
- Text- and image-to-video output is silent — unlike newer open models such as LTX-2.5, it does not generate a soundtrack
- 720p ceiling; no 4K path
Try it
| Where | Type | Notes |
|---|---|---|
| Hugging Face (TI2V-5B) | weights | Apache 2.0 |
| Hugging Face (T2V-A14B) | weights | Apache 2.0 |
| ComfyUI | local | Native Wan 2.2 workflows |
Official sources
- GitHub github
- Model card (TI2V-5B) model
Change log
- — Added hardware requirements (Mac support, memory, NVIDIA). Source: the Wan2.2 README (5B model on 24 GB, 14B models on 80 GB); Mac memory is estimated.
- — Initial entry. Released 2025-07-28 per the GitHub README news, under Apache 2.0. Added 2026-10-28 from the popularity sweep: 18.2k GitHub stars, and the Comfy-Org ComfyUI repack had 8.5M Hugging Face downloads in the last month — the most-downloaded image-to-video repo on Hugging Face. Still the newest open Wan line — no later Wan version has open weights under Wan-AI on Hugging Face; the most recent upload is Wan2.2-Animate-2-14B (2026-07).
Esc