Mode isteğe bağlı
`animation` animates the reference character with the driving motion. `replacement` replaces the driving subject with the reference character while keeping the original scene.
Animation Replacement
Driving Type isteğe bağlı
Driving signal for animation mode. `end_to_end` (default) drives directly from the SAM3-masked driving video and is the recommended, most robust path. `pose` renders an explicit NLF/DWPose skeleton from the driving video (more control for challenging inputs).
End to end Pose
Subject Type isteğe bağlı
Type of subject in the driving video. `animal` switches the SAM3 detection prompt to non-human subjects.
Human Animal
Resolution isteğe bağlı
Output resolution. 512p outputs 896x512 (landscape) or 512x896 (portrait); 704p outputs 1280x704 or 704x1280. Orientation is chosen automatically from the reference image aspect ratio.
512p 704p
Num Inference Steps isteğe bağlı
Number of diffusion sampling steps. Higher improves quality but is slower.
Guidance Scale isteğe bağlı
Classifier-free guidance scale. Controls prompt adherence versus creativity.
1 2 3 4 5 6 7 8 9 10
Shift isteğe bağlı
Flow-matching noise schedule shift. 3.0 is recommended for the 512p tier.
1 2 3 4 5 6 7 8 9 10
Seed isteğe bağlı
Random seed. Leave empty for a random seed. The seed used is returned in the response.
Enable Safety Checker isteğe bağlı
Authorized callers may set false to request relaxed screening.
Açık Enable Safety Checker 