KVAE 2.0 is a family of video tokenizers with a time compression ratio of 4 and spacial compression ratio of 8 and 16
AI & ML interests
Gen AI, AIGC, Video Generation, Image Generation
Recent Activity
Organization Card
Edit this README.md markdown file to author your organization card.
models 63
kandinskylab/KVAE-3D-2.0-t4s16
Updated • 74 • 6
kandinskylab/KVAE-3D-2.0-t4s8
Updated • 57 • 5
kandinskylab/KVAE-2D-1.0
Updated • 2.06k • 7
kandinskylab/KVAE-3D-1.0
Updated • 415 • 8
kandinskylab/Kandinsky-5.0-I2V-Lite-5s-Diffusers
Updated • 8 • 4
kandinskylab/Kandinsky-5.0-I2V-Pro-distilled-5s-Diffusers
Updated • 31 • 6
kandinskylab/Kandinsky-5.0-T2V-Pro-distilled-5s-Diffusers
Updated • 10 • 3
kandinskylab/Kandinsky-5.0-T2V-Pro-pretrain-10s
Text-to-Video • Updated • 2
kandinskylab/Kandinsky-5.0-T2V-Pro-pretrain-5s
Text-to-Video • Updated
kandinskylab/Kandinsky-5.0-I2V-Pro-sft-5s
Text-to-Video • Updated • 11
datasets 0
None public yet