Introduction
Seedance 2.0 Mini reference-to-video reconciles several authorised sources into one shot: images for who and what, clips for motion and pacing, audio for the beat the cut lands on. It takes no first frame.
Seedance 2.0 Mini is the smallest tier of ByteDance's Seedance 2.0 line. It publishes the same endpoints as Seedance 2.0 Fast and returns 4 to 15 second clips at 480p or 720p, with audio generated in the same pass.
Choose a Seedance 2.0 Mini mode by starting material
| Starting material | Mode |
|---|---|
| A script or scene description | Seedance 2.0 Mini Text to Video |
| An approved opening still | Seedance 2.0 Mini Image to Video |
| Separate appearance, motion or audio references | Seedance 2.0 Mini Reference to Video |
Key features
The same contract as Seedance 2.0 Fast
Mini publishes the same endpoints and the same fields as Seedance 2.0 Fast: adaptive framing plus six fixed ratios, 4 to 15 seconds or -1 for a length the model chooses, native audio and seed, with resolution capped at 720p. A pipeline written against Mini moves to Fast by changing the model id, not the request.
Built for volume
Mini is the tier to pick when throughput matters more than the extra quality of the larger Seedance 2.0 models. Every endpoint is asynchronous: send an Idempotency-Key with each request, store the task ids and let polling or callbacks resolve them. The key is honoured for 24 hours, so a retry after a dropped connection returns the original task.
Longer sequences with Video Extend
To go past fifteen seconds, send a finished clip to the video-extend endpoint: its final frame opens a new Seedance 2.0 Mini shot and you get one file back with both joined.
Request parameters
| Parameter | Required | Description |
|---|---|---|
aspect_ratio | No | The shape of the frame: wide, square or tall. 16:9 · 9:16 · 4:3 · 3:4 · 1:1 · 21:9 · adaptive · Default: adaptive |
bitrate_mode | No | Encoding bitrate of the delivered file: standard, or high for crisper detail and a larger file. standard · high · Default: standard |
duration_seconds | No | How long the clip runs. You pay per second. -1–15 · Default: 5 |
enable_web_search | No | Checks the web first, for dates, places and current facts. Default: false |
generate_audio | No | Adds sound made to match the picture: voices, ambience and effects. Default: true |
prompt | Yes | Describe the intended subject, action, camera, light, sound, and constraints. |
reference_audio_urls | No | Audio to match: a voice, music or a rhythm. |
reference_image_urls | No | Pictures of the people, outfits or places the result should keep. |
reference_video_urls | No | Clips whose motion, camera or style the result should follow. |
resolution | No | Output size. Bigger sizes look sharper and cost more. 480p · 720p · Default: 720p |
return_last_frame | No | Also return the clip’s final frame as a separate image. Default: false |
seed | No | Reuse the same number to get a repeatable result. ≥ 0 · ≤ 2147483647 |
watermark | No | Add the model’s visible "AI generated" watermark to the video. Default: false |
Pricing
Prices are in credits, the same credits you use on the website (1 credit = $0.01). The hold is taken when the task is accepted and settled to the actual charge when it finishes; failed tasks are refunded.
| Option | Credits per second | ≈ USD |
|---|---|---|
| resolution 480p · with_video true | 1.65 | $0.017 |
| resolution 720p · with_video true | 3.54 | $0.035 |
| resolution 480p · with_video false | 3.69 | $0.037 |
| enable_web_search true · resolution 480p · with_video false | 5.4 | $0.054 |
| enable_web_search true · resolution 480p · with_video true | 5.4 | $0.054 |
| resolution 720p · with_video false | 7.94 | $0.079 |
| enable_web_search true · resolution 720p · with_video false | 10.8 | $0.11 |
| enable_web_search true · resolution 720p · with_video true | 10.8 | $0.11 |
Each task is rounded up to whole credits, so one run at the lowest tier costs 9 credits for a 5-second clip ($0.09).
For an exact number before you run, send the same body to POST /jobs/quote.
Use cases
One reference set for a whole series
Three views of one man from the front, three-quarter and profile, plus a fourth image of his apron, can carry an entire series while only the prompt changes between requests. The published bakery example is built exactly that way.
Pacing borrowed from a clip
A reference clip can supply rhythm instead of content. One example matches an unhurried continuous push from a clip, stages it down an aisle from a reference image and lands the footsteps on the pulse of a reference track, eight seconds in 9:16.
A couple held steady across angles
Three stills of the same couple let a new shot find a third angle while faces and wardrobe stay the same, as in the park-bench example rendered at 480p.
Prompt guide & pro tips
Name each reference by position
The prompt is required and does the casting, because references are read in the order you send them. Write "References 1-3 are..." or use @Image1, @Image2 so that each asset has exactly one job.
Know the ceilings
Send up to 9 images, 3 clips and 3 audio tracks, with at least one image or clip in every request.
Adapt the included example
The published example uses aspect_ratio 16:9, duration_seconds 6, generate_audio true and resolution 720p, with four images in reference_image_urls.
