Wan 2.2
by Wan team (Alibaba)
Open MoE video model family for text-to-video, image-to-video, speech-to-video and character animation at 480p/720p.
AI video generators and platforms Open source
1. Price: huggingface.co/Wan-AI/Wan2.2-T2V-A14B
Open weights, free to download; self-hosted (the 5B model runs on a single RTX 4090).
huggingface.co/Wan-AI/Wan2.2-T2V-A14BNo quote yet: price is read from the official pages.
2. Commercial use: huggingface.co/Wan-AI/Wan2.2-T2V-A14B
“The models in this repository are licensed under the Apache 2.0 License.”
Apache 2.0 allows commercial use; generated content must stay within the listed limits.
huggingface.co/Wan-AI/Wan2.2-T2V-A14B3. Credit the author: huggingface.co/Wan-AI/Wan2.2-T2V-A14B
“We claim no rights over the your generated contents, granting you the freedom to use them while ensuring that your usage complies with the provisions of this license.”
No credit on screen. Keep the license notice inside the code you ship.
huggingface.co/Wan-AI/Wan2.2-T2V-A14B4. Agent access: github.com/Wan-Video/Wan2.2
There is no package or API. Files are downloaded by hand from the official site.
github.com/Wan-Video/Wan2.2License checked Oct 25, 2026 against 2 official pages. Tap a verdict to see its source. How we checked Report an error
Wan 2.2: open AI models that make short videos
Wan 2.2 is a free, open family of AI video models from Alibaba's Wan team. It makes short video clips from a written description and brings a still picture to life. It can also make a person in a photo talk or dance along with sound or another video. You run it on your own powerful graphics card, and you may use the clips in paid work.
Where you can use it
A clip from a written idea
Describe a scene in a sentence, such as two cats boxing on a stage, and get a short 720p video. Useful for social posts, mood videos or story drafts.
Bring a product photo to life
Start from your own picture, such as a product shot or an illustration, and add movement described in words. The video keeps the shape of the picture.
A talking or singing person from audio
Give one photo of a person and a voice or song recording. The model makes a video of that person speaking or singing along, as long as the audio.
Make a character copy a dance
Take a video of someone moving and a picture of a character. The character repeats the moves, or replaces the person in the video.
Make videos from Python code
Call the model from a Python script, for example to make a batch of clips for a product catalog.
Moving backgrounds for a landing page Idea
Make a calm looping clip, like waves or clouds, from a short description and use it as the hero video of a site.
As reported by Wan team (Alibaba): Compared with Wan2.1, Wan2.2 is trained on +65.6% more images and +83.2% more videos.; The 5B model makes 720P video at 24fps..
Wan 2.2 popularity
How to start
Tell your AI assistant
“On my machine with a 24 GB NVIDIA card, set up Wan2.2 from github.com/Wan-Video/Wan2.2, download Wan-AI/Wan2.2-TI2V-5B, and make a 1280*704 clip from my prompt with --offload_model True --convert_model_dtype --t5_cpu; do not use DashScope prompt extension.”
Show codeStep 1 or Step 2 or Step 3
Get the code and install the packages. PyTorch 2.4 or newer is needed; install flash_attn last if it fails.
git clone https://github.com/Wan-Video/Wan2.2.git
cd Wan2.2
# Ensure torch >= 2.4.0
pip install -r requirements.txt
Download a model. The 5B model is the one that fits a single 24 GB card.
huggingface-cli download Wan-AI/Wan2.2-TI2V-5B --local-dir ./Wan2.2-TI2V-5B
Run generate.py with the task, size, model folder and your prompt.
python generate.py --task ti2v-5B --size 1280*704 --ckpt_dir ./Wan2.2-TI2V-5B --offload_model True --convert_model_dtype --t5_cpu --prompt "Two anthropomorphic cats in comfy boxing gear and bright gloves fight intensely on a spotlighted stage"
Mistakes to avoid
The 5B model uses its own 720P sizes.
The README states the memory each command needs.
