AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

SAFETY-GUIDED FLOW (SGF): A UNIFIED FRAMEWORK FOR NEGATIVE GUIDANCE IN SAFE GENERATION

Mingyu Kim, Young-Heon Kim, Mijung Park

ICLR 2026 · Image generation › Fast diffusion sampling · approach: Guidance for conditional diffusion · 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
replace Safe Denoiser guidance with SGF MMD guidance on SAFREESAFREE · Ring-A-Bell (nudity)ASR: 0.127 -> 0.051Improved
replace Safe Denoiser guidance with SGF MMD guidance on SLDSLD · MMA-Diffusion (nudity)ASR: 0.481 -> 0.297Improved
replace Safe Denoiser with SGF on SAFREESAFREE · COCO (benign prompts)FID: 22.55 -> 23.73Hurt
add early stop of negative guidance to SGF (ablation)SGF on SDv3 · ImageNet class-to-image (lambda=1.0)FID: 36.81 -> 31.81Improved
add early stop of negative guidance to SPELL (ablation)SPELL on SDv3 · ImageNet class-to-image (lambda=1.0)FID: 51.76 -> 48.50Improved
add early stop to SGF (ablation)SGF on SDv3 · ImageNet class-to-image (lambda=1.0)Vendi: 3.126 -> 3.076Hurt
add early stop to SGF (ablation)SGF on SDv3 · ImageNet class-to-image (lambda=1.0)CLIP: 30.47 -> 30.78Improved
apply SGF negative guidance with training images as negative setmemorized SD-v2.1 · Memorized SDv2.1 (ImageNette)Sim@95%: 0.437 -> 0.328Improved
apply SGF negative guidance to memorized SD-v2.1memorized SD-v2.1 · Memorized SDv2.1 (ImageNette)FID: 41.19 -> 32.44Improved
apply SGF negative guidance to memorized SD-v2.1memorized SD-v2.1 · Memorized SDv2.1 (ImageNette)CLIP: 31.78 -> 30.93No clear effect
restrict negative guidance to earliest denoising window instead of extending or shifting it later (ablation)SAFREE + SGF · Ring-A-Bell, UnlearnDiff, MMA-Diffusion (nudity)ASRImproved
increase negative pool from N=515 to N=3,200 (ablation)SAFREE + SGF · Wall-clocktime per image (s): 4.32 -> 4.70Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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