AI Paper Atlas

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

DivControl: Knowledge Diversion for Controllable Image Generation

Yucheng Xie, Fu Feng, Ruixiao Shi, Jing Wang, Yong Rui, Xin Geng

AAAI 2026 · Image generation › Text-to-image diffusion · approach: Text-driven synthesis and semantic guidance · 0 citations (OpenAlex)

Read the paper

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 knowledge diversion (SVD learngenes and tailors with dynamic gate) (ablation)ControlNet on PixArt-δ · 8 basic conditions (average)LPIPS / SSIM / CLIP-I: LPIPS 0.328 -> 0.302; SSIM 0.663 -> 0.693; CLIP-I 89.43 -> 90.63Improved
add REPA on top of knowledge diversion (ablation)DivControl · 8 basic conditions (average)LPIPS / SSIM / CLIP-I: LPIPS 0.302 -> 0.290; SSIM 0.693 -> 0.696; CLIP-I 90.63 -> 91.31Improved
use alignment weight 0.05 instead of 0.5 (ablation)REPA · basic conditionsFID: 40.76 -> 39.84Improved
align at layer 4 instead of layer 2 or 6 (ablation)REPA · basic conditionsLPIPS: 0.301 -> 0.290 (layer 2); 0.303 (layer 6)Improved
DivControl vs CtrLoRA-SD training costDivControl · training costGPU hours: 6000 -> 165Improved
DivControl vs CtrLoRA-PA on basic conditionsDivControl · 8 basic conditions (average)CLIP-I: 91.85 -> 92.29Improved
DivControl vs CtrLoRA-SD on average CLIP-IDivControl · 8 basic conditions (average)CLIP-I: 92.24 -> 92.29No clear effect
finetune tailors only on 200 images for high-shift novel conditionsDivControl · novel conditions (average)CLIP-I: 92.34 -> 93.07 vs CtrLoRA-PAImproved

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