REVIEW 3 cited by
Characteristic Guidance: Non-linear Correction for Diffusion Model at Large Guidance Scale
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
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.
Forward citations
Cited by 3 Pith papers
-
Classifier-Free Guidance: From High-Dimensional Analysis to Generalized Guidance Forms
CFG's distortion of the target distribution vanishes as data dimension grows, and a power-law generalization improves fidelity and diversity in high-dimensional generative models.
-
A Minimalist Method for Fine-tuning Text-to-Image Diffusion Models
A one-step RL method learns a prompt-conditioned initial noise distribution for a frozen diffusion model, improving scores on the training reward models, with the largest gains at low inference steps.
-
Normalized Attention Guidance: Universal Negative Guidance for Diffusion Models
Normalized Attention Guidance (NAG) stabilizes attention-space extrapolation with L1 normalization and refinement, restoring negative prompting in few-step diffusion models across architectures and modalities.
Discussion (0). Continue with ORCID to comment.