Wanovo - AI Video Generation

Wanovo turns a prompt, a photo, or references into a video. It runs on Wan 2.7 and Wan 3.0. With Wan 3.0, the picture and the soundtrack come out together: spoken lines, background music, and sound effects in one clip, up to 30 seconds at 30fps.

Text to Video

Describe what happens. Wan 3.0 can break the prompt into several shots, keep the action moving, and add the voice and sound that fit the scene. Pick 5 to 30 seconds.

Image to Video

Use one photo as the opening frame, or two photos as the first and last frame. The model fills in the motion and keeps the look of your image.

Reference to Video

Hold a person, product, or scene steady across the clip. Add up to 10 images and 5 video clips. Add an audio clip when the voice or the track should follow something you already recorded.

Choose the size before you generate

480P to try an idea. 720P or 1080P when you want the cut you post. Frames: 9:16, 3:4, 1:1, 4:3, and 16:9, so the same scene can fit a vertical short or a widescreen cut.

Wan 2.7

Switch to Wan 2.7 for another generation pass, or to edit a clip you already have: replace what is in the frame, or restyle the video. Wan 2.7 outputs 720P or 1080P, up to 15 seconds.

What you can make

A short story from a text prompt
A still photo set in motion
A character or product that stays consistent
A vertical clip for Shorts, Reels, and TikTok
A scene that already includes dialogue and sound