Hailuo 02’s FL2V function provides unprecedented creative control by generating dynamic videos between a user-defined start and end frame. This feature not only masters extreme physics and complex transitions but also enables the novel capability to deduce a story leading up to a specified final image.
API Key authentication. Format: Bearer YOUR_API_KEY.
Last frame image (required). URL or Base64 Data URL. Image format: JPG/JPEG/PNG/WebP, <20MB, short side >300px, aspect ratio between 2:5 and 5:2. Video resolution is determined by the first frame; if dimensions differ, the last frame will be auto-cropped.
1"https://example.com/last-frame.jpg"
First frame image (optional). URL or Base64 Data URL. If not provided, the model will auto-generate a first frame. Image format: JPG/JPEG/PNG/WebP, <20MB, short side >300px, aspect ratio between 2:5 and 5:2.
1"https://example.com/first-frame.jpg"
Video content description (optional). Supports 15 camera control instructions. Format: Use [command] syntax for camera movements. Example: '[Pan left] Scene description' or '[Pan left,Pedestal up] for combined movements'. Max 2000 characters.
1 - 2000"[Pan left] A beautiful sunset transition"
Whether to automatically optimize the prompt. Default is true. Set to false for more precise control.
true
Video duration in seconds. Options: 6 or 10. Note: 10 seconds only supports 768P resolution. Default is 6.
6, 10 6
Video resolution. Options: 768P or 1080P. Note: FL2V does not support 512P. 10 seconds only supports 768P, 1080P only supports 6 seconds. Default is 768P.
768P, 1080P "1080P"