Up to 30 seconds per pass
Alibaba says Wan 3.0 generates up to 30 seconds of video in a single pass, at 480p, 720p or 1080p.
Alibaba · Video model · Released August 2026
Alibaba’s Wan 3.0 makes up to 30 seconds of video in a single pass. On Flowith you can start from a sentence or from an image you made on the same canvas.
The settings you get in the Flowith composer. Checked on November 14, 2026.
Alibaba says Wan 3.0 generates up to 30 seconds of video in a single pass, at 480p, 720p or 1080p.
Alibaba describes changing visuals, plot and dialogue of a generated video without a full regeneration, a capability carried over from Wan 2.7.
Alibaba highlights diverse, lifelike faces in text to video and consistent characters, props and style in reference to video.
Alibaba says audio texture and on-screen text are still being improved, so keep lettering for the edit.
The button above opens a canvas with the model already selected in the composer.
Say what happens, how the camera moves and what it sounds like. Add a start or end frame, reference images or clips, or a saved character.
Generate, and the clip lands on the canvas as a card next to its references.
Reshoot, continue from the last frame, or put the shots in order in the editor. Or ask Creator Agent to plan the film and pick a model for each shot.
Each one opens Flowith with the prompt filled in and Wan 3.0 picked. Change anything before you send.
All of these run on the same canvas, so you can try one prompt on several models and keep the best take.
| Model | Clip length | Resolution | References | Pick it for |
|---|---|---|---|---|
| Seedance 2.5 | 4–30 s | 480p–1080p | 30 images, 10 videos, 10 audio | Long single takes that follow many references |
| Kling 4.0 | 3–30 s | 720p, 1080p | 10 images, 5 videos | People, motion and start/middle/end frames |
| Wan 3.0 | 5, 10, 15, 20, 30 s | 480p–1080p | Start image | Text or image to video with sound |
| Gemini Omni 1.2 Flash | 3–15 s | 360p–4K | 6 images, 3 videos | Cheap drafts, then edits and upscales |
| Veo 3.1 | 4, 6, 8 s | 720p–4K, by variant | Start image | Short clips with native sound |
Text, image and video models side by side. Compare them on the same prompt, pick one per shot, or let the agent choose.
Write it, picture it, film it. One sentence is enough to begin.