---
title: "Kandinsky 6.0 pro-pretrain"
description: "Kandinsky 6.0 pro-pretrain from Kandinsky6: text-to-video and image-to-video; Planned."
modelId: "kandinsky6-pro-pretrain"
pageSource: generated
---
Kandinsky 6.0 pro-pretrain is a video generation model from Kandinsky6. The catalog records it for text-to-video, image-to-video, and audio-video-generation.
Code: [kandinskylab/kandinsky-6](https://github.com/kandinskylab/kandinsky-6).
## What it is for
Pick `kandinsky6-pro-pretrain` when one recipe covers text-to-video and image-to-video: a prompt in, an optional still, a clip out. Start here instead of wiring two upstream demos.
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-pro-pretrain.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
Launch `worldfoundry-eval run kandinsky6-pro-pretrain --pipeline.task-profile text-to-video` to sample the clip. 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-Pro-pretrain-5s-Diffusers`. Prepare the environment and check local assets with `bash scripts/inference/prepare_model_infer.sh kandinsky6-pro-pretrain`. Add `--download` to fetch missing public checkpoints.
Status: **Planned**.