# Seedance 2.0 API 文档
> 通过 AI Studio API 使用 Seedance 2.0 模型生成视频。
## 概览
使用 AI Studio API 创建 Seedance 2.0 生成任务并查询任务状态。接口采用异步流程：先创建任务拿到 `taskId`，再通过任务查询接口轮询结果。
## 认证方式
所有请求都需要在 `Authorization` 请求头中携带 API Key。
```http
Authorization: Bearer YOUR_API_KEY
```
## 可用模型
| modelId | 版本 | 服务商 | 运行模型 |
| --- | --- | --- | --- |
| `video:bytedance-seedance-2` | Seedance 2.0 | ByteDance | seedance-2-0-vip |
| `video:bytedance-seedance-2-0-fast` | Seedance 2.0 Fast | ByteDance | seedance-2-0-fast-vip |
| `video:bytedance-seedance-2-0-mini` | Seedance 2.0 Mini | Bytedance Seedance 2.0 Mini | bytedance/seedance-2-mini |
| `video:fal-bytedance-seedance-2-0-text-to-video` | Seedance 2.0 Text to Video | ByteDance | bytedance/seedance-2.0/text-to-video |
| `video:fal-bytedance-seedance-2-0-fast-text-to-video` | Seedance 2.0 Fast Text to Video | ByteDance | bytedance/seedance-2.0/fast/text-to-video |
| `video:fal-bytedance-seedance-2-0-image-to-video` | Seedance 2.0 Image to Video | ByteDance | bytedance/seedance-2.0/image-to-video |
| `video:fal-bytedance-seedance-2-0-fast-image-to-video` | Seedance 2.0 Fast Image to Video | ByteDance | bytedance/seedance-2.0/fast/image-to-video |
| `video:fal-bytedance-seedance-2-0-reference-to-video` | Seedance 2.0 Reference to Video | ByteDance | bytedance/seedance-2.0/reference-to-video |
| `video:fal-bytedance-seedance-2-0-fast-reference-to-video` | Seedance 2.0 Fast Reference to Video | ByteDance | bytedance/seedance-2.0/fast/reference-to-video |
| `video:fal-bytedance-seedance-2-0-mini-text-to-video` | Seedance 2.0 Mini Text to Video | ByteDance | bytedance/seedance-2.0/mini/text-to-video |
| `video:fal-bytedance-seedance-2-0-mini-image-to-video` | Seedance 2.0 Mini Image to Video | ByteDance | bytedance/seedance-2.0/mini/image-to-video |
| `video:fal-bytedance-seedance-2-0-mini-reference-to-video` | Seedance 2.0 Mini Reference to Video | ByteDance | bytedance/seedance-2.0/mini/reference-to-video |
## 1. 创建生成任务
### 接口地址
```http
POST https://localhost:3000/api/ai-studio/execute
Content-Type: application/json
Authorization: Bearer YOUR_API_KEY
```
### 请求示例
```json
{
"modelId": "video:bytedance-seedance-2",
"isPublic": true,
"payload": {
"model": "seedance-2-0-vip",
"input": {
"prompt": "A serene beach at sunset with waves gently crashing on the shore, palm trees swaying in the breeze, and seagulls flying across the orange sky",
"first_frame_url": "https://templateb.aiquickdraw.com/custom-page/akr/section-images/example2.png",
"last_frame_url": "https://templateb.aiquickdraw.com/custom-page/akr/section-images/example3.png",
"reference_image_urls": [
"https://templateb.aiquickdraw.com/custom-page/akr/section-images/example1.png"
],
"reference_video_urls": [
"https://templateb.aiquickdraw.com/custom-page/akr/section-images/example1.mp4"
],
"reference_audio_urls": [
"https://templateb.aiquickdraw.com/custom-page/akr/section-images/example1.mp3"
],
"return_last_frame": false,
"generate_audio": false,
"resolution": "720p",
"aspect_ratio": "16:9",
"duration": 15,
"web_search": false
}
}
}
```
### 成功响应
```json
{
"success": true,
"data": {
"modelId": "video:bytedance-seedance-2",
"generationId": "generation-id",
"reservedCredits": 20,
"taskId": "provider-task-id",
"state": "queued"
}
}
```
## 2. 查询任务状态
### 接口
```http
GET https://localhost:3000/api/ai-studio/tasks/{taskId}
Authorization: Bearer YOUR_API_KEY
```
### 成功响应
```json
{
"success": true,
"data": {
"generationId": "generation-id",
"taskId": "provider-task-id",
"modelId": "video:bytedance-seedance-2",
"state": "succeeded",
"mediaUrls": [
"https://example.com/result.mp4"
],
"reservedCredits": 20,
"refundedCredits": 0
}
}
```
## 请求字段
### Seedance 2.0
#### Payload 字段
| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `model` | enum | 是 | `"seedance-2-0-vip"` | seedance-2-0-vip | The model name to use for generation. Required field. - Must be `seedance-2-0-vip` for this endpoint |
| `input` | object | 是 | `-` | - | Input parameters for the generation task |
#### input 字段
| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `prompt` | string | 否 | `"A serene beach at sunset with waves gently crashing on the shore, palm trees swaying in the breeze, and seagulls flying across the orange sky"` | - | The text prompt used to generate the video. Required field. (Min length: 3, Max length: 20000 characters) |
| `first_frame_url` | string | 否 | `-` | - | First frame image url or asset://{assetId} (for example: asset://asset-20260404242101-76djj) |
| `last_frame_url` | string | 否 | `-` | - | End frame image url or asset://{assetId} (for example: asset://asset-20260404242101-76djj) |
| `reference_image_urls` | string[] | 否 | `["https://file.aiquickdraw.com/custom-page/akr/section-images/example1.png"]` | - | Enter a list of image URLs or asset://{assetId} (for example: asset://asset-20260404242101-76djj).
