This paper was accepted at the Mathematics of Modern Machine Learning (M3L) Workshop at NeurIPS 2024.
We investigate the unreasonable effectiveness of classifier-free guidance (CFG).
CFG is the dominant method of conditional sampling for text-to-image diffusion models, yet
unlike other aspects of diffusion, it remains on shaky theoretical footing. In this paper, we disprove common misconceptions, by showing that CFG interacts differently with DDPM and DDIM, and neither sampler with CFG generates the gamma-powered distribution.
Then, we clarify the behavior of CFG by showing that it is a kind…
We investigate the unreasonable effectiveness of classifier-free guidance (CFG).
CFG is the dominant method of conditional sampling for text-to-image diffusion models, yet
unlike other aspects of diffusion, it remains on shaky theoretical footing. In this paper, we disprove common misconceptions, by showing that CFG interacts differently with DDPM and DDIM, and neither sampler with CFG generates the gamma-powered distribution.
Then, we clarify the behavior of CFG by showing that it is a kind…