Inference-Time Scaling of Diffusion Models via Progressive Seed Pruning

TL;DR - Progressive Seed Pruning improves diffusion-model inference by evaluating many noise seeds early and progressively eliminating weak trajectories. It delivers better image-generation quality than competing selection methods at matched compute.

• Scores intermediate denoised estimates to identify promising seeds before full generation.
• Front-loads exploration while keeping total model evaluations fixed, trading additional memory for more effective compute use.
• Outperforms best-of-N, importance-sampling, and tree-search baselines across diffusion and flow-matching backbones.
• Improves automated GenEval scores and human-rated prompt alignment.