KovAPIKovAPI
Video ● Operational Service status →

Seedance 2.0

⧉
seedance-2.0
Model Type 2.02.0 Fast2.0 Mini2.0 · Special Beta

Seedance 2.0 standard tier: 5-15 seconds in one-second steps, three resolutions 480P / 720P / 1080P, five aspect ratios (16:9 / 9:16 / 1:1 / 4:3 / 3:4), native audio available. Text-to-video without a reference image, image-to-video with reference images (they set the subject, scene and style; they are not used as the first frame). Asynchronous; billed per second; failed jobs refunded in full.

Text-to-videoImage-to-video480P / 720P / 1080PAsync jobs

Live Test · Playground

Try out Seedance 2.0 right here (available after login).

Input

0 / 5000 bytes
Reference images0 / 9
Click to upload or drag files here jpg / png / webp / gif, up to 16 MB each or paste links
With multiple references, address them in the prompt as @Image1 / @Image2, e.g. "the character from @Image1 stands in the scene from @Image2". Without tokens the model decides on its own.
Real human faces work as reference images, no masking needed. Please make sure you have the right to use the likeness of anyone pictured.
Reference videos0 / 3
Click to upload or drag files here mp4 / mov, up to 50 MB and 30 s each; all reference videos together at most 15s or paste links
Can be combined with reference images: photos set the look, the video sets motion and camera. Address it as @Video1 in the prompt.
Reference audio0 / 3
Click to upload or drag files here mp3 / wav / m4a, up to 15 MB and 30 s each or paste links
Needs a reference image or video as well. Address it as @Audio1 in the prompt.
Uploaded references are kept for 7 days.
Rendering usually takes 5-20 min; when the backend is busy it can exceed 60 min (no result after 120 min counts as a timeout, fully refunded). Poll the job id rather than resubmitting - each resubmission is billed separately. Billed per second, fully refunded on failure. Prompt limit 5000 bytes (about 1666 Chinese characters).

Output

video
Results will appear here after running.
🕑 Generated images and videos are kept for 15 days before 2026-10-29 09:49:40 UTC; from that time, they are kept for 7 days and existing files older than 7 days are removed.

Content requirements

Full details →

About Seedance 2.0

Seedance 2.0 is the standard tier of ByteDance's Seedance 2.0 family. Duration is any integer 5-15 seconds, three resolutions (480P / 720P / 1080P), five aspect ratios (16:9 / 9:16 / 1:1 / 4:3 / 3:4), with an optional generated soundtrack; omit the reference image for text-to-video, include reference images for image-to-video (they set the subject, scene and style; they are not used as the first frame). Async job: POST /v1/videos/generations returns HTTP 202 and a job id immediately; poll GET /v1/videos/jobs/{id} until status=succeeded and read data[0].url. That link is an mp4 re-hosted by us — it is kept for 15 days (far longer than the upstream CDN link), so download it or copy it to your own storage before then.

Use cases

Standard short-form production

5-15 seconds covers most social and ad asset lengths.

Image-to-video

Reference images pin down the subject, wardrobe and scene, so product shots and character sheets come alive; name them @Image1 / @Image2 in the prompt and the identity carries through.

Multi-ratio delivery

Run the same prompt at 16:9 / 9:16 / 1:1 to reuse one idea across platforms.

Clips with sound

audio is on by default, so clips ship with ambient sound and skip a separate audio pass.

How to choose

Pick it when visual quality comes first or you need 1080P — 2.0 is the standard tier of Seedance 2.0 and the only one in the family with 1080P. When budget comes first use seedance-2.0-fast (the low-latency tier: same lengths and ratios, lower rate); for bulk drafts use seedance-2.0-mini; for more than 15 seconds use seedance-2.5.

FAQ

Which resolution should I pick?
480P, 720P and 1080P are selected with the resolution parameter; 720P is the default and each tier has its own per-second rate (see the price box; 480P is 20% under 720P). A tier that is not open yet is refused at submit with a clear message — never silently downgraded, never charged.
How is it different from 2.0 Fast?
2.0 is the standard tier; Fast is the low-latency tier of the same generation — same lengths, ratios and reference limits, no 1080P, lower rate. Choose 2.0 for fine detail and stability, Fast when cost matters.
How does image-to-video work?
Pass images (an array of reference images; a single one can go in image), as public URLs, data: URIs or base64. They reach the model as references for the characters, objects, scene or style, and you address them in order as @Image1, @Image2 in the prompt; the model has no first/last-frame control, so a reference image is not guaranteed to be the opening frame. The same request can also carry reference videos in video_references (@Video1, for motion and camera) and reference audio in audio_reference (@Audio1).
How is it billed, and am I charged on failure?
Billed per second (reference-video seconds count too): the hold placed at submit is computed from the duration you asked for, and the settle is the exact same number. A failed or timed-out render refunds the whole hold, so you never pay for a clip you did not receive.

Related Models

Explore other models you can integrate.

View all →