Wan 2.2 AI Form
Upload images and describe your prompt with improved AI model
Wan 2.2 AI
Turn prompts or pictures into Hollywood-grade clips in minutes
Wan 2.2 AI Examples
Original Image 1
Video Result 1
Original Image 2
Video Result 2
Wan 2.2 AI FAQ
Have a different question and can’t find the answer you’re looking for? Reach out to our support team by sending us an email and we’ll get back to you as soon as we can.
What is Wan 2.2?
Wan 2.2 is Alibaba DAMO Academy’s latest open-source video generation model, succeeding Wan 2.1. It supports both text-to-video and image-to-video capabilities.
How does Wan 2.2 Image to Video AI function?
Wan 2.2 takes your uploaded reference image plus an optional prompt, encodes it through a high-compression VAE, then a two-expert MoE diffusion backbone predicts the in-between frames while letting you steer 60 + cinematic controls such as lighting, camera motion and colour tone.
Which input types and output resolutions are supported?
You can generate video from text prompts, images, or a mix of both. Open checkpoints output up to 720 P @ 24 fps.
Which formats are supported by Wan 2.2 Image to Video AI?
Inputs: JPG, JPEG, PNG, WEBP; max 10 MB; 360–2000 px on the shortest edge. Outputs: silent MP4 (default) or WebM video at 480 P, 720 P, 24–30 fps depending on the resolution tier.
How does Wan 2.2 Image to Video AI differ from Wan 2.1?
Wan 2.2 Image to Video AI offers improved video quality, faster processing times, and better motion consistency compared to Wan 2.1. It also supports both 480p and 720p resolutions with 5-second video generation.
Is there a free trial available for Wan 2.2 Image to Video AI?
No, it is a paid service, but you gain 10 free credits when you sign up.