Lifestyle
Potter's hands at the wheel
A slow push-in on wet clay with the hum of the wheel. 5 s, 720p, text only.
Seedance 2.0 · 720P · 16:9 · 5s
Use this exampleBYTEDANCE SEED · AI VIDEO GENERATOR
Seedance 2.0 generates picture and audio in one pass. Start from a text prompt, or guide it with up to 9 images, 3 video clips and 3 audio clips. Choose 5 to 30 seconds and 480p, 720p or 1080p.
Review results, manage assets and access generation history in AI Studio.
Every example below was actually generated with Seedance 2.0 on ImgAI, with the original prompt and settings. Click "Use this example" to load it into the creator.
Lifestyle
A slow push-in on wet clay with the hum of the wheel. 5 s, 720p, text only.
Seedance 2.0 · 720P · 16:9 · 5s
Use this exampleStory
A vertical clip that cuts from a wide tracking shot to a low close-up of the trick, then to a grin at the camera, with wheel sounds. 5 s, 720p.
Seedance 2.0 · 720P · 9:16 · 5s
Use this exampleCommercial
A slow push-in on the bottle through rolling mist as a drop runs down the glass. 5 s, 720p, square.
Seedance 2.0 · 720P · 1:1 · 5s
Use this exampleLandscape
An aerial drift over warm windows with wind and a distant bell. 5 s, 720p.
Seedance 2.0 · 720P · 16:9 · 5s
Use this exampleSeedance 2.0 is ByteDance's video generation model from its Seed team. ByteDance describes it as natively multimodal: it accepts text, images, audio and video as input and generates video together with its soundtrack, rather than adding sound afterwards. It can follow multi-shot instructions within one clip.
On ImgAI you can attach up to 9 reference images, 3 reference videos (15 seconds in total) and 3 audio clips (15 seconds in total), switch audio on or off, and pick 5, 10, 15 or 30 seconds at 480p, 720p or 1080p in 7 aspect ratios. A 5-second clip costs 472–2532 credits depending on resolution; longer clips scale with duration.
Based on the model's published capabilities and what we actually generated, to help you judge whether it fits your task.
Turn a product photo into a short ad with camera moves and matching sound.
Multi-shot clips with action, dialogue-free sound design and a clear beginning and end.
Bring a poster, an illustration or a profile picture to life from its first frame.
Landscapes and ambient shots with natural sound for edits and backgrounds.
Specs come from the configuration currently available on this site; the creator always shows the live price. Failed generations are refunded automatically.
| Input | Text + up to 9 reference images |
| Resolution | 480P · 720P · 1080P |
| Duration | 5 / 10 / 15 / 30 s |
| Prompt length limit | 3,000 characters |
Supported aspect ratios
| Resolution | 5 s | 10 s | 15 s | 30 s |
|---|---|---|---|---|
| 480p | 472 | 943 | 1,415 | 2,829 |
| 720p | 1,015 | 2,029 | 3,043 | 6,086 |
| 1080p | 2,532 | 5,063 | 7,595 | 15,189 |
These come from real generations — read them alongside the original prompts in the examples.
For clips over 5 seconds, describe the action in segments: "[0–3 s] … [3–5 s] …".
Name sound effects and music: "wheels on asphalt, a short laugh, no music". Say "no narration" if you want none.
Refer to uploads as @1, @2 in the prompt so the model knows which image is the product and which is the style.
Test the idea at 5 seconds and 480p, then render the final at 720p or 1080p and the length you need.
Seedance 2.0 is ByteDance's multimodal video model. It takes text, images, video and audio as input and generates video with its soundtrack in one pass.
5, 10, 15 or 30 seconds, at 480p, 720p or 1080p.
A 5-second clip costs 472–2532 credits depending on resolution, and longer clips cost proportionally more. The full table is below; the creator shows the exact price before you generate. Failed generations are refunded automatically.
Yes. Audio is a switch in the creator. Turn it off if you plan to add your own music or voice-over.
Up to 9 images, 3 videos (15 seconds in total) and 3 audio clips (15 seconds in total). Mention them as @1, @2… in the prompt.
Seedance 2.5 is the newer model and has its own page on ImgAI. Seedance 2.0 remains available with its own pricing and duration options; compare both in the creator.
Sign up and generate with credits. Results are saved to your library, ready to download or keep editing.