Classifier-Free Diffusion Guidance
Paper
•
2207.12598
•
Published
•
2
Guidance - "The intended effect is to decrease the diversity of the samples while increasing the quality of each individual sample."
Note Section 4.1 Here we experimentally verify the main claim of this paper: that classifier-free guidance is able to trade off IS and FID in a manner like classifier guidance or GAN truncation. We apply our proposed classifier-free guidance to 64 × 64 and 128 × 128 class-conditional ImageNet generation. In Table 1 and Fig. 4, we show sample quality effects of sweeping over the guidance strength w on our 64 × 64 ImageNet models