doubao-seedance-1-0-pro-fast-251015

• Text to Video: doubao-seedance-1-0-lite-t2v-250428
• Image to Video: doubao-seedance-1-0-lite-i2v-250428
• Support both Text and Image: doubao-seedance-1-0-pro-250528, doubao-seedance-1-0-pro-fast-251015, doubao-seedance-1-5-pro-251215

Generated video duration, unit: seconds. Supports 2~12 seconds.

Default value for Seedance 1.5 pro and Seedance 1.0 lite: 720p
Default value for Seedance 1.0 pro & pro-fast: 1080p
Video resolution, enum values:

• 480p
• 720p

1080p: Not supported for reference image scenarios, and temporarily not supported by Seedance 1.5 pro

Aspect ratio of the generated video
Default value for Text to Video is generally 16:9
Default value for Image to Video is generally adaptive.
Special note: The default value for reference image to video is 16:9
Default value for Seedance 1.5 pro is adaptive

Specify the service level type for processing this request, enum values:

• default: Online inference mode, with lower RPM and concurrency quotas (see Model List for details), suitable for scenarios with high requirements on inference timeliness.
• flex: Offline inference mode, with higher TPD quotas (see Model List for details), priced at 50% of online inference, suitable for scenarios with low requirements on inference latency.

Only supported by Seedance 1.5 pro. Controls whether the generated video contains sound synchronized with the picture.

• true: The video output by the model contains synchronized audio. Seedance 1.5 pro can automatically generate matching human voices, sound effects and background music based on text prompts and visual content. It is recommended to enclose dialogue parts in double quotes to optimize audio generation effects. For example: The man stopped the woman and said: “Remember, you must not point at the moon with your finger in the future.”
• false: The video output by the model is silent.

Random seed integer, used to control the randomness of generated content.
Value range: Integer between [-1, 2^32-1].

Not supported for reference image scenarios. Whether to fix the camera. Enum values:

• true: Fix the camera. The platform will append fixed camera instructions to the user’s prompt, and the actual effect is not guaranteed.
• false: Do not fix the camera.

Whether the generated video contains a watermark. Enum values:

• false: Without watermark.
• true: With watermark.

Task timeout threshold. Specify the expiration time of the task after submission (unit: seconds), calculated from the created at timestamp. The default value is 172800 seconds, which is 48 hours. Value range: [3600, 259200].
Regardless of the service_tier used, it is recommended to set an appropriate timeout period according to the business scenario. After this time, the task will be automatically terminated and marked as expired status.