Introduction
Send image_url and prompt to animate a still; last_image_url, duration_seconds, resolution and generate_audio are optional, with watermark, return_last_frame and output_format as extras. There is no aspect_ratio field, because the clip keeps the shape of the start image. Write the prompt about motion, camera and sound instead of describing the photo a second time.
| Field | Value |
|---|---|
| Input | Image |
| Output | Video |
| Publisher | ByteDance (Seedance 2.5 Flash, speed tier of Seedance 2.5, announced by BytePlus on 12 November 2026) |
| API names | bytedance/seedance-2.5-flash/text-to-video, image-to-video, reference-to-video, video-edit, video-extend |
| Resolution | 480p or 720p (default 720p); 1080p and 4K not supported |
| Clip length | 4–30 whole seconds, default 5; video-edit follows its 4–30 s source |
| Aspect ratio | 16:9 (default), 9:16, 4:3, 3:4, 1:1, 21:9 or adaptive on text and reference requests; image-to-video follows the start image |
| Reference limits | Up to 10 images, 5 clips (30 s in total) and 5 audio files on reference-to-video |
| Reference clip rules | Each clip counts as at least 2 s and needs about 409,600 pixels (854×480 or larger) |
| Edit inputs |
|
| Audio |
|
| Output options | mp4 (default) or mov; watermark off by default; |
| Billing basis | Per second by resolution; reference clips add their seconds; edits bill source seconds; failed generations are free |
| Measured render time | 84 s to about 11 min for 4 s at 480p (13 November 2026 runs) |
Key features & highlights
Flagship workflows at a lower ceiling
Flash keeps the four Seedance 2.5 workflows that fit drafting (text, start and end frames, mixed references, clip editing), drops 1080p and 4K, and adds a video-extend built on its image-to-video mode. BytePlus presents the trade as results close to the flagship at nearly twice the speed. Our 4-second 480p renders took anywhere from 84 seconds to about 11 minutes, so measure speed on your own queue.
Give every upload a job in the prompt
Name uploads by type and order with a space: @Image 1, @Video 1, @Audio 1. With two portraits as @Image 1 and @Image 2 in 16:9, both people appeared together in one elevator scene and kept their faces, hair and clothes. With one image, one clip and one voice file, the clip's street, yellow tram and tracking camera carried over, but the person stayed back to the camera and the face of @Image 1 barely showed.
A sunny street turned into a snowy evening
Both riders, their bikes, the tram and the camera move matched the source frame by frame, and the weather and light changed while nothing else did. That was a 4.0 s clip at 480p with audio off, which also kept the original soundtrack.
One switch decides whose soundtrack you get
generate_audio is on by default and produces speech, effects and ambience with the picture. In video-edit, switching it off keeps the source clip's own track (44.1 kHz in our test), while switching it on generates a new one that can follow @Audio 1. The switch has no effect on the price.
Request parameters
| Parameter | Required | Description |
|---|---|---|
prompt | Yes | Required. Say what moves, in what order, how the camera behaves and what is heard, and let the picture carry the look. at least 1 characters · at most 20000 characters |
image_url | Yes | Required. |
last_image_url | No | Optional end frame, sent together with |
resolution | No | 480p or 720p, default 720p; the per-second rate depends on the choice. |
duration_seconds | No | Whole seconds from 4 to 30, default 5, and every requested second is billed. |
generate_audio | No | On by default: sound is generated in the same pass from your Audio: line and the picture. Turn it off for a silent clip; the price is the same either way. Default: |
output_format | No | mp4 (default) or mov. Choose the container your editor or player expects; it does not change the picture size or the price. |
return_last_frame | No | Off by default. Turn it on to also receive the final frame as a JPEG that you can send as |
watermark | No | Off by default. Turn it on to have the model add its visible watermark to the frames, for example on review copies. Default: |
Pricing
Charged per requested second, with the rate set by the resolution you pick. An end frame, the audio switch, the watermark, the last-frame image and the file format leave the price unchanged, and failed generations are not charged.
| Specification | Price |
|---|---|
| $0.115 / second |
| $0.2392 / second |
Use cases
Trying a shot plan before a final render
Send a 4-second, 480p, 16:9 prompt that ends with an Audio: line, such as a rain-soaked night crosswalk. Our run returned 854×480 at 24 fps, 4.064 s long, with an AAC stereo track of rain and laughter. Change one phrase and rerun to see what moved.