Single image requirements:
Format: jpeg, png, webp, bmp, tiff, gif.
Aspect ratio (width/height): (0.4, 2.5)
Width and height (px): (300, 6000)
Size: Single image less than 30 MB.
Maximum number of files: The sum of the number of frames at the beginning and end must not exceed 9.. |
| `reference_video_urls` | string[] | 否 | `-` | - | Enter a list of video URLs or asset://{assetId} (for example: asset://asset-20260404242101-76djj) .
Single video requirements:
Video format: mp4, mov.
Resolution: 480p, 720p
Duration: Single video duration [2, 15] s, maximum 3 reference videos, total duration of all videos not exceeding 15 seconds.
Dimensions:
Aspect ratio (width/height): [0.4, 2.5]
Width/height (px): [300, 6000]
Total pixels: [640×640=409600, 834×1112=927408], i.e., the product of width and height must meet the range requirement of [409600, 927408].
Size: Single video not exceeding 50 MB.
Frame rate (FPS): [24, 60] |
| `reference_audio_urls` | string[] | 否 | `-` | - | Enter a list of audio URLs or asset://{assetId} (for example: asset://asset-20260404242101-76djj) .
Single audio requirements:
Format: wav, mp3
Duration: Single audio duration [2, 15] s, maximum 3 reference audios, total duration of all audios not exceeding 15 s.
Size: Single audio file size not exceeding 15 MB. |
| `return_last_frame` | boolean | 否 | `false` | - | Whether to return the last frame of the video as an image. |
| `generate_audio` | boolean | 否 | `true` | - | Whether to generate audio for the video. - **true**: Generate with audio
- **false**: Generate without audio |
| `resolution` | enum | 否 | `"720p"` | 480p, 720p, 1080p, 4k | Video resolution - 480p for faster generation, 720p for balance, 1080p for High-quality video, 4K Ultra-High Definition, delivering perfect visual details. |
| `aspect_ratio` | enum | 否 | `"16:9"` | 1:1, 4:3, 3:4, 16:9, 9:16, 21:9, adaptive | Video aspect ratio configuration. Required field. |
| `duration` | number | 否 | `5` | - | Video duration in 4-15 seconds. |
| `web_search` | boolean | 否 | `false` | - | Use online search |
| `nsfw_checker` | boolean | 否 | `-` | - | Defaults to false. You can set it to false based on your needs. If set to false, our content filtering will be disabled, and all results will be returned directly by the model itself.
Note: There is no guarantee that everything can be filtered out; if you are not satisfied with the results, you will need to make your own arrangements. |
### Seedance 2.0 Fast
#### Payload 字段
| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `model` | enum | 是 | `"seedance-2-0-fast-vip"` | seedance-2-0-fast-vip | The model name to use for generation. Required field. - Must be `seedance-2-0-fast-vip` for this endpoint |
| `input` | object | 是 | `-` | - | Input parameters for the generation task |
#### input 字段
| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `prompt` | string | 否 | `"A serene beach at sunset with waves gently crashing on the shore, palm trees swaying in the breeze, and seagulls flying across the orange sky"` | - | The text prompt used to generate the video. Required field. (Min length: 3, Max length: 20000 characters) |
| `first_frame_url` | string | 否 | `-` | - | First frame image url or asset://{assetId} (for example: asset://asset-20260404242101-76djj) |
| `last_frame_url` | string | 否 | `-` | - | End frame image url or asset://{assetId} (for example: asset://asset-20260404242101-76djj) |
| `reference_image_urls` | string[] | 否 | `["https://file.aiquickdraw.com/custom-page/akr/section-images/example1.png"]` | - | Enter a list of image URLs or asset://{assetId} (for example: asset://asset-20260404242101-76djj).
Single image requirements:
Format: jpeg, png, webp, bmp, tiff, gif.
Aspect ratio (width/height): (0.4, 2.5)
Width and height (px): (300, 6000)
Size: Single image less than 30 MB.