@Image1, @Image2 and @Image3 are the same man from front, three-quarter and profile; @Image4 is his apron. Put him behind the counter of a small bakery at opening time in that apron, sliding a tray into the case and glancing up as the door chimes. Warm ovens, flat morning light.Three angles hold the face, the fourth image holds the costume, and the prompt says which is which. Keep that split when you cast your own character.
Need an exact first frame? Use image-to-video
This endpoint has no first- or last-frame field. When the opening picture must match a still exactly, send that still to image-to-video and describe only the motion.
API quick start
Call the Seedance 2.0 Mini API in three steps
- Create an API key. Sign in to PopNow and create a key in the API console. Keys start with sk-popnow- and use the same credits as the website.
- Send the request. POST /jobs/createTask with model bytedance/seedance-2.0-mini/reference-to-video and an input object that follows the parameter table. The response returns a task ID straight away.
- Get the result. Poll GET /jobs/recordInfo with the task ID, or pass a callBackUrl and we post the result to it. Download the output links when the task succeeds.
# 1. Create the task. Keep the Idempotency-Key if you retry after a network error.
export IDEMPOTENCY_KEY="$(uuidgen)"
curl -X POST https://api.popnow.ai/api/v1/jobs/createTask \
-H "Authorization: Bearer $POPNOW_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $IDEMPOTENCY_KEY" \
-d '{
"model": "bytedance/seedance-2.0-mini/reference-to-video",
"input": {
"prompt": "A slow aerial shot drifting over a misty pine forest at sunrise",
"reference_image_urls": [
"https://media.popnow.ai/influencer/examples/ava.webp"
],
"aspect_ratio": "adaptive",
"resolution": "720p",
"duration_seconds": 5,
"generate_audio": true
}
}'
# 2. Copy data.taskId from the response, then poll until state is succeeded, failed, canceled or expired.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
-H "Authorization: Bearer $POPNOW_API_KEY"Replace the prompt and any links with your own. The API tab has the response, polling and callback reference.
Seedance 2.0 Mini API questions
How much does the Seedance 2.0 Mini API cost?
Seedance 2.0 Mini starts at 9 credits ($0.09) for a 5-second clip with Reference to Video, its cheapest task. Prices by option: 480p · true 1.65 credits per second, 720p · true 3.54 credits per second, 480p · false 3.69 credits per second, true · 480p · false 5.4 credits per second. Credits are the same as on the website (1 credit = $0.01), new accounts get 30 free credits, and failed tasks are refunded.
What is the model name for Seedance 2.0 Mini in the API?
Put bytedance/seedance-2.0-mini/text-to-video for Create Video; bytedance/seedance-2.0-mini/image-to-video for Image to Video; bytedance/seedance-2.0-mini/reference-to-video for Reference to Video; bytedance/seedance-2.0-mini/video-extend for Extend Video in the model field of POST /jobs/createTask.
Is Seedance 2.0 Mini good enough to deliver from?
It shares the line's native audio and its aspect ratio options, adaptive included, but output stops at 720p; when a delivery spec asks for more, move that job to standard Seedance 2.0. Judge it on your own material rather than on tier names: run one brief through Mini and one through 2.0 at identical settings and compare the two.
How do I get a clip longer than fifteen seconds?
Chain shots through the frame. Export the final frame of the clip you approved and send it to image-to-video as the opening frame of the next shot, so a long sequence is built from segments you control rather than from one take that drifts.
Does Seedance 2.0 Mini have a seed?
No. Neither Mini nor Fast publishes one. To compare prompt variants, hold every other field constant and read the difference across several takes.
Can I send footage I already have?
As a reference, yes: reference-to-video accepts up to 3 clips that lend motion, pacing and camera language to a new shot. To continue a finished clip, send it to the video-extend endpoint: its final frame opens the next shot and you get one joined file back. There is no edit endpoint.
Does the API generate audio?
Yes, in the same pass as the picture. generate_audio defaults to true on all three endpoints and produces ambience, movement effects and voice locked to the frames. Switching it off does not lower the rate in this tier, so turn it off only when the track will be replaced anyway.
What are the limits of the Seedance 2.0 Mini API?
Clip length: 4–15 s; Resolutions: 480p · 720p; Aspect ratios: 16:9 · 9:16 · 4:3 · 3:4 · 1:1 · 21:9 · adaptive; Reference audio: 3; Reference images: 9. Requests outside these limits are rejected before anything is charged.
Can I try Seedance 2.0 Mini without writing code?
Yes. The Playground runs Seedance 2.0 Mini on your PopNow credits, needs no API key, and shows the matching code for every run.
All Seedance models
Seedance 2.0 Fast has the same settings and is tuned for speed, and full Seedance 2.0 goes up to 4K for delivery.
- Seedance 2.5 APIByteDance's newest: 30-second clips with native audioFrom 56 credits for a 5-second clip
- Seedance 2.0 Mini APILightweight Seedance for quick 720p drafts with soundFrom 9 credits for a 5-second clip
- Seedance 2.0 APICinematic clips up to 4K with native audioFrom 33 credits for a 5-second clip
- Seedance 2.0 Fast APIFaster Seedance 2.0 with sound at 720pFrom 17 credits for a 5-second clip
- Seedance 1.5 Pro APINative-audio clips with an optional locked cameraFrom 9 credits for a 5-second clip

