# SWIFT: Self-guided Weak-to-strong dIFfusion models via Target extrapolation

> Source: <https://aiflash.com/news/136478/>
> Published: 2026-10-21 03:00:39+00:00

Training high-quality diffusion models is computationally expensive, and inference-time guidance often adds further sampling cost. In this work, we introduce Swift, a simple yet effective self-guided training method that uses a frozen weak denoiser to improve a stronger model without adding inferenc