AI Paper Atlas

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

RADIANCE: Relative Adaptive Denoising with IP-Adapter for Novel Concept Enhancement

Zi-Xiang Ni, Bo-Lun Huang, Teng-Fang Hsiao, Bo-Kai Ruan, Hong-Han Shuai

ECCV 2026 · Image generation › Text-to-image diffusion · approach: Compositional text-to-image guidance · 0 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 Bidirectional Scale Controller to fixed-scale guidance (ablation)RADIANCE · RareBench (single-object)overall score: 73.0 -> 89.9Improved
add Bidirectional Scale Controller (ablation)RADIANCE · RareBench (single-object)overall score: 86.8 -> 89.9Improved
use feedback-driven scaling instead of negative prompt (ablation)RADIANCE · RareBench (single-object)overall score: 83.4 -> 89.9Improved
start feedback at T_early=17 instead of 15 (ablation)RADIANCE · RareBench (single-object)overall score: 89.9 -> 88.1Hurt
start feedback at T_early=13 instead of 15 (ablation)RADIANCE · RareBench (single-object)overall score: 89.9 -> 89.1No clear effect
add Delayed Adapter Activation (ablation)RADIANCE · RareBench (multi-object)overall score: 62.7 -> 76.0Improved
add Layer-wise Alternating Guidance (ablation)RADIANCE · RareBench (multi-object)overall score: 71.0 -> 76.0Improved
apply RADIANCE to SD 3.5SD 3.5 · RareBenchoverall score: 75.9 -> 84.7Improved
apply RADIANCE to SD 1.5SD 1.5 · RareBenchoverall score: 33.9 -> 44.0Improved
RADIANCE versus prompt-switching R2F on SD 3.5RADIANCE · RareBenchoverall score: 81.7 -> 84.7Improved
RADIANCE versus R2F on Multi-RelationRADIANCE · RareBenchMulti-Relation score: 64.4 -> 63.1No clear effect
apply RADIANCE to SD 3.5SD 3.5 · T2I-CompBenchoverall score: 74.2 -> 75.9Improved

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