Kandinsky LabKandinsky 5.0 Video
Kandinsky 5.0 T2V Pro Distilled 5s
Generate five-second video from text with this 19B Pro checkpoint. Its weights were distilled to reduce sampling work.
Use the released distilled checkpoint
The official Diffusers bundle publishes a distilled Pro transformer. Its card requests CPU offloading. This guide does not infer a sampling-step count from the older Lite sixteen-step release.kandinskylab/Kandinsky-5.0-T2V-Pro-distilled-5s-Diffusers — model card and files
Account for the complete video pipeline
The generator is used with Qwen2.5-VL and CLIP text encoders and a HunyuanVideo VAE. Those upstream components are not new Kandinsky foundation models.kandinskylab/Kandinsky-5.0-T2V-Pro-distilled-5s-Diffusers — model card and files
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | Downloadable |
| Model identifiers | kandinskylab/Kandinsky-5.0-T2V-Pro-distilled-5s-Diffusers |
| Generator size | 19B parameterskandinskylab/Kandinsky-5.0-T2V-Pro-distilled-5s-Diffusers — model card and files |
| Weight license | MITkandinskylab/Kandinsky-5.0-T2V-Pro-distilled-5s-Diffusers — model card and files |
| Clip duration | Up to 5 secondskandinskylab/Kandinsky-5.0-T2V-Pro-distilled-5s-Diffusers — model card and files |