Diffusion-Sharpening: Fine-tuning Diffusion Models with Denoising Trajectory Sharpening

tyfeld, Ling Yang, Xinchen Zhang, Yunhai Tong, Mengdi Wang, Bin Cui

Diffusion-Sharpening: Fine-tuning Diffusion Models with Denoising Trajectory Sharpening: 16 upvotes on Hugging Face Daily Papers, #11 of 38 papers on 2025-02-18. Day-by-day upvote history.

We propose Diffusion-Sharpening, a fine-tuning approach that enhances downstream alignment by optimizing sampling trajectories. Existing RL-based fine-tuning methods focus on single training timesteps and neglect trajectory-level alignment, while recent sampling trajectory optimization methods incur significant inference NFE costs. Diffusion-Sharpening overcomes this by using a path integral framework to select optimal trajectories during training, leveraging reward feedback, and amortizing inference costs. Our method demonstrates superior training efficiency with faster convergence, and best inference efficiency without requiring additional NFEs. Extensive experiments show that Diffusion-Sharpening outperforms RL-based fine-tuning methods (e.g., Diffusion-DPO) and sampling trajectory optimization methods (e.g., Inference Scaling) across diverse metrics including text alignment, compositional capabilities, and human preferences, offering a scalable and efficient solution for future diffusion model fine-tuning. Code: https://github.com/Gen-Verse/Diffusion-Sharpening

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.