Dreamina Video Generation API
POSThttps://api.acedata.cloud/dreamina/videos
Audio-driven talking-photo digital human video generation (OmniHuman 1.5)
Request Headers
authorizationstring
Bearer token
Request Body
asyncboolean
If set to true, the request will immediately return task_id without the need to provide callback_url; results can be obtained by polling the corresponding tasks interface.
Please select
modelstring
The model being used is OmniHuman 1.5.
Please select
promptstring
Optional text prompts for guiding expressions, emotions, stability, and style.
mask_urlarray
Optional subject mask URL (from object detection) to specify and drive a particular person in a multi-person image.
audio_urlstringRequired parameter
Public URL for audio (mp3/wav). The character will lip-sync to it, and it is recommended that the duration be controlled within 60 seconds.
image_urlstringRequired parameter
Public URL of portrait images. Clear frontal face effects are best.
callback_urlstring
If provided, the request will immediately return task_id, and the result will be pushed to that URL once ready.
Response
Dreamina
Allow Use General Balance
When 'Allow General Balance' is enabled, the general balance is used automatically if an app's balance is insufficient.
Kind reminder: For streaming requests, the above code may not be fully applicable. Please refer to the integration documentation for changes.
