Lev Novitskiy

leffff's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 2 papers 2 days ago

SLIME: Stabilized Likelihood Implicit Margin Enforcement for Preference Optimization

Paper • 2602.02383 • Published 3 days ago • 27

Green-VLA: Staged Vision-Language-Action Model for Generalist Robots

Paper • 2602.00919 • Published 4 days ago • 199

liked a model 21 days ago

black-forest-labs/FLUX.2-dev

Image-to-Image • Updated Nov 27, 2025 • 147k • • 1.32k

liked a model about 1 month ago

meituan-longcat/LongCat-Video

Text-to-Video • Updated Oct 29, 2025 • 1.34k • • 425

liked a model about 2 months ago

leekwoon/maze2d-medium-v1-H256-T256

Updated Feb 2, 2023 • 1

updated 3 models about 2 months ago

kandinskylab/Kandinsky-5.0-I2V-Lite-5s-Diffusers

Updated Dec 14, 2025 • 88 • 4

kandinskylab/Kandinsky-5.0-I2V-Pro-distilled-5s-Diffusers

Updated Dec 12, 2025 • 58 • 6

kandinskylab/Kandinsky-5.0-T2V-Pro-distilled-5s-Diffusers

Updated Dec 12, 2025 • 20 • 3

updated a collection about 2 months ago

Kandinsky 5.0 Video Pro Diffusers

Collection

Kandinsky 5.0 Video Pro is a 19B model that generates high-quality HD videos from English and Russian prompts with controllable camera motion. • 4 items • Updated Dec 14, 2025 • 11

updated 2 models 2 months ago

kandinskylab/Kandinsky-5.0-I2V-Pro-sft-5s-Diffusers

Updated Dec 3, 2025 • 315 • 24

kandinskylab/Kandinsky-5.0-T2V-Pro-sft-5s-Diffusers

Updated Dec 3, 2025 • 436 • 7

published 2 models 2 months ago

kandinskylab/Kandinsky-5.0-T2V-Pro-distilled-5s-Diffusers

Updated Dec 12, 2025 • 20 • 3

kandinskylab/Kandinsky-5.0-I2V-Pro-distilled-5s-Diffusers

Updated Dec 12, 2025 • 58 • 6

upvoted 2 papers 2 months ago

Kandinsky 5.0: A Family of Foundation Models for Image and Video Generation

Paper • 2511.14993 • Published Nov 19, 2025 • 231

Time-Correlated Video Bridge Matching

Paper • 2510.12453 • Published Oct 14, 2025 • 2

upvoted a collection 2 months ago

Kandinsky 5.0 Video Pro Diffusers

Collection

Kandinsky 5.0 Video Pro is a 19B model that generates high-quality HD videos from English and Russian prompts with controllable camera motion. • 4 items • Updated Dec 14, 2025 • 11

New activity in kandinskylab/Kandinsky-5.0-I2V-Pro-sft-5s-Diffusers 2 months ago

Update README.md

#3 opened 2 months ago by

leffff

authored 2 papers 3 months ago

VIVAT: Virtuous Improving VAE Training through Artifact Mitigation

Paper • 2506.07863 • Published Jun 9, 2025 • 1

Kandinsky 5.0: A Family of Foundation Models for Image and Video Generation

Paper • 2511.14993 • Published Nov 19, 2025 • 231