About Seedance 1.5 Pro
ByteDance Seedance 1.5 Pro publishes text-to-video and image-to-video with a camera_fixed switch and native audio, returning 4-to-12-second clips at 480p, 720p or 1080p.
Call it with the model name bytedance/seedance-1.5-pro/text-to-video on POST /jobs/createTask, from 9 credits for a 5-second clip ($0.09). New accounts get 30 free credits to try it in the Playground first.
Introduction
Seedance 1.5 Pro text-to-video builds the whole frame from the prompt and renders the soundtrack in the same pass. camera_fixed decides whether the model invents a camera move or holds the frame absolutely still.
ByteDance Seedance 1.5 Pro publishes two endpoints, text-to-video and image-to-video. Both return 4 to 12 second clips at 480p, 720p or 1080p with native audio, and both carry a camera_fixed switch.
Choose a Seedance 1.5 Pro mode by starting material
| Starting material | Mode |
|---|---|
| An approved opening still | Seedance 1.5 Pro Image to Video |
| A script or scene description | Seedance 1.5 Pro Text to Video |
Key features
camera_fixed holds the frame
Left false, the default, the model invents its own moves: a drift, a push, a slow orbit. Set it to true and the camera stops while the subject keeps moving inside the frame. A locked frame can be tracked, keyed, composited or looped, and neither Seedance 2.0 nor 2.5 offers this switch.
Sound in the same pass
generate_audio defaults to true and renders ambience, movement effects and voice locked to the frames. It moves the request into a higher rate tier, so turn it off for product loops and for plates that will be scored later.
A clear ceiling
Clips run 4 to 12 whole seconds at 480p, 720p or 1080p, in six fixed aspect ratios with 16:9 as the default and no adaptive option. There is no reference endpoint; seed is available at 480p and 720p. Jobs that need 4K, longer takes or a multi-image cast belong on Seedance 2.0 or 2.5; what 1.5 Pro keeps is the camera lock.
Request parameters
| Parameter | Required | Description |
|---|---|---|
seed | No | Reuse the same number to get a repeatable result. ≥ 0 · ≤ 2147483647 |
prompt | Yes | What to generate: subject, action, camera movement and mood. |
resolution | No | Output size. Bigger sizes look sharper and cost more. 480p · 720p · 1080p · Default: 720p |
aspect_ratio | No | The shape of the frame: wide, square or tall. 21:9 · 16:9 · 4:3 · 1:1 · 3:4 · 9:16 · Default: 16:9 |
camera_fixed | No | Locks the camera so only the subject moves. Default: false |
generate_audio | No | Adds sound made to match the picture: voices, ambience and effects. Default: true |
duration_seconds | No | How long the clip runs. You pay per second. ≥ 4 · ≤ 12 · Default: 5 |
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 |
|---|---|---|
| generate_audio false · resolution 480p | 1.68 | $0.017 |
| generate_audio true · resolution 480p | 3.35 | $0.034 |
| generate_audio false · resolution 720p | 3.41 | $0.034 |
| generate_audio true · resolution 720p | 6.81 | $0.068 |
| generate_audio false · resolution 1080p | 7.36 | $0.074 |
| generate_audio true · resolution 1080p | 14.73 | $0.15 |
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
Locked shots for compositing
Set camera_fixed and describe motion that happens inside the frame. The published example is a static wide shot of hotel sheets in which only the sheets and the subject's breathing move: footage that can be keyed, tracked or looped.
A controlled prompt comparison
Lock the camera, keep every other field constant and change one clause per run: the light source, the lens, a single action. Fix seed as well (480p and 720p) and the random start stays put too; a seed is a comparison handle rather than a frame-identical guarantee, so compare a couple of takes of each version, and with the camera locked the difference belongs to the wording.
Painterly and stylised looks
The prompt sets the look as well as the action. One of this endpoint's examples asks for a chiaroscuro oil-painting treatment lit only by candles, with a very slow dolly in and camera_fixed left off.
Prompt guide & pro tips
Decide the camera first
camera_fixed is the first decision on this generation. If the result has to be tracked, keyed, looped or cut against real footage, set it to true and restate the lock in the prompt. If you want a move, leave it false and name it: a push, a pan, a tilt or an orbit.
Adapt the included example
The published example uses aspect_ratio 16:9, camera_fixed true, duration_seconds 5, generate_audio true and resolution 720p.
The lock is set in the field and repeated in the first sentence of the prompt. Every bit of motion belongs to the subject or the sheets.
API quick start
Call the Seedance 1.5 Pro 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-1.5-pro/text-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: $IDEMPOTENCY_KEY" \
-d '{
"model": "bytedance/seedance-1.5-pro/text-to-video",
"input": {
"prompt": "A slow aerial shot drifting over a misty pine forest at sunrise",
"aspect_ratio": "16:9",
"resolution": "720p",
"duration_seconds": 5,
"generate_audio": true
}
}'
# 2. Copy data.taskId from the response, then poll until state is succeeded, failed, canceled or expired.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=$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 1.5 Pro API questions
How much does the Seedance 1.5 Pro API cost?
Seedance 1.5 Pro starts at 9 credits ($0.09) for a 5-second clip with Create Video, its cheapest task. Prices by option: false · 480p 1.68 credits per second, true · 480p 3.35 credits per second, false · 720p 3.41 credits per second, true · 720p 6.81 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 1.5 Pro in the API?
Put bytedance/seedance-1.5-pro/text-to-video for Create Video; bytedance/seedance-1.5-pro/image-to-video for Image to Video; bytedance/seedance-1.5-pro/video-extend for Extend Video in the model field of POST /jobs/createTask.
What does camera_fixed actually do?
It stops the camera. Left false, the model adds its own moves — a drift, a push, a slow orbit. Set true and the frame holds absolutely still while the subject keeps moving inside it, which is what makes the result usable as a plate rather than only as a shot.
Why is there no 4K option on Seedance 1.5 Pro?
This generation publishes 480p, 720p and 1080p only, and stops at twelve seconds. Those are the real ceilings. Jobs that need 4K, thirty seconds or a multi-image cast belong on Seedance 2.0 or 2.5 — which in exchange do not offer the camera lock.
Should I use Seedance 1.5 Pro or Seedance 2.0?
2.0 is longer, larger and has a reference endpoint; 1.5 Pro has the camera lock and a slightly tighter control surface. If the shot has to hold absolutely still, 1.5 Pro is the only generation that will do it on request.
Does Seedance 1.5 Pro accept reference images?
No. This generation publishes text-to-video and image-to-video only — a single opening frame on image-to-video, but no multi-reference endpoint. For a cast carried across several shots, use the reference endpoint on Seedance 2.0 or 2.5.
Does it generate audio?
Yes, in the same pass as the picture. generate_audio defaults to true and produces ambience, movement effects and voice locked to the frames. It moves the request into a higher rate tier, so turn it off for product loops and plates headed for a sound pass.
What are the limits of the Seedance 1.5 Pro API?
Clip length: 4–12 s; Resolutions: 480p · 720p · 1080p; Aspect ratios: 21:9 · 16:9 · 4:3 · 1:1 · 3:4 · 9:16. Requests outside these limits are rejected before anything is charged.
Can I try Seedance 1.5 Pro without writing code?
Yes. The Playground runs Seedance 1.5 Pro on your PopNow credits, needs no API key, and shows the matching code for every run.
All Seedance models
Seedance 2.0 runs longer, reaches 4K and adds reference scenes, but has no camera lock.
- 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