Diffusion Models without Classifier-free Guidance

Model-guidance replaces classifier-free guidance by training on condition posterior probabilities, doubling inference speed and achieving 1.34 FID on ImageNet 256.

Zhicong Tang, Dong Chen, Jianmin Bao, Baining Guo

Published 2026Sydney Poster Session 5 · Thu, Dec 10, 10:00 AM–1:00 PM local time · Hall 1-4▲ 8 on Hugging Face Code ★ 175 arXiv ↗OpenReview ↗

72%

OverallHighly rated

OverallHighly ratedVote to see the scoreThe exact score shows once you've voted, so every vote is your own call. The first half of each home page shelf shows its scores.

Readers

–

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel8/20reviewers recommend it

lenient 2/5

medium 5/10

strict 1/5

AI panel?Vote to see what the 20 AI reviewers said

Abstract

This paper presents Model-guidance (MG), a novel objective for training diffusion model that addresses and removes of the commonly used Classifier-free guidance (CFG). Our innovative approach transcends the standard modeling of solely data distribution to incorporating the posterior probability of conditions. The proposed technique originates from the idea of CFG and is easy yet effective, making it a plug-and-play module for existing models. Our method significantly accelerates the training process, doubles the inference speed, and achieve exceptional quality that parallel and even surpass concurrent diffusion models with CFG. Extensive experiments demonstrate the effectiveness, efficiency, scalability on different models and datasets. Finally, we establish state-of-the-art performance on ImageNet 256 benchmarks with an FID of 1.34. Our code is available at https://github.com/tzco/Diffusion-wo-CFG.