infery
← All models

Kandinsky5 Pro

kandinsky5-pro-text-to-video

Video generationby Sber

Kandinsky 5.0 Pro is a diffusion model for fast, high-quality text-to-video generation.

Example

Details

Accepts
text + image

Pricing

Price
25 cr / video

Prices in credits (1 credit = $0.01).

Data schema

Input

FieldTypeDescription
seedThe seed to use for generation. If not provided, a random seed will be used.
promptrequiredstringThe prompt to generate the video from.
durationstringVideo duration.
image_urlstringThe URL of the image to use as a reference for the video generation.
resolutionstringenum: 512P, 1024PVideo resolution: 512p or 1024p.
accelerationAcceleration level for faster generation.
num_inference_stepsinteger
aspect_ratiostringenum: 3:2, 1:1, 2:3Aspect ratio of the generated video. One of (3:2, 1:1, 2:3).

Output

FieldTypeDescription
seedintegerThe seed used for generation.
videoThe generated video file.