SDXL

The 'SDXL' dataset/benchmark is used to evaluate the performance of diffusion models in terms of their generative capabilities and the effectiveness of post-training acceleration methods.

Papers using SDXL (3)

MosaicDiff: Training-free Structural Pruning for Diffusion Model Acceleration Reflecting Pretraining Dynamics2025ProReflow: Progressive Reflow with Decomposed Velocity2025Learnable Sparsity for Vision Generative Models2024