← Wednesday, October 21, 2026Models & trainingPaper

SWIFT uses a frozen weak denoiser to improve diffusion training without inference overhead

huggingface.co by Yanjin He et al. Editor score 8/10

SWIFT extrapolates training targets away from a frozen weak denoiser’s predictions, then discards the guide; experiments report improvements across model scales and resolutions. The method targets training quality without adding inference cost or changing the sampler.

What

Swift trains a stronger diffusion model using a frozen weak denoiser, improving clean-target regression without inference-time guidance.

Method

For each noisy input, Swift extrapolates the clean target away from the weak denoiser’s prediction; the guide needs no backpropagation and is discarded afterward.

Why it matters

The method retains the original sampler without inference overhead, improving training without adding generation-time sampling cost.

Read on huggingface.co →

Headline, summary, brief and diagram are written by a model from the source's own text; the link, byline and numbers come from the source. Read the original before relying on a claim.