Restyling footage you already shot
Upload a 4–30 second clip, describe the change, then list what must stay. A sunny street with two cyclists and a tram became a snowy evening in our test, and with generate_audio switched off the original soundtrack came back unchanged.
Character and product mockups
Attach a portrait and a product photo as @Image 1 and @Image 2 and ask for 9:16. Our two-image test returned 480×854 with the man lifting a glass dropper bottle toward the lens, so both references showed up. Use the result to judge the idea before building a polished version.
Looping a portrait animation
Give the same photo as image_url and last_image_url and describe the motion between them. Our potter portrait returned a 562×748 clip of 4.064 s whose opening and closing frames both matched the source pose.
Chaining one shot into the next
Set return_last_frame to true and the MP4 arrives with a JPEG of its closing frame (854×480 at 480p 16:9 in our test). Pass that JPEG as image_url of the next image-to-video request so the following shot begins where the last one stopped.
Prompt guide & pro tips
Choose the endpoint for your input
Use text-to-video for a prompt alone, image-to-video for a start frame, reference-to-video for images, clips or a voice, video-edit for an existing 4–30 second clip, and video-extend to add 4–30 seconds to a clip of up to 60 seconds. All five share the 480p/720p range and the
generate_audioswitch.Send the createTask request
POST to https://api.spicyapi.ai/api/v1/jobs/createTask with the header Authorization: Bearer YOUR_SPICY_API_KEY and the body {"model": "bytedance/seedance-2.5-flash/text-to-video", "input": {"prompt": "A lighthouse keeper climbs a spiral stair at dawn and wipes fog from the lamp glass. Audio: wind, boots on iron.", "
duration_seconds": 4, "resolution": "480p"}}.Poll for the finished clip
The response gives a taskId in state queued. Call GET /api/v1/jobs/recordInfo?taskId=YOUR_TASK_ID, or pass a callBackUrl, until the state is succeeded, then read the MP4 address from output.assets. Field details are in the task guide at docs.spicyapi.ai/docs/tasks.
Change one phrase, then move up
Compare variations at 480p and 4 seconds, altering a single phrase per run. When a take works, rerun it at 720p and your target length, or send the same brief to Seedance 2.5 for 1080p.
Seedance 2.5 Flash image to video in one call
Seedance 2.5 Flash image to video is ByteDance's way to animate one picture on the speed tier of Seedance 2.5. You send the picture as image_url and a prompt about what should move. The model returns a 4 to 30 second MP4 at 480p or 720p that opens on your picture, with sound generated in the same pass. Add last_image_url and the clip lands on a second picture, which covers loops, return-to-pose shots and A-to-B transitions (often searched as first-and-last-frame video). BytePlus, ByteDance's cloud platform, says Flash gives results close to Seedance 2.5 at nearly twice the generation speed.
Request example
POST https://api.spicyapi.ai/api/v1/jobs/createTask with Authorization: Bearer YOUR_SPICY_API_KEY and Content-Type: application/json. This body is our potter test, one portrait used as both start and end frame:
{
"model": "bytedance/seedance-2.5-flash/image-to-video",
"input": {
"image_url": "https://example.com/potter-portrait.jpg",
"last_image_url": "https://example.com/potter-portrait.jpg",
"prompt": "The potter cups the spinning clay and slowly draws its wall upward, then lifts her eyes to the camera with a warm smile and settles back into the same pose. Locked-off medium shot, soft window light. Audio: the steady hum of the wheel and the wet squeak of clay, no music.",
"duration_seconds": 4,
"resolution": "480p",
"generate_audio": true
}
}
Response example
Submission returns a task id at once:
{"code": 200, "msg": "success", "data": {"taskId": "task_abc123", "state": "queued"}}
Poll GET /api/v1/jobs/recordInfo?taskId=task_abc123 or pass callBackUrl. A finished task lists the MP4 (see the task API guide):
{"code": 200, "msg": "success", "data": {"taskId": "task_abc123", "state": "succeeded", "output": {"assets": [{"url": "https://example.com/potter.mp4"}]}}}
Parameters
| Parameter | Values | Default |
|---|---|---|
image_url | Start frame | Required |
last_image_url | End frame, sent with image_url | Optional |
prompt | Motion, camera and sound | Required |
duration_seconds | 4 to 30 | 5 |
resolution | 480p, 720p | 720p |
generate_audio | true, false | true |
watermark | Visible model watermark | false |
return_last_frame | Also return the final frame as a JPEG | false |
output_format | mp4, mov | mp4 |
There is no aspect_ratio field. BytePlus's documentation says the model keeps the output aspect ratio consistent with the start frame.
