AI Paper Atlas

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

BideDPO: Conditional Image Generation with Simultaneous Text and Condition Alignment

Dewei Zhou, Mingwei Li, Zongxin Yang, Yu Lu, Yunqiu Xu, Zhizhong Wang, Zeyi Huang, Yi Yang

ICLR 2026 · Image generation › Text-to-image diffusion · approach: T2I evaluation and controllable adapters · 9 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 adaptive loss balancing (ablation)BideDPO on Union-Pro2 · DualAlign depthsuccess rate: 0.78 -> 0.84Improved
add adaptive loss balancing (ablation)BideDPO on Union-Pro2 · DualAlign depthMSE: 157.729 -> 163.968Hurt
add condition preference pairs to text-only pairs (ablation)BideDPO on Union-Pro2 · DualAlign depthMSE: 258.954 -> 163.968Improved
add text preference pairs to condition-only pairs (ablation)BideDPO on Union-Pro2 · DualAlign depthsuccess rate: 0.59 -> 0.84Improved
iterate optimization to 3 rounds (ablation)BideDPO on Union-Pro2 · DualAlign depthsuccess rate: 0.84 -> 0.88Improved
4th iteration (ablation)BideDPO on Union-Pro2 · DualAlign depthsuccess rate: 0.88 -> 0.86Hurt
decoupled BideDPO instead of naive DPOUnion-Pro2 · DualAlign depthsuccess rate: 0.71 -> 0.84Improved
decoupled BideDPO instead of naive DPOFLUX-Canny · DualAlign cannysuccess rate: 0.55 -> 0.73Improved
decoupled BideDPO instead of SFT on same positivesFLUX-Depth · DualAlign depthMSE: 162.2 -> 145.9Improved
apply BideDPOUnion-Pro2 · DualAlign depthsuccess rate: 0.49 -> 0.84Improved
apply BideDPOFLUX-Canny · DualAlign cannysuccess rate: 0.33 -> 0.73Improved
apply BideDPO to IP-AdapterFLUX IP-Adapter · Style-conditionedstyle score: 6.50 -> 6.26Hurt

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