AI Paper Atlas

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

UniCombine: Unified Multi-Conditional Combination with Diffusion Transformer

Haoxuan Wang, Jinlong Peng, Qingdong He, Hao Yang, Ying Jin, Jiafu Wu, Xiaobin Hu, Yanjie Pan, Zhenye Gan, Mingmin Chi, Bo Peng, Yabiao Wang

ICCV 2025 · Image generation › Text-to-image diffusion · approach: Compositional text-to-image guidance · 40 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 Conditional MMDiT Attention (replacing full MMDiT attention) (ablation)UniCombine training-free · Subject-InsertionDINO: 88.42 -> 89.01Improved
add CMMDiT Attention (ablation)UniCombine training-free · Subject-Insertionattention operations: 732.17M -> 612.63MImproved
add CMMDiT Attention (ablation)UniCombine training-free · Subject-CannyDINO: 86.31 -> 86.88Improved
add CMMDiT Attention (ablation)UniCombine training-free · Subject-DepthMSE: 547.63 -> 507.40Improved
add CMMDiT Attention (ablation)UniCombine training-free · Multi-SpatialMSE: 524.04 -> 519.53Improved
put trainable LoRA in denoising branch instead of text branch (ablation)UniCombine training-based · Subject-InsertionDINO: 92.32 -> 92.96Improved
add Denoising-LoRA to single-stream blocks as well as dual-stream blocks (ablation)UniCombine training-based · Subject-InsertionDINO: 92.38 -> 92.96Improved
train Denoising-LoRA on multi-conditional data (training-based vs training-free)UniCombine · Subject-InsertionFID: 6.37 -> 4.55Improved
train Denoising-LoRAUniCombine · Multi-SpatialMSE: 519.53 -> 165.90Improved
train Denoising-LoRAUniCombine · Subject-CannyCLIP-T: 33.21 -> 33.30No clear effect
train Denoising-LoRAUniCombine · Multi-SpatialCLIP-T: 33.70 -> 33.45No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 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