Seedance 2.5 API 调用参考
字节跳动最新款：30 秒视频，原生音频
用一个 PopNow API 密钥，就能在自己的代码里调用 Seedance 2.5。下面列出要填的调用名、这个型号接受的每个输入字段、每次请求花多少积分，以及一段可以直接粘进终端运行的请求。
参数说明直接取自型号的输入 schema，暂时只有英文。
一览
- 出品方
- ByteDance
- 产出
- 视频
- 起价
- 11.07 积分 每秒成片 ($0.1107)
- 一般耗时
- 约 279 秒
1 积分 = 0.01 美元。任务受理时先冻结可能的最高费用，完成后按实际用量结算、向上取整到整积分，多冻的退回；失败的任务不扣积分。想在运行前知道确切数字，先调 POST /api/v1/jobs/quote。
生成视频
bytedance/seedance-2.5/text-to-video
价格
| 选项 | 积分 (每秒成片) | 美元 |
|---|---|---|
generate_audio = false, resolution = 480p | 18.51 | $0.1851 |
generate_audio = true, resolution = 480p | 18.51 | $0.1851 |
generate_audio = false, resolution = 720p | 41.6 | $0.416 |
generate_audio = true, resolution = 720p | 41.6 | $0.416 |
generate_audio = false, resolution = 1080p | 102.35 | $1.0235 |
generate_audio = true, resolution = 1080p | 102.35 | $1.0235 |
参数
| 字段 | 类型 | 默认值 | 取值范围 | 作用 |
|---|---|---|---|---|
prompt必填 | string | — | — | What to generate: subject, action, camera movement and mood. |
aspect_ratio可选 | string | adaptive | 21:9, 16:9, 4:3, 1:1, 3:4, 9:16, adaptive | Aspect ratio of the generated video. |
resolution可选 | string | 720p | 480p, 720p, 1080p | Output resolution. Super-resolution tiers are not offered. |
duration_seconds可选 | integer | 5 | 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, … (+13) | Clip length in seconds. This is the billed quantity. |
generate_audio可选 | boolean | true | — | Generate a native soundtrack synchronised to the picture. |
output_format可选 | string | mp4 | mp4, mov | Container of the returned video. |
enable_web_search可选 | boolean | false | — | Let the model search the web for information related to the prompt before rendering. |
seed可选 | integer | — | 0 到 2147483647 | Random seed. Omit to let the model pick one. |
return_last_frame可选 | boolean | false | — | Also return the clip’s final frame as a separate image. |
watermark可选 | boolean | false | — | Ask the model to watermark the video as AI-generated. |
请求示例
这段请求原样就能运行，没写的字段都用默认值。运行前先把密钥放进环境变量 POPNOW_API_KEY。
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: $(uuidgen)" \
-d '{
"model": "bytedance/seedance-2.5/text-to-video",
"input": {
"prompt": "A paper boat drifts down a rain-soaked street at dusk, neon signs reflecting in the water, slow tracking shot at ground level",
"generate_audio": true,
"duration_seconds": 5,
"resolution": "720p"
}
}'响应里会立刻带回 taskId。之后用 GET /api/v1/jobs/recordInfo 取结果，或者在请求里加上 callBackUrl 等通知。
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=TASK_ID_FROM_CREATE_TASK" \
-H "Authorization: Bearer $POPNOW_API_KEY"图生视频
bytedance/seedance-2.5/image-to-video
价格
| 选项 | 积分 (每秒成片) | 美元 |
|---|---|---|
generate_audio = false, resolution = 480p | 18.51 | $0.1851 |
generate_audio = true, resolution = 480p | 18.51 | $0.1851 |
generate_audio = false, resolution = 720p | 41.6 | $0.416 |
generate_audio = true, resolution = 720p | 41.6 | $0.416 |
generate_audio = false, resolution = 1080p | 102.35 | $1.0235 |
generate_audio = true, resolution = 1080p | 102.35 | $1.0235 |
参数
| 字段 | 类型 | 默认值 | 取值范围 | 作用 |
|---|---|---|---|---|
image_url必填 | string | — | — | URL of the image used as the first frame. |
prompt可选 | string | — | — | What to generate: subject, action, camera movement and mood. |
last_image_url可选 | string | — | — | URL of the image used as the closing frame. Only accepted together with image_url. |
aspect_ratio可选 | string | adaptive | adaptive | Aspect ratio of the generated video. Seedance 2.5 frames an image-to-video clip on the first frame, so adaptive is the only accepted value. |
resolution可选 | string | 720p | 480p, 720p, 1080p | Output resolution. Super-resolution tiers are not offered. |
duration_seconds可选 | integer | 5 | 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, … (+13) | Clip length in seconds. This is the billed quantity. |
generate_audio可选 | boolean | true | — | Generate a native soundtrack synchronised to the picture. |
