# Correction Training for Diffusion Models

Diffusion sampling accumulates the model's own prediction errors, and a corrector trained on the base model's predictions against the same clean target lowers DiT-XL/2 FID on ImageNet class-conditional generation from 9.58 to 2.07, approaching CFG without guidance.

Diffusion sampling accumulates the model's own prediction errors, and a corrector trained on the base model's predictions against the same clean target lowers DiT-XL/2 FID on ImageNet class-conditional generation from 9.58 to 2.07, approaching CFG without guidance.