Submit First-and-Last-Frame-to-Video Task
Generate videos with a start frame and an end frame. first_pic_url is required as the start frame image, and end_pic_url is required as the end frame image.
Authorizations
Authenticate using Bearer token. Get your API Key from the WeryAI Console.
Example: Authorization: Bearer sk-xxxxxxxxxxxxxxxx
Body
Model Key. Supported models for first-last-image-to-video:
"VEO_3_1"
Positive text prompt
1 - 2000"The camera slowly moves from the first frame to the last frame with smooth motion."
Start frame image URL (supports jpg, jpeg, png, webp)
"https://example.com/start.jpg"
End frame image URL (supports jpg, jpeg, png, webp)
"https://example.com/end.jpg"
Video aspect ratio. Refer to the model table above for supported values per model. Models marked with - do not support aspect ratio selection. For HAILUO_03, the output aspect ratio follows the input image and this parameter is ignored.
"16:9"
Video duration in seconds. Refer to the model table above for supported values per model.
5
Negative text prompt
1000Number of videos to generate (1~4).
1, 2, 3, 4 Video resolution. Supported values per model. For Werydance models, only Werydance 2.0 supports 1080p.
Whether to generate audio. Enter true or false manually. Only supported by the following models:
HAILUO_03 always generates synchronized audio natively; this parameter is ignored.
"false"
Callback URL
Caller ID
