Characteristic Guidance: Non-linear Correction for Diffusion Model at Large Guidance Scale
This work addresses a specific issue in diffusion model guidance for researchers and practitioners, offering an incremental improvement to existing methods.
The authors tackled the problem of linear guidance in diffusion models overlooking nonlinear effects at large guidance scales by proposing characteristic guidance, a training-free method that enforces the Fokker-Planck equation, resulting in enhanced semantic characteristics and reduced irregularities in image generation across diverse applications.
Popular guidance for denoising diffusion probabilistic model (DDPM) linearly combines distinct conditional models together to provide enhanced control over samples. However, this approach overlooks nonlinear effects that become significant when guidance scale is large. To address this issue, we propose characteristic guidance, a guidance method that provides first-principle non-linear correction for classifier-free guidance. Such correction forces the guided DDPMs to respect the Fokker-Planck (FP) equation of diffusion process, in a way that is training-free and compatible with existing sampling methods. Experiments show that characteristic guidance enhances semantic characteristics of prompts and mitigate irregularities in image generation, proving effective in diverse applications ranging from simulating magnet phase transitions to latent space sampling.