Differential Diffusion

2000년 도입 · 논문 3편에서 사용

Differential Diffusion is an enhancement of image-to-image diffusion models that adds the ability to control the amount of change applied to each image fragment via a change map.

출처: Differential Diffusion: Giving Each Pixel Its Strength

소개 논문: Differential Diffusion: Giving Each Pixel Its Strength