Kandinsky LabKandinsky 5.0 Video
Kandinsky 5.0 T2V Lite No-CFG 5s
Generate five-second video from text with this 2B Lite checkpoint. Guidance was distilled into its weights.
Use guidance-distilled weights
The No-CFG variant removes the separate classifier-free guidance pass. The model table lists 50 function evaluations. It is distinct from the sixteen-step diffusion-distilled checkpoint.kandinskylab/Kandinsky-5.0-T2V-Lite-nocfg-5s — 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-nocfg-5s — model card and files
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | Downloadable |
| Model identifiers | kandinskylab/Kandinsky-5.0-T2V-Lite-nocfg-5skandinskylab/Kandinsky-5.0-T2V-Lite-nocfg-5s-Diffusers |
| Generator size | 2B parameterskandinskylab/Kandinsky-5.0-T2V-Lite-nocfg-5s — model card and files |
| Weight license | MITkandinskylab/Kandinsky-5.0-T2V-Lite-nocfg-5s — model card and files |
| Clip duration | Up to 5 secondskandinskylab/Kandinsky-5.0-T2V-Lite-nocfg-5s — model card and files |