view article Article Training Design for Text-to-Image Models: Lessons from Ablations 10 days ago β’ 57
view article Article Weβre open-sourcing our text-to-image model and the process behind it Nov 12, 2025 β’ 85
FasterViT: Fast Vision Transformers with Hierarchical Attention Paper β’ 2306.06189 β’ Published Jun 9, 2023 β’ 31