Tuning-Free Multi-Event Long Video Generation via Synchronized Coupled Sampling Paper β’ 2503.08605 β’ Published 1 day ago β’ 19
Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think Paper β’ 2410.06940 β’ Published Oct 9, 2024 β’ 8
Controllable Human Image Generation with Personalized Multi-Garments Paper β’ 2411.16801 β’ Published Nov 25, 2024 β’ 4
Controllable Human Image Generation with Personalized Multi-Garments Paper β’ 2411.16801 β’ Published Nov 25, 2024 β’ 4 β’ 2