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

Researchers introduced Swift, a self-guided training method that uses a frozen weak denoiser to improve a stronger diffusion model without adding inference-time sampling cost. Swift targets the high computational expense of training high-quality diffusion models and the extra sampling cost that inference-time guidance typically adds. The method is described as simple yet effective, though the source excerpt provides no benchmark figures or quantitative results.

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