Maximum number of files: The sum of the number of frames at the beginning and end must not exceed 9.. |
| `reference_video_urls` | string[] | 否 | `-` | - | Enter a list of video URLs or asset://{assetId} (for example: asset://asset-20260404242101-76djj).
Single video requirements:
Video format: mp4, mov.
Resolution: 480p, 720p
Duration: Single video duration [2, 15] s, maximum 3 reference videos, total duration of all videos not exceeding 15 seconds.
Dimensions:
Aspect ratio (width/height): [0.4, 2.5]
Width/height (px): [300, 6000]
Total pixels: [640×640=409600, 834×1112=927408], i.e., the product of width and height must meet the range requirement of [409600, 927408].
Size: Single video not exceeding 50 MB.
Frame rate (FPS): [24, 60] |
| `reference_audio_urls` | string[] | 否 | `-` | - | Enter a list of audio URLs or asset://{assetId} (for example: asset://asset-20260404242101-76djj).
Single audio requirements:
Format: wav, mp3
Duration: Single audio duration [2, 15] s, maximum 3 reference audios, total duration of all audios not exceeding 15 s.
Size: Single audio file size not exceeding 15 MB. |
| `return_last_frame` | boolean | 否 | `false` | - | Whether to return the last frame of the video as an image. |
| `generate_audio` | boolean | 否 | `true` | - | Whether to generate audio for the video. - **true**: Generate with audio - **false**: Generate without audio |
| `resolution` | enum | 否 | `"720p"` | 480p, 720p | Video resolution - 480p for faster generation, 720p for balance |
| `aspect_ratio` | enum | 否 | `"16:9"` | 1:1, 4:3, 3:4, 16:9, 9:16, 21:9, adaptive | Video aspect ratio configuration. Required field. |
| `duration` | number | 否 | `5` | - | Video duration in 4-15 seconds. |
| `web_search` | boolean | 否 | `false` | - | Use online search. (Web search only can be used in the scene of t2v) |
| `nsfw_checker` | boolean | 否 | `-` | - | Defaults to false. You can set it to false based on your needs. If set to false, our content filtering will be disabled, and all results will be returned directly by the model itself.
Note: There is no guarantee that everything can be filtered out; if you are not satisfied with the results, you will need to make your own arrangements. |
### Seedance 2.0 Mini
#### Payload 字段
| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `model` | enum | 是 | `"bytedance/seedance-2-mini"` | bytedance/seedance-2-mini | The model name to use for generation. Required field. - Must be `bytedance/seedance-2-mini` for this endpoint |
| `input` | object | 是 | `-` | - | Input parameters for the generation task |
#### input 字段
| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `prompt` | string | 否 | `"A serene beach at sunset with waves gently crashing on the shore, palm trees swaying in the breeze, and seagulls flying across the orange sky"` | - | The text prompt used to generate the video. Required field. (Min length: 3, Max length: 20000 characters) |
| `first_frame_url` | string | 否 | `-` | - | First frame image url or asset://{assetId} (for example: asset://asset-20260404242101-76djj) |
| `last_frame_url` | string | 否 | `-` | - | End frame image url or asset://{assetId} (for example: asset://asset-20260404242101-76djj) |
| `reference_image_urls` | string[] | 否 | `["https://file.aiquickdraw.com/custom-page/akr/section-images/example1.png"]` | - | Enter a list of image URLs or asset://{assetId} (for example: asset://asset-20260404242101-76djj).
Single image requirements:
Format: jpeg, png, webp, bmp, tiff, gif.
Aspect ratio (width/height): (0.4, 2.5)
Width and height (px): (300, 6000)
Size: Single image less than 30 MB.
Maximum number of files: The sum of the number of frames at the beginning and end must not exceed 9.. |
| `reference_video_urls` | string[] | 否 | `-` | - | Enter a list of video URLs or asset://{assetId} (for example: asset://asset-20260404242101-76djj).
Single video requirements:
Video format: mp4, mov.
Resolution: 480p, 720p
Duration: Single video duration [2, 15] s, maximum 3 reference videos, total duration of all videos not exceeding 15 seconds.
Dimensions:
Aspect ratio (width/height): [0.4, 2.5]
Width/height (px): [300, 6000]
Total pixels: [640×640=409600, 834×1112=927408], i.e., the product of width and height must meet the range requirement of [409600, 927408].
Size: Single video not exceeding 50 MB.
Frame rate (FPS): [24, 60] |
| `reference_audio_urls` | string[] | 否 | `-` | - | Enter a list of audio URLs or asset://{assetId} (for example: asset://asset-20260404242101-76djj).
Single audio requirements:
Format: wav, mp3
Duration: Single audio duration [2, 15] s, maximum 3 reference audios, total duration of all audios not exceeding 15 s.
