Seedance 2.0 Pro
Next-gen multimodal video (text / first-frame / ref / audio sync)
Try it
Leave empty for random
You can fill this in now — signing in happens when you run it, and your inputs come with you.
At a glance
- Developer
- ByteDance Seed
- Can do
- Text to video, Image to video, Reference to video
- Credits per run
- 10 credits
- Typical time
- ~120s
- Added
- 2026-08-11
Parameters
What the model takes. The form above is generated from exactly this list, and the API accepts the same field names.
| Parameter | Type | Default | Range / options |
|---|---|---|---|
audio_urlsReference audio（max 3, total ≤15s) | Audio upload | — | ≤ 3 |
video_urlsReference video（max 3, total 2-15s) | Video upload | — | ≤ 3 |
image_urlsReference image（max 9) | Image upload | — | ≤ 9 |
end_image_urlEnd image (optional) | Image upload | — | — |
image_urlrequiredStart image | Image upload | — | — |
promptPrompt | Long text | — | — |
aspect_ratioAspect ratio | Choice | auto | auto · 21:9 · 16:9 · 4:3 · 1:1 · 3:4 · 9:16 |
resolutionResolution | Choice | 720p | 480p · 720p · 1080p |
durationDuration (seconds) | Range | 5 | 4 · 5 · 6 · 7 · 8 · 9 · 10 · 11 · 12 · 13 · 14 · 15 |
seedSeed | Number | — | — |
generate_audioGenerate audio | On / off | No | — |
Use it from the API
The same run, as a request. Send your API key as a bearer token; poll the returned request_uid until it is done.
curl -X POST https://api.wisaven.com/v1/ai/async/tasks \
-H "Authorization: Bearer $WISAVEN_API_KEY" \
-H "X-App-Id: wisaven" -H "Content-Type: application/json" \
-d '{
"model": "seedance-2-pro",
"task": "text-to-video",
"input": {
"audio_urls": "https://…",
"video_urls": "https://…",
"image_urls": "https://…",
"end_image_url": "https://…"
}
}'Questions
What can Seedance 2.0 Pro do?
Text to video, Image to video, Reference to video. Fill in the parameters on this page to try it.
How many credits does Seedance 2.0 Pro cost?
About 10 credits per run, charged at the platform's live price when you run it. One credit balance covers every workspace.
How long does it take?
Around 120 seconds; heavier settings or a queue take longer, and the page shows progress.
Do I need an account, and who owns the output?
Browsing and filling in the form need no account; running it does (new accounts start with free credits). What you generate is yours, personally or commercially, subject to the terms.
Other models like this
Where this model is used: Video·All models