Wan 2.2 Image to Video

Model by Wan team (Alibaba).

Modelimage + text in, video out

Input

image, text

Output

video

Examples

An image and a prompt in, a video clip out.

Available as a Pack. Write to [email protected].

An image and a prompt in, an 81-frame clip at 832x464 out, in 23.8 s on one TPU v6e chip.

As served, measured 22 October 2026. The 16 s result is on the research page.

From a photo and the prompt “a group of camels resting in the desert”. 81 frames at 832x464.

From a photo and the prompt “a table and chairs in a room with sunlight coming through the window”. 81 frames at 832x464.

More models

Image and video upscaling.

Text to image.

Chat with streaming, OpenAI-compatible.

3D point tracks of a moving body in; skeleton, skin and bone motion out as GLB.