Skip to content

Latest commit

 

History

History
17 lines (14 loc) · 6.2 KB

File metadata and controls

17 lines (14 loc) · 6.2 KB

BodyGenImageToVideo

Fields

Field Type Required Description
image components.BodyGenImageToVideoImage ✔️ Uploaded image to generate a video from.
model_id Optional[str] Hugging Face model ID used for video generation.
height Optional[int] The height in pixels of the generated video.
width Optional[int] The width in pixels of the generated video.
fps Optional[int] The frames per second of the generated video.
motion_bucket_id Optional[int] Used for conditioning the amount of motion for the generation. The higher the number the more motion will be in the video.
noise_aug_strength Optional[float] Amount of noise added to the conditioning image. Higher values reduce resemblance to the conditioning image and increase motion.
safety_check Optional[bool] Perform a safety check to estimate if generated images could be offensive or harmful.
seed Optional[int] Seed for random number generation.
num_inference_steps Optional[int] Number of denoising steps. More steps usually lead to higher quality images but slower inference. Modulated by strength.