Size: Single audio file size not exceeding 15 MB. |
| `generate_audio` | boolean | 否 | `true` | - | Whether to generate audio for the video. - **true**: Generate with audio - **false**: Generate without audio |
| `resolution` | enum | 否 | `"720p"` | 480p, 720p | Video resolution - 480p for faster generation, 720p for balance |
| `aspect_ratio` | enum | 否 | `"16:9"` | 1:1, 4:3, 3:4, 16:9, 9:16, 21:9, adaptive | Video aspect ratio configuration. Required field. |
| `duration` | number | 否 | `5` | - | Video duration in 4-15 seconds. |
| `web_search` | boolean | 否 | `-` | - | Use online search. (Web search only can be used in the scene of t2v) |
| `nsfw_checker` | boolean | 否 | `-` | - | Defaults to false. You can set it to false based on your needs. If set to false, our content filtering will be disabled, and all results will be returned directly by the model itself.
Note: There is no guarantee that everything can be filtered out; if you are not satisfied with the results, you will need to make your own arrangements. |
### Seedance 2.0 Text to Video
#### Payload 字段
| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `bitrate_mode` | enum | 否 | `"standard"` | standard, high | Output bitrate mode. 'high' requests a higher-quality, larger-file encode from the model; 'standard' uses the default bitrate. |
| `prompt` | string | 是 | `"An octopus finds a football in the ocean and excitedly calls its octopus friends to come and play. Cut scene to an octopus football game under the sea."` | - | The text prompt used to generate the video |
| `generate_audio` | boolean | 否 | `true` | - | Whether to generate synchronized audio for the video, including sound effects, ambient sounds, and lip-synced speech. The cost of video generation is the same regardless of whether audio is generated or not. |
| `duration` | enum | 否 | `"auto"` | auto, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 | Duration of the video in seconds. Supports 4 to 15 seconds, or auto to let the model decide based on the prompt. |
| `resolution` | enum | 否 | `"720p"` | 480p, 720p, 1080p, 4k | Video resolution - 480p for faster generation, 720p for balance, 1080p for high quality, 4k for highest quality. |
| `aspect_ratio` | enum | 否 | `"auto"` | auto, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 | The aspect ratio of the generated video. Use 16:9 for landscape, 9:16 for portrait/vertical, 1:1 for square, 21:9 for ultrawide cinematic, or auto to let the model decide. |
| `end_user_id` | object | 否 | `-` | - | The unique user ID of the end user. |
#### input 字段
_该模型暂无字段配置。_
### Seedance 2.0 Fast Text to Video
#### Payload 字段
| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `bitrate_mode` | enum | 否 | `"standard"` | standard, high | Output bitrate mode. 'high' requests a higher-quality, larger-file encode from the model; 'standard' uses the default bitrate. |
| `prompt` | string | 是 | `"An octopus finds a football in the ocean and excitedly calls its octopus friends to come and play. Cut scene to an octopus football game under the sea."` | - | The text prompt used to generate the video |
| `generate_audio` | boolean | 否 | `true` | - | Whether to generate synchronized audio for the video, including sound effects, ambient sounds, and lip-synced speech. The cost of video generation is the same regardless of whether audio is generated or not. |
| `duration` | enum | 否 | `"auto"` | auto, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 | Duration of the video in seconds. Supports 4 to 15 seconds, or auto to let the model decide based on the prompt. |
| `resolution` | enum | 否 | `"720p"` | 480p, 720p | Video resolution - 480p for faster generation, 720p for balance. |
| `aspect_ratio` | enum | 否 | `"auto"` | auto, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 | The aspect ratio of the generated video. Use 16:9 for landscape, 9:16 for portrait/vertical, 1:1 for square, 21:9 for ultrawide cinematic, or auto to let the model decide. |
| `end_user_id` | object | 否 | `-` | - | The unique user ID of the end user. |
#### input 字段
_该模型暂无字段配置。_
### Seedance 2.0 Image to Video
#### Payload 字段
| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `bitrate_mode` | enum | 否 | `"standard"` | standard, high | Output bitrate mode. 'high' requests a higher-quality, larger-file encode from the model; 'standard' uses the default bitrate. |
