Seedance v1.5 Pro Image to Video

POST/v1/run

ByteDance Seedance v1.5 Pro image-to-video model transforming still images into cinematic video with native audio generation, camera control, and professional-grade output quality.

Request body

Submit an async generation request. The model field selects the model; other fields are model-specific input parameters.

stringmodelrequired

Model identifier. Set to bytedance/seedance/1.5/pro/image-to-video.

Default: bytedance/seedance/1.5/pro/image-to-video

stringpromptrequired

The text prompt to generate a video from.

Default: A girl holding a fox, the girl opens her eyes and gently looks at the camera, the fox is held gently, the camera slowly pulls back, the girl's hair is blown by the wind, and the sound of the wind can be heard.

stringimagerequired

The URL of the starting image for video generation.

Optional<string>end_image

The URL of the ending image for video generation.

Optional<integer>duration

Duration of the video in seconds.

Allowed values: 4, 5, 6, 7, 8, 9, 10, 11, 12

Default: 5

Optional<string>aspect_ratio

The aspect ratio of the generated video.

Allowed values: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16

Optional<string>resolution

The resolution of the video to generate.

Allowed values: 480p, 720p, 1080p

Default: 720p

Optional<boolean>camera_fixed

Whether to fix the camera position.

Default: false

Optional<boolean>generate_audio

Whether to generate audio for the video.

Default: true

Optional<integer>seed

The random seed used for generation.

Response Schema

The submit endpoint returns an accepted generation task. Poll the result endpoint with the returned id for terminal outputs or errors.

Optional<string>error

Error message if the task failed. Empty on success.

stringidrequired

Unique identifier for the generation task.

Optional<string>model

Model ID used for the prediction.

Optional<array>outputs

Array of generated content. Empty when status is not completed.

stringstatusrequired

Status of the task: pending, running, completed, failed, or timeout.

Allowed values: pending, running, completed, failed, timeout

Model capabilities

array<string>capability_tagsrequired

Capabilities declared by the model registry.

Default: image-to-video

stringexecution_moderequired

Execution mode declared by the model registry.

Default: async

# 1. Submit a generation request
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "bytedance/seedance/1.5/pro/image-to-video",
  "prompt": "A girl holding a fox, the girl opens her eyes and gently looks at the camera, the fox is held gently, the camera slowly pulls back, the girl's hair is blown by the wind, and the sound of the wind can be heard.",
  "image": "https://p9-arcosite.byteimg.com/tos-cn-i-goo7wpa0wc/a28ec84ff9fc4287a0d98191020a3218~tplv-goo7wpa0wc-image.image",
  "duration": 5,
  "aspect_ratio": "21:9"
}'

# 2. If the response is still running, poll the returned id
curl https://api.sandbase.ai/v1/run/run_abc123 \
  -H "Authorization: Bearer $SANDBASE_API_KEY"

Response202 Accepted

{
  "id": "run_abc123",
  "model": "bytedance/seedance/1.5/pro/image-to-video",
  "status": "running",
  "outputs": []
}