Vikhr: The Family of Open-Source Instruction-Tuned Large Language Models for Russian Paper β’ 2405.13929 β’ Published May 22, 2024 β’ 54
FusionFrames: Efficient Architectural Aspects for Text-to-Video Generation Pipeline Paper β’ 2311.13073 β’ Published Nov 22, 2023 β’ 56
Kandinsky: an Improved Text-to-Image Synthesis with Image Prior and Latent Diffusion Paper β’ 2310.03502 β’ Published Oct 5, 2023 β’ 78
Kandinsky: an Improved Text-to-Image Synthesis with Image Prior and Latent Diffusion Paper β’ 2310.03502 β’ Published Oct 5, 2023 β’ 78