---
title: "Kandinsky 6.0 lite"
description: "Kandinsky 6.0 lite from Kandinsky6: text-to-video and image-to-video; Planned."
modelId: "kandinsky6-lite"
pageSource: generated
---

Kandinsky 6.0 lite is a video generation model from Kandinsky6. The catalog records it for text-to-video, image-to-video, and audio-video-generation.

<ModelPaperFigures modelId="kandinsky6-lite" locale="en" />

Code: [kandinskylab/kandinsky-6](https://github.com/kandinskylab/kandinsky-6).

<ModelCommandBuilder modelId="kandinsky6-lite" locale="en" />

## What it is for

`kandinsky6-lite` is the recorded text/image-to-video line. Use it when you want both prompt and still conditioning on the same catalog card.

Catalog tasks include text-to-video, image-to-video, and audio-video-generation. Documented modalities: text and image in, video out.

## Runtime contract

Optional `prompt`, `image`, `seed`, `frames`, and `fps`; artifacts `generated_video` and `kandinsky6-lite.mp4`.

CLI task profiles: `text-to-video`, `image-to-video`, `audio-video-generation`, and `video_generation`. WorldFoundry binds `Kandinsky6Pipeline`.

Family status: **Planned**.

Native audio-video inference; checkpoint-backed CUDA parity is pending.

A pipeline binding is recorded, but a successful run has not been established for this entry.

## Running in WorldFoundry

The catalog launch is `worldfoundry-eval run kandinsky6-lite --pipeline.task-profile text-to-video`. The command builder above switches `--pipeline.task-profile` among recorded tasks and still emits `worldfoundry-eval run`.

It runs in the unified environment `worldfoundry-unified-cu128` (Python 3.11, CUDA 12.8).

Recorded weight repositories include `kandinskylab/Kandinsky-6.0-Lite-5s-Diffusers`. Prepare the environment and check local assets with `bash scripts/inference/prepare_model_infer.sh kandinsky6-lite`. Add `--download` to fetch missing public checkpoints.

Status: **Planned**.

<ModelRelatedRecipes modelId="kandinsky6-lite" locale="en" />