Alexey Letunovskiy

AlexeyLetunovskiy's activity

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

upvoted a paper 5 days ago

GreenWAM: A World Foundation Model for Robotics

Paper • 2610.18774 • Published 6 days ago • 107

liked a Space 13 days ago

Running on Zero

MCP

5

Kandinsky 6.0 Lite (distill 5s)

🎬

5

Text/image-to-video with synchronized audio (10 steps)

authored a paper 13 days ago

Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation

Paper • 2610.05608 • Published 15 days ago • 174

liked 4 models 13 days ago

kandinskylab/Kandinsky-6.0-Lite-distill-5s-Diffusers

Image-to-Video • 3B • Updated 7 days ago • 755 • 22

kandinskylab/Kandinsky-6.0-Lite-5s-Diffusers

Image-to-Video • 3B • Updated 7 days ago • 444 • 34

kandinskylab/Kandinsky-6.0-Pro-distill-5s-Diffusers

Image-to-Video • 30B • Updated 7 days ago • 709 • 31

kandinskylab/Kandinsky-6.0-Pro-5s-Diffusers

Image-to-Video • 30B • Updated 7 days ago • 353 • 60

upvoted a paper 13 days ago

Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation

Paper • 2610.05608 • Published 15 days ago • 174

upvoted 2 papers 2 months ago

Ouroboros: A Self-Developing Frontier Coding Agent with Reviewed Core Evolution

Paper • 2608.08311 • Published Aug 8 • 95

KVAE: Family of Tokenizers for Multimodal Generative Models

Paper • 2608.05798 • Published Aug 6 • 32

upvoted a paper 9 months ago

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

Paper • 2602.00919 • Published Jan 31 • 324

upvoted a paper 11 months ago

GigaEvo: An Open Source Optimization Framework Powered By LLMs And Evolution Algorithms

Paper • 2511.17592 • Published Nov 17, 2025 • 122

upvoted 8 collections 11 months ago

Kandinsky 5.0 Video Lite

Collection

Kandinsky 5.0 Video Lite is a lightweight 2B model that generates up to 10-second SD videos from English and Russian prompts with high visual quality. • 9 items • Updated 13 days ago • 18

Kandinsky 5.0 Video Pro

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. • 5 items • Updated 13 days ago • 20

Kandinsky 5.0 Image Lite

Collection

Kandinsky 5.0 Image Lite is a 6B DiT-based model that generates and edits HD images from English and Russian text prompts with high visual quality. • 4 items • Updated 13 days ago • 27

KVAE 1.0

Collection

KVAE 1.0 tokenizers are for images (KVAE-2D-1.0) and video (KVAE-3D-1.0) are distributed under MIT license (commercial use is possible). • 2 items • Updated 13 days ago • 8

Kandinsky 5.0 Video Pro LoRas

Collection

8 items • Updated 13 days ago • 3

Kandinsky 5.0 Video Lite Diffusers

Collection

Kandinsky 5.0 Video Lite is a lightweight 2B model that generates up to 10-second SD videos from English and Russian prompts with high visual quality. • 8 items • Updated 13 days ago • 6

Kandinsky 5.0 Video Lite LoRas

Collection

16 items • Updated 13 days ago • 6

Kandinsky 5.0 Image Lite Diffusers

Collection

4 items • Updated 13 days ago • 11