# BideDPO: Conditional Image Generation with Simultaneous Text and Condition Alignment

arXiv: https://arxiv.org/abs/2511.19268 · HTML: https://mlsanity.com/paper/2511.19268/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion and multimodal model alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 43 of its 49 references that are in the map.
- First posted on arXiv 24 Nov 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Diffusion and multimodal model alignment](https://mlsanity.com/alignment/diffusion-and-multimodal-model-alignment/)

## Builds on (most cited first, 30 of 43)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2308.06721/) (2023)
- [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024)
- [ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2304.05977/) (2023)
- [Diffusion Model Alignment Using Direct Preference Optimization](https://mlsanity.com/paper/2311.12908/) (2023)
- [Flow-GRPO: Training Flow Matching Models via Online RL](https://mlsanity.com/paper/2505.05470/) (2025)
- [Directly Fine-Tuning Diffusion Models on Differentiable Rewards](https://mlsanity.com/paper/2309.17400/) (2023)
- [Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2305.16322/) (2023)
- [MACE: Mass Concept Erasure in Diffusion Models](https://mlsanity.com/paper/2403.06135/) (2024)
- [Aligning Text-to-Image Diffusion Models with Reward Backpropagation](https://mlsanity.com/paper/2310.03739/) (2023)
- [TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition](https://mlsanity.com/paper/2307.12493/) (2023)
- [ControlNeXt: Powerful and Efficient Control for Image and Video Generation](https://mlsanity.com/paper/2408.06070/) (2024)
- [ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback](https://mlsanity.com/paper/2404.07987/) (2024)
- [Prodigy: An Expeditiously Adaptive Parameter-Free Learner](https://mlsanity.com/paper/2306.06101/) (2023)
- [MIGC: Multi-Instance Generation Controller for Text-to-Image Synthesis](https://mlsanity.com/paper/2402.05408/) (2024)
- [EasyControl: Adding Efficient and Flexible Control for Diffusion Transformer](https://mlsanity.com/paper/2503.07027/) (2025)
- [Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances](https://mlsanity.com/paper/2410.18775/) (2024)
- [Wavelet-based Fourier Information Interaction with Frequency Diffusion Adjustment for Underwater Image Restoration](https://mlsanity.com/paper/2311.16845/) (2023)
- [LooseControl: Lifting ControlNet for Generalized Depth Conditioning](https://mlsanity.com/paper/2312.03079/) (2023)
- [Pyramid Diffusion Models For Low-light Image Enhancement](https://mlsanity.com/paper/2305.10028/) (2023)
- [Ctrl-Adapter: An Efficient and Versatile Framework for Adapting Diverse Controls to Any Diffusion Model](https://mlsanity.com/paper/2404.09967/) (2024)
- [3DIS: Depth-Driven Decoupled Instance Synthesis for Text-to-Image Generation](https://mlsanity.com/paper/2410.12669/) (2024)
- [MIGC++: Advanced Multi-Instance Generation Controller for Image Synthesis](https://mlsanity.com/paper/2407.02329/) (2024)
- [Scalable Ranked Preference Optimization for Text-to-Image Generation](https://mlsanity.com/paper/2410.18013/) (2024)

## Built on by (most cited first, 10 of 10)

- [LUVE : Latent-Cascaded Ultra-High-Resolution Video Generation with Dual Frequency Experts](https://mlsanity.com/paper/2602.11564/) (2026)
- [From Zero to Detail: A Progressive Spectral Decoupling Paradigm for UHD Image Restoration with New Benchmark](https://mlsanity.com/paper/2604.15654/) (2026)
- [RefineAnything: Multimodal Region-Specific Refinement for Perfect Local Details](https://mlsanity.com/paper/2604.06870/) (2026)
- [MetaPoint: Unlocking Precise Spatial Control in Agentic Visual Generation](https://mlsanity.com/paper/2606.05031/) (2026)
- [Temporal and Cross-Modal Alignment for Enhanced Audiovisual Video Captioning](https://mlsanity.com/paper/2607.01667/) (2026)
- [Advances in GRPO for Generation Models: A Survey](https://mlsanity.com/paper/2603.06623/) (2026)
- [FoleyDirector: Fine-Grained Temporal Steering for Video-to-Audio Generation via Structured Scripts](https://mlsanity.com/paper/2603.19857/) (2026)
- [TRACE: High-Fidelity 3D Scene Editing via Tangible Reconstruction and Geometry-Aligned Contextual Video Masking](https://mlsanity.com/paper/2604.01207/) (2026)
- [Controlla: Learning Controllability via Graph-Constrained Latent Geometry](https://mlsanity.com/paper/2605.16603/) (2026)
- [FedOT: Ownership Verification and Leakage Tracing via Watermarks for Federated LDMs](https://mlsanity.com/paper/2606.22875/) (2026)

## Abstract (arXiv)

Conditional image generation enhances text-to-image synthesis with structural, spatial, or stylistic priors, but current methods face challenges in handling conflicts between sources. These include 1) input-level conflicts, where the conditioning image contradicts the text prompt, and 2) model-bias conflicts, where generative biases disrupt alignment even when conditions match the text. Addressing these conflicts requires nuanced solutions, which standard supervised fine-tuning struggles to provide. Preference-based optimization techniques like Direct Preference Optimization (DPO) show promise but are limited by gradient entanglement between text and condition signals and lack disentangled training data for multi-constraint tasks. To overcome this, we propose a bidirectionally decoupled DPO framework (BideDPO). Our method creates two disentangled preference pairs-one for the condition and one for the text-to reduce gradient entanglement. The influence of pairs is managed using an Adaptive Loss Balancing strategy for balanced optimization. We introduce an automated data pipeline to sample model outputs and generate conflict-aware data. This process is embedded in an iterative optimization strategy that refines both the model and the data. We construct a DualAlign benchmark to evaluate conflict resolution between text and condition. Experiments show BideDPO significantly improves text success rates (e.g., +35%) and condition adherence. We also validate our approach using the COCO dataset. Project Pages: https://limuloo.github.io/BideDPO/.