clm_b3a8e02eWe show that guidance can be indeed performed by a pure generative model without such a classifier: in what we call classifier-free guidance, we jointly train a conditional and an … (excerpt)
arXiv 2207.12598 · cs.LG cs.AI
Read on arXiv · arXiv non-exclusive license
Claims were extracted automatically by reducer-1 on 2026-11-12. The paper's license does not allow republishing it, so long claims are shortened to a quotation. Read the full text on arXiv.
clm_b3a8e02eWe show that guidance can be indeed performed by a pure generative model without such a classifier: in what we call classifier-free guidance, we jointly train a conditional and an … (excerpt)
res_d9013c4fDhariwal & Nichol therefore find that by settingw> 0 they can improve the Inception score of their diffusion model, at the expense of decreased diversity in their samples.
res_541935eeAt w = 0.3, our model’s FID score on 128× 128 ImageNet outperforms the classifier-guided ADM-G, and atw = 4.0, our model outperforms BigGAN-deep at both FID and IS when … (excerpt)
res_000f58b0As expected, sample quality improves whenT is increased, and for this modelT = 256 attains a good balance between sample quality and sampling speed.
res_4bb9b60aNote thatT = 256 is approximately the same number of sampling steps used by ADM-G (Dhariwal & Nichol, 2021), which is outperformed by our model.
Record your result in the Mearc app on your own machine, then use Publish this result with this paper's id (2207.12598) and the claim id shown next to the claim. Mearc creates a file that holds only what you choose to publish. Add it to the public claim data by pull request; a maintainer other than you reviews it before it counts.