AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

PC-Flow: Preference Alignment in Flow Matching via Classifier

Shaomeng Wang, He Wang, Longquan Dai, Jinhui Tang

AAAI 2026 · Image generation › Text-to-image diffusion · approach: Preference optimization for diffusion · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add PC-Flow preference classifier guidance to the base flow modelSD-3.5-M · PartiPromptsLAION Aesthetics: 5.57 -> 5.94Improved
add PC-Flow guidanceSD-3.5-M · HPS benchmarkHPS: 27.93 -> 28.95Improved
add PC-Flow guidanceSD-3.5-M · PartiPromptsPickScore: 22.53 -> 22.63Improved
add PC-Flow guidanceSD-3.5-M · HPS benchmarkCLIP score: 33.99 -> 34.45Improved
compare PC-Flow with Flux1.dev on PickScorePC-Flow · PartiPromptsPickScore: 22.80 (Flux1.dev) vs 22.63 (PC-Flow)Hurt
compare PC-Flow with SANA-1.5 on LAION AestheticsPC-Flow · PartiPromptsLAION Aesthetics: 5.96 (SANA-1.5) vs 5.94 (PC-Flow)No clear effect
raise temperature beta from 20 to 200 (ablation)PC-Flow loss · HPS benchmarkLAION Aesthetics: 5.81 -> 6.14Improved
use a very small temperature beta of 5 instead of 200 (ablation)PC-Flow loss · HPS benchmarkPickScore: 22.27 -> 20.34Hurt
raise temperature beta from 200 to 2000 (ablation)PC-Flow loss · HPS benchmarkLAION Aesthetics: 6.14 -> 5.87Hurt
raise guidance weight gamma from 0.05 to 0.10 (ablation)PC-Flow sampling · HPS benchmarkLAION Aesthetics: 5.84 -> 6.14Improved
raise guidance weight gamma above 0.10 (to 0.15 and 0.20) (ablation)PC-Flow sampling · HPS benchmarkLAION Aesthetics: 6.14 -> 5.87 (0.15), 5.85 (0.20)Hurt
use PC-Flow instead of AuraFlowPC-Flow · HPS benchmarkPickScore win rate (%): 87.08Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy