Vikhr: The Family of Open-Source Instruction-Tuned Large Language Models for Russian Paper • 2405.13929 • Published May 22 • 52
FusionFrames: Efficient Architectural Aspects for Text-to-Video Generation Pipeline Paper • 2311.13073 • Published Nov 22, 2023 • 56
Kandinsky: an Improved Text-to-Image Synthesis with Image Prior and Latent Diffusion Paper • 2310.03502 • Published Oct 5, 2023 • 77
