view article Article Training Design for Text-to-Image Models: Lessons from Ablations 12 days ago • 57
Fast Autoregressive Video Diffusion and World Models with Temporal Cache Compression and Sparse Attention Paper • 2602.01801 • Published 13 days ago • 28
Add-it: Training-Free Object Insertion in Images With Pretrained Diffusion Models Paper • 2411.07232 • Published Nov 11, 2024 • 68