How billing works
You pay per requested second, and the resolution sets the rate; the price on this page shows both. The potter request asked for 4 seconds, the file measured 4.064 seconds, and the charge was for 4. An end frame, audio on or off, the watermark, the last-frame JPEG and the file format do not change the price. Failed generations are not charged.
Tips for good results
- Choose a start frame that already looks like the opening. The picture fixes subject, setting and light, so place the subject where the shot should begin.
- Crop before you upload. Our portrait source came back as 562×748 at 480p. Cut 9:16 for vertical, 1:1 for square or 16:9 for wide.
- Prompt the motion. The potter prompt never describes her clothes or the studio. It lists actions in order, then the camera and the light.
- End with an
Audio:line. List the sounds the picture implies, such as the wheel hum and the wet squeak of clay in our example; "no music" leaves the track free for your own score. - Use
last_image_urlthree ways. Repeat the start picture for a loop or return to pose; our potter run ended back in the source pose. Send a related picture with the same framing and light for an A-to-B move, and describe the path. Or leave it out. - Match the two frames. Keep subject position, crop and light close. We have one loop run on record, so check the join in your player before you rely on a seamless repeat.
- Chain shots. Turn on
return_last_frameand send the JPEG as the nextimage_url.
What our tests showed
On 13 November 2026 the potter request above (4 seconds, 480p, audio on) came back as a 562×748 clip of 4.064 seconds, and the opening and closing frames returned to the source pose. The same request took 84 seconds on one run and 4.8 minutes on another, so plan for minutes and use polling or callBackUrl. Longer and 720p clips take longer.
Limits and errors
- Flash renders 480p and 720p; it has no 1080p, no 4K and no video-extend endpoint.
image_urlandpromptare both required, andduration_secondsis a whole number from 4 to 30. A request that breaks these is invalid; fix the field and resubmit.- The model runs its own copyright and likeness check, which stopped one of our text-to-video requests. A failed task is not charged; change the picture or the wording instead of resending it unchanged.
- Send pictures you own or have licensed for this use. Do not animate a real person's photo without their permission or present the result as real footage.
When to choose a sibling
- Seedance 2.5 image to video for 1080p or 4K, draft mode and extending a clip.
- Seedance 2.0 Fast for the previous generation at 480p and 720p.
- Flash reference to video when the person or product should appear in a new scene instead of opening it.
- Flash text to video when you have no picture, or Flash video edit when you have a clip to restyle.
API quick start
# Generate the idempotency key once; reuse it when retrying after a lost response.
export SPICY_IDEMPOTENCY_KEY="${SPICY_IDEMPOTENCY_KEY:-$(uuidgen)}"
curl -X POST https://api.spicyapi.ai/api/v1/jobs/createTask \
-H "Authorization: Bearer $SPICY_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $SPICY_IDEMPOTENCY_KEY" \
-d '{
"model": "bytedance/seedance-2.5-flash/image-to-video",
"input": {
"duration_seconds": 5,
"image_url": "https://example.com/reference.png",
"output_format": "mp4",
"prompt": "A slow aerial shot drifting over a misty pine forest at sunrise",
"resolution": "720p"
}
}'
# Copy data.taskId from the response into TASK_ID, then poll the status.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.spicyapi.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
-H "Authorization: Bearer $SPICY_API_KEY"
See the API reference for authentication, the complete schema, polling, and error handling.










