AI Paper Atlas

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

Cross-ControlNet: Training-Free Fusion of Multiple Conditions for Text-to-Image Generation

Xiang Liu, Junjun Jiang, Wei Han, Kui Jiang, Xianming Liu

ICLR 2026 · Image generation › Text-to-image diffusion · approach: Compositional text-to-image guidance

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 PixFusion over MaxFusion fusion (ablation)Cross-ControlNet · Conflicting conditions (Pose, Seg)mIoU-P: 0.3528 -> 0.3610Improved
add ChannelFusion in final layer (ablation)Cross-ControlNet · Conflicting conditions (Pose, Seg)mIoU-P: 0.3610 -> 0.3648Improved
add KV-Injection (ablation)Cross-ControlNet · Conflicting conditions (Pose, Seg)mIoU-P: 0.3648 -> 0.3719Improved
apply ChannelFusion at shallow layers instead of final layer (ablation)Cross-ControlNet · Conflicting conditions (Pose, Seg)mIoU-P: 0.3648 -> 0.3447Hurt
start KV-Injection at step 5 instead of step 0 (ablation)Cross-ControlNet · Conflicting conditions (Pose, Seg)MSE-S: 0.2003 -> 0.1983Improved
start KV-Injection late (step 20) (ablation)Cross-ControlNet · Conflicting conditions (Pose, Seg)CLIP score: 0.2978 -> 0.2952Hurt
increase Gaussian kernel std from 0.8 to 3.0 (ablation)Cross-ControlNet · Conflicting conditions (Pose, Seg)mIoU-P: 0.3718 -> 0.3667Hurt
set threshold delta to 0 (naive averaging) (ablation)Cross-ControlNet · Qualitativepose faithfulnessHurt
use Cross-ControlNet instead of MaxFusion on complementary conditionsCross-ControlNet · Complementary (Hed, Seg)SSIM: 0.2382 -> 0.2404Improved
use Cross-ControlNet vs EasyControl on FLUXCross-ControlNet · Complementary (Canny, Depth), FLUX.1-devSSIM: 0.4129 -> 0.3735Hurt
use Cross-ControlNet vs MaxFusion latencyCross-ControlNet · Inference timetime (s): 12.932 -> 14.759Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 3 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