| `duration` | enum | 否 | `"auto"` | auto, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 | Duration of the video in seconds. Supports 4 to 15 seconds, or auto to let the model decide based on the prompt. |
| `resolution` | enum | 否 | `"720p"` | 480p, 720p, 1080p, 4k | Video resolution - 480p for faster generation, 720p for balance, 1080p for high quality, 4k for highest quality. |
| `aspect_ratio` | enum | 否 | `"auto"` | auto, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 | The aspect ratio of the generated video. Use 16:9 for landscape, 9:16 for portrait/vertical, 1:1 for square, 21:9 for ultrawide cinematic, or auto to infer from the input image. |
| `end_user_id` | object | 否 | `-` | - | The unique user ID of the end user. |
| `end_image_url` | object | 否 | `-` | - | The URL of the image to use as the last frame of the video. When provided, the generated video will transition from the starting image to this ending image. Supported formats: JPEG, PNG, WebP. Max 30 MB. |
| `prompt` | string | 是 | `"An octopus finds a football in the ocean and excitedly calls its octopus friends to come and play. Cut scene to an octopus football game under the sea."` | - | The text prompt describing the desired motion and action for the video. |
| `generate_audio` | boolean | 否 | `true` | - | Whether to generate synchronized audio for the video, including sound effects, ambient sounds, and lip-synced speech. The cost of video generation is the same regardless of whether audio is generated or not. |
| `image_url` | string | 是 | `"https://v3b.fal.media/files/b/0a8eba37/Cqg-4Uwzyz4DELfceT1CF_a17e588773ec45b1a9e6f100a787b80b.jpg"` | - | The URL of the starting frame image to animate. Supported formats: JPEG, PNG, WebP. Max 30 MB. |
#### input 字段
_该模型暂无字段配置。_
### Seedance 2.0 Fast Image to Video
#### Payload 字段
| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `bitrate_mode` | enum | 否 | `"standard"` | standard, high | Output bitrate mode. 'high' requests a higher-quality, larger-file encode from the model; 'standard' uses the default bitrate. |
| `duration` | enum | 否 | `"auto"` | auto, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 | Duration of the video in seconds. Supports 4 to 15 seconds, or auto to let the model decide based on the prompt. |
| `resolution` | enum | 否 | `"720p"` | 480p, 720p | Video resolution - 480p for faster generation, 720p for balance. |
| `aspect_ratio` | enum | 否 | `"auto"` | auto, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 | The aspect ratio of the generated video. Use 16:9 for landscape, 9:16 for portrait/vertical, 1:1 for square, 21:9 for ultrawide cinematic, or auto to infer from the input image. |
| `end_user_id` | object | 否 | `-` | - | The unique user ID of the end user. |
| `end_image_url` | object | 否 | `-` | - | The URL of the image to use as the last frame of the video. When provided, the generated video will transition from the starting image to this ending image. Supported formats: JPEG, PNG, WebP. Max 30 MB. |
| `prompt` | string | 是 | `"An octopus finds a football in the ocean and excitedly calls its octopus friends to come and play. Cut scene to an octopus football game under the sea."` | - | The text prompt describing the desired motion and action for the video. |
| `generate_audio` | boolean | 否 | `true` | - | Whether to generate synchronized audio for the video, including sound effects, ambient sounds, and lip-synced speech. The cost of video generation is the same regardless of whether audio is generated or not. |
| `image_url` | string | 是 | `"https://v3b.fal.media/files/b/0a8eba37/Cqg-4Uwzyz4DELfceT1CF_a17e588773ec45b1a9e6f100a787b80b.jpg"` | - | The URL of the starting frame image to animate. Supported formats: JPEG, PNG, WebP. Max 30 MB. |
#### input 字段
_该模型暂无字段配置。_
### Seedance 2.0 Reference to Video
#### Payload 字段
| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `bitrate_mode` | enum | 否 | `"standard"` | standard, high | Output bitrate mode. 'high' requests a higher-quality, larger-file encode from the model; 'standard' uses the default bitrate. |
| `duration` | enum | 否 | `"auto"` | auto, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 | Duration of the video in seconds. Supports 4 to 15 seconds, or auto to let the model decide based on the prompt. |
| `resolution` | enum | 否 | `"720p"` | 480p, 720p, 1080p, 4k | Video resolution - 480p for faster generation, 720p for balance, 1080p for high quality, 4k for highest quality. |