output_format可选 | string | mp4 | mp4, mov | Container of the returned video. |
enable_web_search可选 | boolean | false | — | Let the model search the web for information related to the prompt before rendering. |
seed可选 | integer | — | 0 到 2147483647 | Random seed. Omit to let the model pick one. |
return_last_frame可选 | boolean | false | — | Also return the clip’s final frame as a separate image. |
watermark可选 | boolean | false | — | Ask the model to watermark the video as AI-generated. |
请求示例
这段请求原样就能运行，没写的字段都用默认值。运行前先把密钥放进环境变量 POPNOW_API_KEY。
示例里的 image_url 用的是 PopNow 的示例素材，换成你自己的公开 HTTPS 链接、上传文件或已保存的素材即可。
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: $(uuidgen)" \
-d '{
"model": "bytedance/seedance-2.5/image-to-video",
"input": {
"prompt": "He lands softly on the rooftop, laughs and turns toward the camera while the balloons sway in the evening breeze; slow push-in",
"image_url": "https://media.popnow.ai/influencer/examples/marco.webp",
"generate_audio": true,
"duration_seconds": 5,
"resolution": "720p"
}
}'响应里会立刻带回 taskId。之后用 GET /api/v1/jobs/recordInfo 取结果，或者在请求里加上 callBackUrl 等通知。
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=TASK_ID_FROM_CREATE_TASK" \
-H "Authorization: Bearer $POPNOW_API_KEY"参考生视频
bytedance/seedance-2.5/reference-to-video
价格
| 选项 | 积分 (每秒成片) | 美元 |
|---|---|---|
generate_audio = false, resolution = 480p, with_video = true | 11.07 | $0.1107 |
generate_audio = true, resolution = 480p, with_video = true | 11.07 | $0.1107 |
generate_audio = false, resolution = 480p, with_video = false | 18.51 | $0.1851 |
generate_audio = true, resolution = 480p, with_video = false | 18.51 | $0.1851 |
generate_audio = false, resolution = 720p, with_video = true | 24.89 | $0.2489 |
generate_audio = true, resolution = 720p, with_video = true | 24.89 | $0.2489 |
generate_audio = false, resolution = 720p, with_video = false | 41.6 | $0.416 |
generate_audio = true, resolution = 720p, with_video = false | 41.6 | $0.416 |
generate_audio = false, resolution = 1080p, with_video = true | 61.23 | $0.6123 |
generate_audio = true, resolution = 1080p, with_video = true | 61.23 | $0.6123 |
generate_audio = false, resolution = 1080p, with_video = false | 102.35 | $1.0235 |
generate_audio = true, resolution = 1080p, with_video = false | 102.35 | $1.0235 |
参数
| 字段 | 类型 | 默认值 | 取值范围 | 作用 |
|---|---|---|---|---|
prompt必填 | string | — | — | What to generate: subject, action, camera movement and mood. |
reference_image_urls可选 | array<string> | — | 最多 30 项 | Reference image URLs that carry over characters, style or scene composition. Up to 30 images. Cannot be combined with a first-frame image. |
reference_video_urls可选 | array<string> | — | 最多 10 项 | Reference video URLs that carry over motion and pacing. Up to 10 clips, 2-30 seconds each and 30 seconds in total. Reference footage is added to the billed duration. |
reference_audio_urls可选 | array<string> | — | 最多 10 项 | Reference audio URLs the generated soundtrack follows, for beat matching or lip sync. Up to 10 clips, 2-30 seconds each and 30 seconds in total. |
aspect_ratio可选 | string | adaptive | 21:9, 16:9, 4:3, 1:1, 3:4, 9:16, adaptive | Aspect ratio of the generated video. |
resolution可选 | string | 720p | 480p, 720p, 1080p | Output resolution. Super-resolution tiers are not offered. |
duration_seconds可选 | integer | 5 | 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, … (+13) | Clip length in seconds. This is the billed quantity. |
generate_audio可选 | boolean | true | — | Generate a native soundtrack synchronised to the picture. |
output_format可选 | string | mp4 | mp4, mov | Container of the returned video. |
enable_web_search可选 | boolean | false | — | Let the model search the web for information related to the prompt before rendering. |
seed可选 | integer | — | 0 到 2147483647 | Random seed. Omit to let the model pick one. |
