Seedance 2.5
Overview
Seedance 2.5 is ByteDance’s next-generation AI video model, built for up to 30-second video generation, advanced multimodal reference control, precise local editing, and more flexible, production-ready creative workflows.
Test API KEY: key_00000000000000000000000000000000Endpoints
1. Create Task
Request
POST https://api.pixwithapi.online/api/task/createHeaders
| Header | Value | Required |
|---|---|---|
| Content-Type | application/json | Yes |
| Api-Key | {API_KEY} | Yes |
Request Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
| prompt | string | Yes | The video generation prompt. |
| image_urls | array | Conditional | Provide one required first-frame image and an optional second last-frame image for image-to-video mode. Omit for text-to-video mode. |
| model_id | string | Yes | 2-80 |
| options | object | Yes | Generation options. |
| options.prompt_optimization | boolean | No | Translate and optimize the prompt before generation. Default: false. |
| options.aspect_ratio | string | No | Output aspect ratio. Text-to-video valid values: 'Auto', '16:9', '4:3', '1:1', '3:4', '9:16', '21:9'. Image-to-video (first/last frame) only supports 'Auto'. Default: 'Auto'. |
| options.resolution | string | No | Output resolution. Valid values: '480p', '720p', '1080p'. Default: '480p'. |
| options.duration | int | No | Output duration in seconds. Valid values: 5, 10, 15, 20, 25, 30. Default: 5. |
| options.enable_web_search | boolean | No | Text-to-video only. Enable online search for generation context. Default: true. Ignored for image-to-video. |
| options.sound | boolean | No | Generate synchronized audio. Default: true. |
Example Request — Text-to-Video
{
"prompt": "A cinematic tracking shot through a rainy neon city at night",
"model_id": "2-80",
"options": {
"prompt_optimization": true,
"aspect_ratio": "16:9",
"resolution": "1080p",
"duration": 10,
"enable_web_search": true,
"sound": true
}
}Example Request — Start and End Frame
{
"prompt": "Move smoothly from the opening composition into the final frame",
"image_urls": [
"https://cdn.pixwithapi.online/images/example-first-frame.jpg",
"https://cdn.pixwithapi.online/images/example-last-frame.webp"
],
"model_id": "2-80",
"options": {
"prompt_optimization": true,
"aspect_ratio": "Auto",
"resolution": "480p",
"duration": 15,
"sound": true
}
}Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | int | 1=success, 0=error |
| message | string | Success and failure messages |
| data | object | |
| data.task_id | string | Task identifier. |
| data.estimated_time | int | Estimated time in seconds. |
Response
{
"code": 1,
"message": "success",
"data": {
"task_id": "d425ab4dc256f0ebaa84862b9cea8a3d",
"estimated_time": 500
}
}2. Create Task With R2V
Seedance 2.5 R2V generates video from a prompt and reference media. Reference images help keep the subject consistent; optional videos and audio can guide motion and sound. It supports 1–10 images, up to 5 videos, and up to 5 audio clips.
| Parameter | Type | Required | Description |
|---|---|---|---|
| model_id | string | Yes | 2-81. |
| prompt | string | Yes | Video generation prompt, 1–12,000 characters. |
| reference_urls | object | Yes | Reference media URLs; use this instead of image_urls. |
| reference_urls.reference_images | array of URLs | Yes | 1–10 reference images. |
| reference_urls.reference_videos | array of URLs | No | Up to 5 reference videos. |
| reference_urls.reference_audios | array of URLs | No | Up to 5 reference audio clips. |
| options | object | No | Output settings. Omitted fields use the defaults below. |
| options.prompt_optimization | boolean | No | Translate and optimize the prompt before generation. Default: true. |
| options.aspect_ratio | string | No | Output aspect ratio: Auto, 16:9, 4:3, 1:1, 3:4, 9:16, or 21:9. Default: Auto. |
| options.resolution | string | No | Output resolution: 480p, 720p, or 1080p. Default: 480p. |
| options.duration | int | No | Output duration in seconds: 5, 10, 15, 20, 25, or 30. Default: 5. |
| options.sound | boolean | No | Generate synchronized audio. Default: true. |
{
"model_id": "2-81",
"prompt": "Keep the subject consistent with the reference image and motion",
"reference_urls": {
"reference_images": ["https://media.example.com/subject.png"],
"reference_videos": ["https://media.example.com/motion.mp4"],
"reference_audios": []
},
"options": {
"prompt_optimization": true,
"aspect_ratio": "Auto",
"resolution": "720p",
"duration": 10,
"sound": true
}
}Response
{"code":1,"message":"success","data":{"task_id":"d425ab4dc256f0ebaa84862b9cea8a3d"}}Last updated on