Media Generation API

Generate SVD

POST
Generate videos in response to the given request.

Request

This endpoint expects an object.
image
stringRequired
Starting point image encoded in base64 string.
cfg_scale
doubleOptionalDefaults to 3
Floating-point number represeting how closely to adhere to 'image'. Must be a positive number no greater than 10.0.
constant_rate_factor
integerOptionalDefaults to 23
Integer representing the quality of the video encoding. Higher quality means the file will be larger.The range of the CRF scale is [0,51], where 0 is lossless, 23 is the default, and 51 is worst quality possible.
fps
integerOptionalDefaults to 7
Integer representing how fast the generated frames should play back.
height
integerOptional
Integer representing the height of video/animation to generate.If not provided, the output height will be inferred from the input 'image', and the closest resolution supported will be chosen. Supported resolutions (w,h): {(576, 1024), (1024, 576), (768, 768)}.
motion_scale
doubleOptionalDefaults to 0.5
A floating point number between 0.0 and 1.0 indicating how much motion should be in the generated video/animation.
noise_aug_strength
doubleOptionalDefaults to 0.02
A floating point number between 0.0 and 1.0 indicatiing how much noise to add to the initial image. Higher values encourage creativity.
num_videos
integerOptionalDefaults to 1
Integer representing how many output videos/animations to generate with a single 'image' and configuration.
seed
unionOptional
Integer number or list of integers representing the seeds of random generators.Fixing random seed is useful when attempting to generate a specific video/animation (or set of videos/animations). Must be greater than 0 and less than 2^32.
steps
integerOptionalDefaults to 25
Integer repreenting how many steps of diffusion to run. Must be greater than 0 and less than or equal to 50.
width
integerOptional
Integer representing the width of video/animation to generate.If not provided, the output width will be inferred from the input 'image', and the closest resolution supported will be chosen. Supported resolutions (w,h): {(576, 1024), (1024, 576), (768, 768)}.

Response

This endpoint returns an object
prediction_time_ms
double
Total runtime of the video(s) generation(s).
videos
list of objects
List of VideoGeneration(s) generated by the request.