return_last_frame可选 | boolean | false | — | Also return the clip’s final frame as a separate image. |
watermark可选 | boolean | false | — | Ask the model to watermark the video as AI-generated. |
请求示例
这段请求原样就能运行，没写的字段都用默认值。运行前先把密钥放进环境变量 POPNOW_API_KEY。
示例里的 reference_image_urls 用的是 PopNow 的示例素材，换成你自己的公开 HTTPS 链接、上传文件或已保存的素材即可。
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: $(uuidgen)" \
-d '{
"model": "bytedance/seedance-2.5/reference-to-video",
"input": {
"prompt": "The man from the reference image jogs across a sunlit rooftop at golden hour and smiles at the camera; smooth tracking shot",
"reference_image_urls": [
"https://media.popnow.ai/influencer/examples/ava.webp"
],
"generate_audio": true,
"duration_seconds": 5,
"resolution": "720p"
}
}'响应里会立刻带回 taskId。之后用 GET /api/v1/jobs/recordInfo 取结果，或者在请求里加上 callBackUrl 等通知。
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=TASK_ID_FROM_CREATE_TASK" \
-H "Authorization: Bearer $POPNOW_API_KEY"视频续写
bytedance/seedance-2.5/video-extend
价格
| 选项 | 积分 (每秒成片) | 美元 |
|---|---|---|
generate_audio = false, resolution = 480p, with_video = true | 11.07 | $0.1107 |
generate_audio = true, resolution = 480p, with_video = true | 11.07 | $0.1107 |
generate_audio = false, resolution = 480p, with_video = false | 18.51 | $0.1851 |
generate_audio = true, resolution = 480p, with_video = false | 18.51 | $0.1851 |
generate_audio = false, resolution = 720p, with_video = true | 24.89 | $0.2489 |
generate_audio = true, resolution = 720p, with_video = true | 24.89 | $0.2489 |
generate_audio = false, resolution = 720p, with_video = false | 41.6 | $0.416 |
generate_audio = true, resolution = 720p, with_video = false | 41.6 | $0.416 |
generate_audio = false, resolution = 1080p, with_video = true | 61.23 | $0.6123 |
generate_audio = true, resolution = 1080p, with_video = true | 61.23 | $0.6123 |
generate_audio = false, resolution = 1080p, with_video = false | 102.35 | $1.0235 |
generate_audio = true, resolution = 1080p, with_video = false | 102.35 | $1.0235 |
参数
| 字段 | 类型 | 默认值 | 取值范围 | 作用 |
|---|---|---|---|---|
prompt必填 | string | — | — | Required. Describe what happens next: the action that follows, the camera move and the sound. |
video_url必填 | string (uri) | — | — | The clip to continue: MP4, MOV or WebM, 2 to 60 seconds. Its last 30 seconds at most become reference footage for the new segment and are billed as reference seconds; anything earlier is only joined back on. |
resolution可选 | string | 720p | 480p, 720p, 1080p | Size of the new segment. Match your source; it only sets the quality of the new segment. |
duration_seconds可选 | integer | 5 | 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, … (+13) | Length of the new segment in seconds. The reference seconds taken from your clip are billed on top. |
generate_audio可选 | boolean | true | — | Generate sound for the new segment. The sound of your source is kept either way. |
enable_web_search可选 | boolean | false | — | Let the model search the web for information related to the prompt before rendering. |
seed可选 | integer | — | 0 到 2147483647 | Random seed. Omit to let the model pick one. |
watermark可选 | boolean | false | — | Ask the model to watermark the new segment as AI-generated. |
请求示例
这段请求原样就能运行，没写的字段都用默认值。运行前先把密钥放进环境变量 POPNOW_API_KEY。
示例里的 video_url 用的是 PopNow 的示例素材，换成你自己的公开 HTTPS 链接、上传文件或已保存的素材即可。
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: $(uuidgen)" \
-d '{
"model": "bytedance/seedance-2.5/video-extend",
"input": {
"prompt": "The flowers keep opening while the camera slowly pulls back to reveal a sunlit meadow",
"video_url": "https://media.popnow.ai/effects/flower-bloom-1abd6efb.mp4",
"generate_audio": true,
"duration_seconds": 5,
"resolution": "720p"
}
}'响应里会立刻带回 taskId。之后用 GET /api/v1/jobs/recordInfo 取结果，或者在请求里加上 callBackUrl 等通知。
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=TASK_ID_FROM_CREATE_TASK" \
-H "Authorization: Bearer $POPNOW_API_KEY"