| `aspect_ratio` | enum | 否 | `"auto"` | auto, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 | The aspect ratio of the generated video. Use 16:9 for landscape, 9:16 for portrait/vertical, 1:1 for square, 21:9 for ultrawide cinematic, or auto to let the model decide. |
| `end_user_id` | object | 否 | `-` | - | The unique user ID of the end user. |
| `video_urls` | string[] | 否 | `-` | - | Reference videos to guide video generation. Refer to them in the prompt as @Video1, @Video2, etc. Supported formats: MP4, MOV. Up to 3 videos, combined duration must be between 2 and 15 seconds, total size under 50 MB. Each video must be between ~480p (640x640) and ~720p (834x1112) in resolution. |
| `prompt` | string | 是 | `"An octopus finds a football in the ocean and excitedly calls its octopus friends to come and play. Cut scene to an octopus football game under the sea."` | - | The text prompt used to generate the video. |
| `generate_audio` | boolean | 否 | `true` | - | Whether to generate synchronized audio for the video, including sound effects, ambient sounds, and lip-synced speech. The cost of video generation is the same regardless of whether audio is generated or not. |
| `audio_urls` | string[] | 否 | `-` | - | Reference audio to guide video generation. Refer to them in the prompt as @Audio1, @Audio2, etc. Supported formats: MP3, WAV. Up to 3 files, combined duration must not exceed 15 seconds. Max 15 MB per file.If audio is provided, at least one reference image or video is required. |
| `image_urls` | string[] | 否 | `["https://v3b.fal.media/files/b/0a8eba37/Cqg-4Uwzyz4DELfceT1CF_a17e588773ec45b1a9e6f100a787b80b.jpg"]` | - | Reference images to guide video generation. Refer to them in the prompt as @Image1, @Image2, etc. Supported formats: JPEG, PNG, WebP. Max 30 MB per image. Up to 9 images. Total files across all modalities must not exceed 12. |
#### input 字段
_该模型暂无字段配置。_
### Seedance 2.0 Fast Reference to Video
#### Payload 字段
| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `bitrate_mode` | enum | 否 | `"standard"` | standard, high | Output bitrate mode. 'high' requests a higher-quality, larger-file encode from the model; 'standard' uses the default bitrate. |
| `duration` | enum | 否 | `"auto"` | auto, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 | Duration of the video in seconds. Supports 4 to 15 seconds, or auto to let the model decide based on the prompt. |
| `resolution` | enum | 否 | `"720p"` | 480p, 720p | Video resolution - 480p for faster generation, 720p for balance. |
| `aspect_ratio` | enum | 否 | `"auto"` | auto, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 | The aspect ratio of the generated video. Use 16:9 for landscape, 9:16 for portrait/vertical, 1:1 for square, 21:9 for ultrawide cinematic, or auto to let the model decide. |
| `end_user_id` | object | 否 | `-` | - | The unique user ID of the end user. |
| `video_urls` | string[] | 否 | `-` | - | Reference videos to guide video generation. Refer to them in the prompt as @Video1, @Video2, etc. Supported formats: MP4, MOV. Up to 3 videos, combined duration must be between 2 and 15 seconds, total size under 50 MB. Each video must be between ~480p (640x640) and ~720p (834x1112) in resolution. |
| `prompt` | string | 是 | `"An octopus finds a football in the ocean and excitedly calls its octopus friends to come and play. Cut scene to an octopus football game under the sea."` | - | The text prompt used to generate the video. |
| `generate_audio` | boolean | 否 | `true` | - | Whether to generate synchronized audio for the video, including sound effects, ambient sounds, and lip-synced speech. The cost of video generation is the same regardless of whether audio is generated or not. |
| `audio_urls` | string[] | 否 | `-` | - | Reference audio to guide video generation. Refer to them in the prompt as @Audio1, @Audio2, etc. Supported formats: MP3, WAV. Up to 3 files, combined duration must not exceed 15 seconds. Max 15 MB per file.If audio is provided, at least one reference image or video is required. |
| `image_urls` | string[] | 否 | `["https://v3b.fal.media/files/b/0a8eba37/Cqg-4Uwzyz4DELfceT1CF_a17e588773ec45b1a9e6f100a787b80b.jpg"]` | - | Reference images to guide video generation. Refer to them in the prompt as @Image1, @Image2, etc. Supported formats: JPEG, PNG, WebP. Max 30 MB per image. Up to 9 images. Total files across all modalities must not exceed 12. |
#### input 字段
_该模型暂无字段配置。_
