One take, twice as long
ByteDance doubled single-pass generation from 15 seconds in Seedance 2.0 to 30 seconds, with audio generated in the same pass.
ByteDance Seed · Video model · Released July 31, 2026
ByteDance’s Seedance 2.5 renders a single take of up to 30 seconds with sound and follows up to 50 references. On Flowith it sits on a canvas next to your characters, storyboard and editor, so a clip becomes a shot in a film.
The settings you get in the Flowith composer. Checked on November 14, 2026.
ByteDance doubled single-pass generation from 15 seconds in Seedance 2.0 to 30 seconds, with audio generated in the same pass.
Mix up to 30 images, 10 video clips and 10 audio clips. ByteDance also lists clay-render references, so a grey 3D layout can set blocking, camera and light.
ByteDance describes timestamp-level control: direct the story, camera and motion for a time range, then change characters or actions in one part of the clip.
A faster, lower-cost edition with smaller limits on Flowith: up to 720p and 10 image, 5 video and 5 audio references. It shows as Coming soon in the model picker until ByteDance opens access.
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 Seedance 2.5 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.