AI Paper Atlas

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

AlignGuard: Scalable Safety Alignment for Text-to-Image Generation

Runtao Liu, I Chieh Chen, Jindong Gu, Jipeng Zhang, Renjie Pi, Qifeng Chen, Philip Torr, Ashkan Khakzar, Fabio Pizzati

ICCV 2025 · Image generation › Text-to-image diffusion · approach: T2I evaluation and controllable adapters · 30 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
use paired safe image as DPO positive instead of black image (ablation)AlignGuard SD v1.5 · CoProV2 test (ablation)IP: 0.21 -> 0.07Improved
use paired safe image as DPO positive instead of warning sign (ablation)AlignGuard SD v1.5 · CoProV2 test (ablation)IP: 0.16 -> 0.07Improved
use paired safe image as DPO positive instead of black image (ablation)AlignGuard SD v1.5 · COCOFID: 85.38 -> 70.96Improved
add consistency loss L_con (ablation)AlignGuard SD v1.5 · COCOFID: 74.82 -> 70.96Improved
add consistency loss L_con (ablation)AlignGuard SD v1.5 · COCOCLIPScore: 30.78 -> 32.32Improved
add consistency loss L_con (ablation)AlignGuard SD v1.5 · CoProV2 test (ablation)IP: 0.16 -> 0.07Improved
use Co-Merge instead of TIES (ablation)AlignGuard SD v1.5 · COCOFID: 79.79 -> 70.96Improved
use Co-Merge instead of Task Vectors (ablation)AlignGuard SD v1.5 · COCOCLIPScore: 4.80 -> 32.32Improved
use Co-Merge instead of Model Soups (ablation)AlignGuard SD v1.5 · CoProV2 test (ablation)IP: 0.14 -> 0.07Improved
merge per-category experts (Co-Merge) rather than single LoRA on all data (ablation)AlignGuard SD v1.5 · CoProV2 testavg IP: 0.16 -> 0.07Improved
scale training data from 10% to 100% (ablation)AlignGuard SD v1.5 · CoProV2 test (ablation)IP: 0.19 -> 0.07Improved
apply AlignGuard alignmentSDXL · COCOFID: 68.90 -> 75.20Hurt

Later papers that compared with this method

3 later accepted papers report AlignGuard as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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