SSA: Sparse Sparse Attention by Aligning Full and Sparse Attention Outputs in Feature Space Paper • 2511.20102 • Published Nov 25, 2025 • 27
SD-1.5 LCM-Lora Distillation Collection Distilling SD-1.5 into LCMs for very fast inference. We can get a viable image in 2-5 steps compared to 50-60 steps required from the orginal model. • 4 items • Updated Nov 20, 2025 • 2
SD-1.5 LCM-Lora Distillation Collection Distilling SD-1.5 into LCMs for very fast inference. We can get a viable image in 2-5 steps compared to 50-60 steps required from the orginal model. • 4 items • Updated Nov 20, 2025 • 2