AI Paper Atlas

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

MagicQuill V2: Precise and Interactive Image Editing with Layered Visual Cues

Zichen Liu, Yue Yu, Hao Ouyang, Qiuyu Wang, Shuailei Ma, Ka Leong Cheng, Wen Wang, Qingyan Bai, Yuxuan Zhang, Yanhong Zeng, Yixuan Li, Xing Zhu and 2 more

CVPR 2026 · Image generation › Text-to-image diffusion · approach: Layout-to-image control

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 edge layer and color layer together instead of edge only (ablation)MagicQuill V2 control layers · Pico-Banana-400K, 1,000 casesLPIPS: 0.317 -> 0.283Improved
add color layer to the edge layer (ablation)MagicQuill V2 control layers · Pico-Banana-400K, 1,000 casesL1: 0.107 -> 0.080Improved
add edge layer to the color layer (ablation)MagicQuill V2 control layers · Pico-Banana-400K, 1,000 casesL1: 0.080 -> 0.080No clear effect
use MagicQuill V2 edge layer instead of Qwen-Image edge control moduleedge-guided editing · Pico-Banana-400K, 1,000 casesL1: 0.131 -> 0.107Improved
add the data-construction pipeline (completion LoRA, relight, perspective, resolution augmentations) to FLUX Kontextcontent layer · Content layer test set (200 samples)LPIPS: 0.359 -> 0.202Improved
remove perspective augmentation (ablation)content layer training data · qualitative cabinet examplequalitative geometry correctionHurt
remove relight augmentation (ablation)content layer training data · qualitative bar examplequalitative lighting harmonyHurt
remove object completion LoRA from data pipeline (ablation)content layer training data · qualitative occluded book examplequalitative interactionHurt
remove resolution augmentation (ablation)content layer training data · qualitative low-quality cuesqualitative image qualityHurt
increase control strength sigma (ablation)edge and color layers · qualitative control strength analysiscue adherenceMixed
fine-tune spatial branch for removal and use MagicQuill V2 instead of OmniEraser (ControlNet)object removal · RORD, 5,000 samplesFID: 25.92 -> 16.42Improved

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