### Seedance 2.0 Mini Text to Video
#### Payload 字段
| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `prompt` | string | 是 | `"An octopus finds a football in the ocean and excitedly calls its octopus friends to come and play. Cut scene to an octopus football game under the sea."` | - | The text prompt used to generate the video |
| `generate_audio` | boolean | 否 | `true` | - | Whether to generate synchronized audio for the video, including sound effects, ambient sounds, and lip-synced speech. The cost of video generation is the same regardless of whether audio is generated or not. |
| `duration` | enum | 否 | `"auto"` | auto, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 | Duration of the video in seconds. Supports 4 to 15 seconds, or auto to let the model decide based on the prompt. |
| `resolution` | enum | 否 | `"720p"` | 480p, 720p | Video resolution - 480p for faster generation, 720p for balance. |
| `aspect_ratio` | enum | 否 | `"auto"` | auto, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 | The aspect ratio of the generated video. Use 16:9 for landscape, 9:16 for portrait/vertical, 1:1 for square, 21:9 for ultrawide cinematic, or auto to let the model decide. |
| `end_user_id` | object | 否 | `-` | - | The unique user ID of the end user. |
#### input 字段
_该模型暂无字段配置。_
### Seedance 2.0 Mini Image to Video
#### Payload 字段
| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `duration` | enum | 否 | `"auto"` | auto, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 | Duration of the video in seconds. Supports 4 to 15 seconds, or auto to let the model decide based on the prompt. |
| `resolution` | enum | 否 | `"720p"` | 480p, 720p | Video resolution - 480p for faster generation, 720p for balance. |
| `aspect_ratio` | enum | 否 | `"auto"` | auto, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 | The aspect ratio of the generated video. Use 16:9 for landscape, 9:16 for portrait/vertical, 1:1 for square, 21:9 for ultrawide cinematic, or auto to infer from the input image. |
| `end_user_id` | object | 否 | `-` | - | The unique user ID of the end user. |
| `end_image_url` | object | 否 | `-` | - | The URL of the image to use as the last frame of the video. When provided, the generated video will transition from the starting image to this ending image. Supported formats: JPEG, PNG, WebP. Max 30 MB. |
| `prompt` | string | 是 | `"An octopus finds a football in the ocean and excitedly calls its octopus friends to come and play. Cut scene to an octopus football game under the sea."` | - | The text prompt describing the desired motion and action for the video. |
| `generate_audio` | boolean | 否 | `true` | - | Whether to generate synchronized audio for the video, including sound effects, ambient sounds, and lip-synced speech. The cost of video generation is the same regardless of whether audio is generated or not. |
| `image_url` | string | 是 | `"https://v3b.fal.media/files/b/0a8eba37/Cqg-4Uwzyz4DELfceT1CF_a17e588773ec45b1a9e6f100a787b80b.jpg"` | - | The URL of the starting frame image to animate. Supported formats: JPEG, PNG, WebP. Max 30 MB. |
#### input 字段
_该模型暂无字段配置。_
### Seedance 2.0 Mini Reference to Video
#### Payload 字段
| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `duration` | enum | 否 | `"auto"` | auto, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 | Duration of the video in seconds. Supports 4 to 15 seconds, or auto to let the model decide based on the prompt. |
| `resolution` | enum | 否 | `"720p"` | 480p, 720p | Video resolution - 480p for faster generation, 720p for balance. |
| `aspect_ratio` | enum | 否 | `"auto"` | auto, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 | The aspect ratio of the generated video. Use 16:9 for landscape, 9:16 for portrait/vertical, 1:1 for square, 21:9 for ultrawide cinematic, or auto to let the model decide. |
| `end_user_id` | object | 否 | `-` | - | The unique user ID of the end user. |
| `video_urls` | string[] | 否 | `-` | - | Reference videos to guide video generation. Refer to them in the prompt as @Video1, @Video2, etc. Supported formats: MP4, MOV. Up to 3 videos, combined duration must be between 2 and 15 seconds, total size under 50 MB. Each video must be between ~480p (640x640) and ~720p (834x1112) in resolution. |
| `prompt` | string | 是 | `"An octopus finds a football in the ocean and excitedly calls its octopus friends to come and play. Cut scene to an octopus football game under the sea."` | - | The text prompt used to generate the video. |
