Video and audio in one pass
Seedance 2.0 generates the picture and the sound together, so lips, footsteps and the room tone line up with what you see.
Seedance 2.0 AdAnt · by ByteDance Seed
Seedance 2.0 is ByteDance Seed's video-with-audio model, released February 9, 2026, and you can try it here: 4 to 15-second clips guided by images, videos and audio.
We ran this prompt once on each model on AdAnt, with no retries and no edits: 9:16, 720p, 6 seconds, audio on. Whether she says the line clearly and in sync, whether the bottle keeps its shape in her hand, and whether it reads as a phone video rather than a film.
Handheld selfie-style UGC video. A woman in her late 20s with curly brown hair, in a sunlit bathroom, holds a small amber glass serum bottle up next to her face, smiles at the camera and says: "This is the only serum I've ever finished twice." Natural window light, real skin texture, slight handheld shake, vertical 9:16 phone framing.
| Model | Made by | Modes | Longest clip | Resolution | Audio | Inputs | Test run | Test cost | Best for |
|---|---|---|---|---|---|---|---|---|---|
| Seedance 2.0 | ByteDance Seed | Text to video, image to video, video editing | 15 s | 4K | Native | Start/end image, up to 9 images, 3 videos, 3 audio clips | 4 min 7 s | about 6 credits | UGC ads and product clips with references |
| Gemini Omni Flash | Text to video, image to video | 10 s | 4K | Native | Start/end image, up to 30 reference images | 37 s | about 3 credits | fast drafts and talking clips with sound | |
| Seedance 2.5 | ByteDance Seed | Text to video, image to video, reference to video | 30 s | 4K | Native | Start/end image, up to 30 images, 10 videos, 10 audio clips | 2 min 36 s | about 9 credits | longer story clips and complex scenes with many references |
| Seedance 2.0 Fast | ByteDance Seed | Text to video, image to video | 15 s | 4K | Native | Start/end image, up to 9 images, 3 videos, 3 audio clips | 1 min 43 s | about 5 credits | testing many hooks and ideas cheaply |
| Topview T1 | Topview | Text to video, image to video | 30 s | 1080p | Native | Start image, optional end image | 3 min 19 s | about 5 credits | longer single takes and calm, natural clips |
Test run and cost come from the same-prompt run above, measured on AdAnt. Longer clips and higher resolutions cost more; the try-it panel shows the price before you run.
Seedance 2.0 generates the picture and the sound together, so lips, footsteps and the room tone line up with what you see.
Pass up to 9 images, 3 videos and 3 audio clips. AdAnt's agents use this to keep an avatar's face and a product's label the same across every shot.
Seedance 2.0 Edit restyles a clip you already have: a new background, a new outfit, a new time of day.
It is the model AdAnt's Creator agent picks for a video ad unless you ask for another, because it balances look, control and cost.
Handheld selfie-style UGC video. [Who] in [where] holds [your product, as in the reference image] and says: "[one line]". [Light], slight handheld shake, vertical 9:16. Keep the product's label exactly as in the reference.
Seedance 2.0 is ByteDance Seed's video model, released in February 2026, that generates video and audio together from text, images, videos and audio. AdAnt runs it (as its Pro tier) for 4 to 15-second clips up to 4K, plus Seedance 2.0 Edit to restyle an existing video, and uses it by default for video ads.
A creator holding your product and talking to camera, consistent across a whole set of ads.
Your product in motion, kept true to its photos by reference images.
Change the look of a clip you already have without reshooting.
Seedance 2.0 is ByteDance Seed's video model, released on February 9, 2026, that makes video and audio together from text, images, videos and audio. On AdAnt it makes 4 to 15-second clips up to 4K and is the default model for video ads. Our 6-second test clip took about 4 minutes and 5.8 credits.
Running this model uses paid credits from an AdAnt plan. Creating an account is free. A 5-second 720p clip costs about 5 credits.
They have the same features: native audio, 4 to 15-second clips and the same references. Seedance 2.0 Fast costs less and, in our test, finished in under 2 minutes against about 4 for the full Seedance 2.0. Use Fast to test hooks, and the full model for the ad you will run.
Seedance 2.5 makes clips up to 30 seconds and takes more references. Seedance 2.0 costs less per second and is AdAnt's default for ads of short shots.
From 4 to 15 seconds per clip on AdAnt. AdAnt's agents join clips for longer ads.
Mostly. It made a natural phone-style clip with sound, but gave her loose waves rather than the curly hair the prompt asked for; Seedance 2.5 and Gemini Omni kept the curls.
ByteDance offers Seedance 2.0 to developers through BytePlus ModelArk. On AdAnt you can run it without your own provider key, from the adant-cli media command or the AdAnt plugin for Claude, paying in AdAnt credits. A 5-second 720p clip costs about 5 credits.
VideoGoogle · fast drafts and talking clips with sound
VideoByteDance Seed · longer story clips and complex scenes with many references
VideoByteDance Seed · testing many hooks and ideas cheaply
VideoTopview · longer single takes and calm, natural clips
MotionKuaishou (Kling AI) · putting a consistent character into a proven performance
ImageGoogle DeepMind · photoreal product shots and keeping a product on brand
ImageGoogle DeepMind · fast social images, thumbnails and drafts
ImageOpenAI · posters, infographics and anything with words
AdAnt's agents research your market, write the script, pick the right model for each shot and make the video in one chat.
Start with AdAnt