kandinskylab/Kandinsky-5.0-I2V-Lite-LoRa-Dolly-out
Image-to-Video • Updated
• 1
Vladimir Korviakov
korviakov
AI & ML interests
Computer Vision, Image & Video synthesis
Recent Activity
upvoted a paper 11 days ago
Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines? upvoted a paper 19 days ago
Rethinking Global Text Conditioning in Diffusion Transformers upvoted a paper 27 days ago
Green-VLA: Staged Vision-Language-Action Model for Generalist Robots Organizations