Hugging Face Trending Papers

Analytic Distribution of Classifier-Free Guidance for Schedule Design

Read the original on Hugging Face Trending Papers →

Classifier-free guidance (CFG) is the default mechanism for conditional generation in diffusion models, but the distribution sampled by its deterministic guided dynamics is not captured by the usual product-distribution heuristic $p_0^ωq_0^{1-ω}$. We analyze CFG through the probability flow ODE and derive exact analytic path-integral representations of the induced distributions for both constant and time-dependent guidance.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.