AI Paper Atlas

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

VSF: Simple, Efficient, and Effective Negative Guidance in Few-Step Image Generation Models By Value Sign Flip

Wenqi Marshall Guo, Shan Du

ICLR 2026 · Image generation › Text-to-image diffusion · approach: Compositional text-to-image guidance · 4 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 VSF negative guidance (Strong)SD-3.5-Large-Turbo · NegGenBenchnegative score: 0.195 -> 0.545Improved
add VSF negative guidance (Quality)SD-3.5-Large-Turbo · NegGenBenchnegative score: 0.195 -> 0.420; quality 0.968 -> 0.986Improved
add VSF to Flux SchnellFlux Schnell · NegGenBenchnegative score: 0.22 -> 0.41Improved
use VSF instead of NASASD-3.5-Large-Turbo · NegGenBenchquality score: 0.867 -> 0.952 (VSF Strong)Improved
flip whole text embedding (WEF) instead of attention values (ablation)VSF · NegGenBench trade-offnegative scoreHurt
add attention masking (ablation)VSF · NegGenBench trade-offpositive scoreImproved
add attention bias -beta (ablation)VSF · NegGenBench trade-offquality scoreNo clear effect
use VSF instead of CFG (28 steps)SD-3.5-Large-Turbo · NegGenBenchnegative score: 0.300 -> 0.420Improved
VSF vs NAG compute costSD-3.5-Large-Turbo · runtimetime (s): 2.98s (NAG) vs 3.00s (VSF)No clear effect

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