MearcAll papers

arXiv 2207.12598 · cs.LG cs.AI

Classifier-Free Diffusion Guidance

Jonathan Ho, Tim Salimans

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.

No reproduction recordedclm_b3a8e02e
We 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)

ABSTRACT · page 1 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedres_d9013c4f
Dhariwal & 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.

C LASSIFIER GUIDANCE · page 4 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedres_541935ee
At 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)

V ARYING THE CLASSIFIER -FREE GUIDANCE STRENGTH · page 7 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedres_000f58b0
As expected, sample quality improves whenT is increased, and for this modelT = 256 attains a good balance between sample quality and sampling speed.

V ARYING THE NUMBER OF SAMPLING STEPS · page 8 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedres_4bb9b60a
Note thatT = 256 is approximately the same number of sampling steps used by ADM-G (Dhariwal & Nichol, 2021), which is outperformed by our model.

V ARYING THE NUMBER OF SAMPLING STEPS · page 8 · Automated extraction, not reviewed · 0 reviewed reproductions

Reproduced one of these claims?

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.