| `generate_audio` | boolean | 否 | `true` | - | Whether to generate synchronized audio for the video, including sound effects, ambient sounds, and lip-synced speech. The cost of video generation is the same regardless of whether audio is generated or not. |
| `audio_urls` | string[] | 否 | `-` | - | Reference audio to guide video generation. Refer to them in the prompt as @Audio1, @Audio2, etc. Supported formats: MP3, WAV. Up to 3 files, combined duration must not exceed 15 seconds. Max 15 MB per file.If audio is provided, at least one reference image or video is required. |
| `image_urls` | string[] | 否 | `["https://v3b.fal.media/files/b/0a8eba37/Cqg-4Uwzyz4DELfceT1CF_a17e588773ec45b1a9e6f100a787b80b.jpg"]` | - | Reference images to guide video generation. Refer to them in the prompt as @Image1, @Image2, etc. Supported formats: JPEG, PNG, WebP. Max 30 MB per image. Up to 9 images. Total files across all modalities must not exceed 12. |
#### input 字段
_该模型暂无字段配置。_
## 价格
创建生成任务时会预扣积分。创建任务响应中的 `reservedCredits` 是本次请求最终预留的积分数量。
| 模型 | 类型 | 规格 | 价格 | 计费方式 |
| --- | --- | --- | --- | --- |
| Seedance 2.0 | 视频转视频 | 480p | 12 积分/秒 | （输入秒数 + 输出秒数）× 12 |
| Seedance 2.0 | 文/图生视频 | 480p | 19 积分/秒 | 输出秒数 × 19 |
| Seedance 2.0 | 视频转视频 | 720p | 25 积分/秒 | （输入秒数 + 输出秒数）× 25 |
| Seedance 2.0 | 文/图生视频 | 720p | 41 积分/秒 | 输出秒数 × 41 |
| Seedance 2.0 | 视频转视频 | 1080p | 62 积分/秒 | （输入秒数 + 输出秒数）× 62 |
| Seedance 2.0 | 文/图生视频 | 1080p | 102 积分/秒 | 输出秒数 × 102 |
| Seedance 2.0 Fast | 视频转视频 | 480p | 9 积分/秒 | （输入秒数 + 输出秒数）× 9 |
| Seedance 2.0 Fast | 文/图生视频 | 480p | 16 积分/秒 | 输出秒数 × 16 |
| Seedance 2.0 Fast | 视频转视频 | 720p | 20 积分/秒 | （输入秒数 + 输出秒数）× 20 |
| Seedance 2.0 Fast | 文/图生视频 | 720p | 33 积分/秒 | 输出秒数 × 33 |
| Seedance 2.0 Mini | 视频转视频 | 480p | 6 积分/秒 | （输入秒数 + 输出秒数）× 6 |
| Seedance 2.0 Mini | 文/图生视频 | 480p | 9.5 积分/秒 | 输出秒数 × 9.5 |
| Seedance 2.0 Mini | 视频转视频 | 720p | 12.5 积分/秒 | （输入秒数 + 输出秒数）× 12.5 |
| Seedance 2.0 Mini | 文/图生视频 | 720p | 20.5 积分/秒 | 输出秒数 × 20.5 |
| Seedance 2.0 Text to Video | 文生视频 | 480p | 27 积分/秒 | 输出秒数 × 27 |
| Seedance 2.0 Text to Video | 文生视频 | 720p | 61 积分/秒 | 输出秒数 × 61 |
| Seedance 2.0 Text to Video | 文生视频 | 1080p | 136 积分/秒 | 输出秒数 × 136 |
| Seedance 2.0 Text to Video | 文生视频 | 4k | 311 积分/秒 | 输出秒数 × 311 |
| Seedance 2.0 Fast Text to Video | 文生视频 | 480p | 23 积分/秒 | 输出秒数 × 23 |
| Seedance 2.0 Fast Text to Video | 文生视频 | 720p | 48 积分/秒 | 输出秒数 × 48 |
| Seedance 2.0 Image to Video | 图生视频 | 480p | 27 积分/秒 | 输出秒数 × 27 |
| Seedance 2.0 Image to Video | 图生视频 | 720p | 61 积分/秒 | 输出秒数 × 61 |
| Seedance 2.0 Image to Video | 图生视频 | 1080p | 136 积分/秒 | 输出秒数 × 136 |
| Seedance 2.0 Image to Video | 图生视频 | 4k | 311 积分/秒 | 输出秒数 × 311 |
| Seedance 2.0 Fast Image to Video | 图生视频 | 480p | 23 积分/秒 | 输出秒数 × 23 |
| Seedance 2.0 Fast Image to Video | 图生视频 | 720p | 48 积分/秒 | 输出秒数 × 48 |
| Seedance 2.0 Reference to Video | 文/图生视频 | 480p | 27 积分/秒 | 输出秒数 × 27 |
| Seedance 2.0 Reference to Video | 视频转视频 | 480p | 16 积分/秒 | （输入秒数 + 输出秒数）× 16 |
| Seedance 2.0 Reference to Video | 文/图生视频 | 720p | 61 积分/秒 | 输出秒数 × 61 |
| Seedance 2.0 Reference to Video | 视频转视频 | 720p | 36 积分/秒 | （输入秒数 + 输出秒数）× 36 |
| Seedance 2.0 Reference to Video | 文/图生视频 | 1080p | 136 积分/秒 | 输出秒数 × 136 |
| Seedance 2.0 Reference to Video | 视频转视频 | 1080p | 82 积分/秒 | （输入秒数 + 输出秒数）× 82 |
| Seedance 2.0 Reference to Video | 文/图生视频 | 4k | 311 积分/秒 | 输出秒数 × 311 |
| Seedance 2.0 Reference to Video | 视频转视频 | 4k | 187 积分/秒 | （输入秒数 + 输出秒数）× 187 |
| Seedance 2.0 Fast Reference to Video | 文/图生视频 | 480p | 23 积分/秒 | 输出秒数 × 23 |
| Seedance 2.0 Fast Reference to Video | 视频转视频 | 480p | 14 积分/秒 | （输入秒数 + 输出秒数）× 14 |
| Seedance 2.0 Fast Reference to Video | 文/图生视频 | 720p | 48 积分/秒 | 输出秒数 × 48 |
| Seedance 2.0 Fast Reference to Video | 视频转视频 | 720p | 29 积分/秒 | （输入秒数 + 输出秒数）× 29 |
| Seedance 2.0 Mini Text to Video | 文生视频 | 480p | 14.4 积分/秒 | 输出秒数 × 14.4 |
| Seedance 2.0 Mini Text to Video | 文生视频 | 720p | 30.9 积分/秒 | 输出秒数 × 30.9 |
| Seedance 2.0 Mini Image to Video | 图生视频 | 480p | 14.4 积分/秒 | 输出秒数 × 14.4 |
| Seedance 2.0 Mini Image to Video | 图生视频 | 720p | 30.9 积分/秒 | 输出秒数 × 30.9 |
| Seedance 2.0 Mini Reference to Video | 文/图生视频 | 480p | 14.4 积分/秒 | 输出秒数 × 14.4 |
| Seedance 2.0 Mini Reference to Video | 文/图生视频 | 720p | 30.9 积分/秒 | 输出秒数 × 30.9 |
## 常见错误
| 状态 | 含义 |
| --- | --- |
| `400` | Invalid request payload |
| `401` | Missing or invalid API key |
| `402` | Insufficient credits or plan limit |
| `404` | Model or task not found |
| `429` | Rate limit exceeded |
| `500` | Server error |