Kandinsky LabKandinsky 5.0 Video
Kandinsky 5.0 T2V Lite Distilled 10s
Generate ten-second video from text with this 2B Lite checkpoint. Its weights were distilled to reduce sampling work.
Use the released distilled checkpoint
This checkpoint is distilled to sixteen function evaluations. It belongs to the ten-second line, which uses NABLA attention.kandinskylab/Kandinsky-5.0-T2V-Lite-distilled16steps-10s — 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-Lite-distilled16steps-10s — model card and files
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | Downloadable |
| Model identifiers | kandinskylab/Kandinsky-5.0-T2V-Lite-distilled16steps-10skandinskylab/Kandinsky-5.0-T2V-Lite-distilled16steps-10s-Diffusers |
| Generator size | 2B parameterskandinskylab/Kandinsky-5.0-T2V-Lite-distilled16steps-10s — model card and files |
| Weight license | MITkandinskylab/Kandinsky-5.0-T2V-Lite-distilled16steps-10s — model card and files |
| Clip duration | Up to 10 secondskandinskylab/Kandinsky-5.0-T2V-Lite-distilled16steps-10s — model card and files |