Kandinsky5 Distill

kandinsky5-distill-text-to-video

post

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

Header parameters
AuthorizationstringRequiredExample: sk-yOm1Vc3raDjQluBttyAwSdbVxtWFEAPCbtAZ2uF3yST1xNCY
Body
modelstringRequired

model is the model name

Example: kandinsky5-distill-text-to-video
promptstringRequired

prompt is the prompt.

Example: A cute baby sea otter.
resolutionstring · enumOptional

Resolution of the generated video in W:H format. One of (768x512, 512x768, 512x512). Default value: "768x512"

Possible enum values: 768x512, 512x768, 512x512

Default: 768x512Example: 768x512Possible values:
video_lengthstring · enumOptional

The length of the video to generate (5s or 10s) Default value: "5s"

Possible enum values: 5s, 10s

Default: 5sExample: 5sPossible values:
output_formatstring · enumOptional

output_format indicate the output format, default value is url.

Default: urlExample: urlPossible values:
Responses
200Success
application/json
post
/v1/videos/generations
200Success

Last updated