These options lower the graphics memory needed.
The DashScope method sends the prompt to Alibaba Cloud and needs a key the person must create.
pip install -r requirements.txt fails on flash_attn and the setup is abandonedThe README gives this order as the fix.
License
Apache-2.0 license. The Wan 2.2 models are under the Apache 2.0 license, and the makers claim no rights over the videos you make. You may use them in paid work, but you are responsible for the content and must not make harmful or misleading videos.
“The models in this repository are licensed under the Apache 2.0 License.” huggingface.co/Wan-AI/Wan2.2-T2V-A14B
“We claim no rights over the your generated contents, granting you the freedom to use them while ensuring that your usage complies with the provisions of this license.” huggingface.co/Wan-AI/Wan2.2-T2V-A14B
“The models in this repository are licensed under the Apache 2.0 License.” huggingface.co/Wan-AI/Wan2.2-T2V-A14B
Passing on the weights or code needs a copy of the license and the notices.
“You must give any other recipients of the Work or Derivative Works a copy of this License” github.com/Wan-Video/Wan2.2/blob/main/LICENSE.txt
“We claim no rights over the your generated contents, granting you the freedom to use them while ensuring that your usage complies with the provisions of this license.” huggingface.co/Wan-AI/Wan2.2-T2V-A14B
AllowedWith conditionsNot allowedNot stated or not checked yet
Is Wan 2.2 free for commercial use? The full answer Not legal advice. Check the license page before you ship.
For your agent
License rules tell your agent what it may do with Wan 2.2. Paste them into your prompt or AGENTS.md.
- Wan 2.2 (AI video generators and platforms). Open MoE video model family for text-to-video, image-to-video, speech-to-video and character animation at 480p/720p. Price: free; commercial use OK; no credit needed.
Connect: download from https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B (no API).
Rule: Keep the Apache-2.0 license and notices when you redistribute the weights.
Rule: The model card bars sharing illegal or harmful content, misinformation and personal data meant to harm.
Rule: You are fully accountable for what you generate.
License: https://github.com/Wan-Video/Wan2.2/blob/main/LICENSE.txt (checked 2026-10-25; details: https://agentgid.com/assets/wan/)
Video made with Wan 2.2 (Alibaba Wan team), Apache License 2.0Alternatives
Wan 2.2 This page
Pick LTX when you want video with sound made in one step from text, images or audio.
Stable Video Diffusion (SVD-XT)
Pick Stable Video Diffusion for a short clip of 25 frames from one still image.
Pick CogVideoX when you also want ready fine-tuning code for text and image to video.
Open-source video toolkit for AI agents that clones reference videos into variants, plus a hosted multi-model video API.
Open-source platform that automates AI short-drama production from script and characters to storyboard and video compositing.
Agents that do the same job
From AgentGid's agent catalog, not yet checked as asset sources: their license and price are on their agent pages.
Questions
Can I use Wan videos in ads or on YouTube?
Yes. The makers claim no rights over generated videos, and the models are under Apache 2.0; the content must stay lawful and not harmful.
Which model runs on one home graphics card?
The TI2V-5B model, on a card with 24 GB of memory such as an RTX 4090.
Can it make a video without a written prompt?
Yes, from the image alone; a prompt can be written for you from the picture with the optional prompt rewriting step.
Can I set the video shape when I start from an image?
The size you give sets the area; the shape follows your input image.
AgentGid articles about Wan 2.2
A Full Motion Studio in 16 Free Repos: The Catches Behind 'No Catch'
A viral post lists 16 free repos for design, motion, 3D, AI video and editing with Opus 5.5. We checked the eight new to AgentGid: rembg's default model needs a commercial licence, Wan 2.2's big models need 80 GB of VRAM, and Natron needs maintainers.
AI Video Generation: 10 Open-Source GitHub Repos for Filmmakers
A viral list of 10 open-source repos for AI filmmakers, checked on GitHub: the six new to us, which need a serious GPU, how model licenses differ from code licenses, which projects have gone quiet and where to start.