Kandinsky LabKandinsky Video
Kandinsky Video 1.1
Video 1.1 first generates an image with Kandinsky 3.0, then conditions later keyframes on that first image and the text. It also accepts an input image for animation.
The release includes trained temporal components
The package includes a 4.0B interpolation model and separate image and temporal MoVQ components. These sizes are components, not the total size of the system.ai-forever/KandinskyVideo_1_1 — model card and files
Keep the original pipeline components together
Practical guidance. Changing the keyframe model or interpolator changes the generated sequence. Compare the complete pipeline when reproducing an older result.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | Downloadable |
| Model identifiers | ai-forever/KandinskyVideo_1_1 |
| Weight license | Apache 2.0ai-forever/KandinskyVideo_1_1 — model card and files |
| Keyframe U-Net | 4.15B parametersai-forever/KandinskyVideo_1_1 — model card and files |
Related models
- Kandinsky 3.0
Kandinsky Lab · Kandinsky 3
An image diffusion model with a larger text encoder and U-Net, trained with attention to Russian cultural subjects.
Launch date not confirmedDownloadable