REVIEW 3 cited by
Classifier-free Guidance with Adaptive Scaling
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
Classifier-free Guidance with Adaptive Scaling
read the original abstract
Classifier-free guidance (CFG) is an essential mechanism in contemporary text-driven diffusion models. In practice, in controlling the impact of guidance we can see the trade-off between the quality of the generated images and correspondence to the prompt. When we use strong guidance, generated images fit the conditioned text perfectly but at the cost of their quality. Dually, we can use small guidance to generate high-quality results, but the generated images do not suit our prompt. In this paper, we present $\beta$-CFG ($\beta$-adaptive scaling in Classifier-Free Guidance), which controls the impact of guidance during generation to solve the above trade-off. First, $\beta$-CFG stabilizes the effects of guiding by gradient-based adaptive normalization. Second, $\beta$-CFG uses the family of single-modal ($\beta$-distribution), time-dependent curves to dynamically adapt the trade-off between prompt matching and the quality of samples during the diffusion denoising process. Our model obtained better FID scores, maintaining the text-to-image CLIP similarity scores at a level similar to that of the reference CFG.
Forward citations
Cited by 3 Pith papers
-
C$^2$FG: Control Classifier-Free Guidance via Score Discrepancy Analysis
C²FG provides a time-dependent exponential decay control for classifier-free guidance based on theoretical upper bounds on conditional-unconditional score discrepancies in diffusion processes.
-
C$^2$FG: Control Classifier-Free Guidance via Score Discrepancy Analysis
C²FG provides a time-dependent guidance controller for diffusion models derived from score discrepancy upper bounds, implemented as an exponential decay function without retraining.
-
MMD Guidance: Training-Free Distribution Adaptation for Diffusion Models via Maximum Mean Discrepancy Guidance
MMD Guidance adapts pretrained diffusion models at inference time by adding gradients of Maximum Mean Discrepancy between generated and reference latents, aligning samples with a target distribution without retraining.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.