# OminiControl2: Efficient Conditioning for Diffusion Transformers

arXiv: https://arxiv.org/abs/2503.08280 · HTML: https://mlsanity.com/paper/2503.08280/

## Key facts

- Cited by 57 papers in the map (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 33 of its 39 references that are in the map.
- First posted on arXiv 11 Mar 2025.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 30 of 33)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [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)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2308.06721/) (2023)
- [T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.08453/) (2023)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis](https://mlsanity.com/paper/2310.00426/) (2023)
- [Efficiently Scaling Transformer Inference](https://mlsanity.com/paper/2211.05102/) (2022)
- [OminiControl: Minimal and Universal Control for Diffusion Transformer](https://mlsanity.com/paper/2411.15098/) (2024)
- [Token Merging for Fast Stable Diffusion](https://mlsanity.com/paper/2303.17604/) (2023)
- [UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild](https://mlsanity.com/paper/2305.11147/) (2023)
- [Delta-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformers](https://mlsanity.com/paper/2406.01125/) (2024)
- [Accelerating Diffusion Transformers with Token-wise Feature Caching](https://mlsanity.com/paper/2410.05317/) (2024)
- [ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback](https://mlsanity.com/paper/2404.07987/) (2024)
- [SSR-Encoder: Encoding Selective Subject Representation for Subject-Driven Generation](https://mlsanity.com/paper/2312.16272/) (2023)
- [Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching](https://mlsanity.com/paper/2406.01733/) (2024)
- [FORA: Fast-Forward Caching in Diffusion Transformer Acceleration](https://mlsanity.com/paper/2407.01425/) (2024)
- [Prodigy: An Expeditiously Adaptive Parameter-Free Learner](https://mlsanity.com/paper/2306.06101/) (2023)
- [ACE++: Instruction-Based Image Creation and Editing via Context-Aware Content Filling](https://mlsanity.com/paper/2501.02487/) (2025)
- [Diffusion Self-Distillation for Zero-Shot Customized Image Generation](https://mlsanity.com/paper/2411.18616/) (2024)
- [DiP-GO: A Diffusion Pruner via Few-step Gradient Optimization](https://mlsanity.com/paper/2410.16942/) (2024)
- [LazyDiT: Lazy Learning for the Acceleration of Diffusion Transformers](https://mlsanity.com/paper/2412.12444/) (2024)
- [Multi-modal Attention for Speech Emotion Recognition](https://mlsanity.com/paper/2009.04107/) (2020)
- [RelaCtrl: Relevance-Guided Efficient Control for Diffusion Transformers](https://mlsanity.com/paper/2502.14377/) (2025)
- [AnyStory: Towards Unified Single and Multiple Subject Personalization in Text-to-Image Generation](https://mlsanity.com/paper/2501.09503/) (2025)

## Built on by (most cited first, 30 of 57)

- [OmniConsistency: Learning Style-Agnostic Consistency from Paired Stylization Data](https://mlsanity.com/paper/2505.18445/) (2025)
- [FullDiT2: Efficient In-Context Conditioning for Video Diffusion Transformers](https://mlsanity.com/paper/2506.04213/) (2025)
- [ContextGen: Contextual Layout Anchoring for Identity-Consistent Multi-Instance Generation](https://mlsanity.com/paper/2510.11000/) (2025)
- [TextFlux: An OCR-Free DiT Model for High-Fidelity Multilingual Scene Text Synthesis](https://mlsanity.com/paper/2505.17778/) (2025)
- [OmniTry: Virtual Try-On Anything without Masks](https://mlsanity.com/paper/2508.13632/) (2025)
- [FastFit: Accelerating Multi-Reference Virtual Try-On via Cacheable Diffusion Models](https://mlsanity.com/paper/2508.20586/) (2025)
- [Image Editing As Programs with Diffusion Models](https://mlsanity.com/paper/2506.04158/) (2025)
- [IC-Custom: Diverse Image Customization via In-Context Learning](https://mlsanity.com/paper/2507.01926/) (2025)
- [LAMIC: Layout-Aware Multi-Image Composition via Scalability of Multimodal Diffusion Transformer](https://mlsanity.com/paper/2508.00477/) (2025)
- [JCo-MVTON: Jointly Controllable Multi-Modal Diffusion Transformer for Mask-Free Virtual Try-on](https://mlsanity.com/paper/2508.17614/) (2025)
- [DeContext as Defense: Safe Image Editing in Diffusion Transformers](https://mlsanity.com/paper/2512.16625/) (2025)
- [SpotEdit: Selective Region Editing in Diffusion Transformers](https://mlsanity.com/paper/2512.22323/) (2025)
- [InnoAds-Composer: Efficient Condition Composition for E-Commerce Poster Generation](https://mlsanity.com/paper/2603.05898/) (2026)
- [LaTo: Landmark-tokenized Diffusion Transformer for Fine-grained Human Face Editing](https://mlsanity.com/paper/2509.25731/) (2025)
- [ConsistCompose: Unified Multimodal Layout Control for Image Composition](https://mlsanity.com/paper/2511.18333/) (2025)
- [NeuralRemaster: Phase-Preserving Diffusion for Structure-Aligned Generation](https://mlsanity.com/paper/2512.05106/) (2025)
- [AVControl: Efficient Framework for Training Audio-Visual Controls](https://mlsanity.com/paper/2603.24793/) (2026)
- [Neural-Driven Image Editing](https://mlsanity.com/paper/2507.05397/) (2025)
- [PositionIC: Unified Position and Identity Consistency for Image Customization](https://mlsanity.com/paper/2507.13861/) (2025)
- [Scaling Up Audio-Synchronized Visual Animation: An Efficient Training Paradigm](https://mlsanity.com/paper/2508.03955/) (2025)
- [MagicQuillV2: Precise and Interactive Image Editing with Layered Visual Cues](https://mlsanity.com/paper/2512.03046/) (2025)
- [IC-Effect: Precise and Efficient Video Effects Editing via In-Context Learning](https://mlsanity.com/paper/2512.15635/) (2025)
- [Generative Refocusing: Flexible Defocus Control from a Single Image](https://mlsanity.com/paper/2512.16923/) (2025)
- [SeeThrough3D: Occlusion Aware 3D Control in Text-to-Image Generation](https://mlsanity.com/paper/2602.23359/) (2026)
- [InfiniHuman: Infinite 3D Human Creation with Precise Control](https://mlsanity.com/paper/2510.11650/) (2025)
- [DiffSeg30k: A Multi-Turn Diffusion Editing Benchmark for Localized AIGC Detection](https://mlsanity.com/paper/2511.19111/) (2025)
- [FlexID: Training-Free Flexible Identity Injection via Intent-Aware Modulation for Text-to-Image Generation](https://mlsanity.com/paper/2602.07554/) (2026)
- [Inject Where It Matters: Training-Free Spatially-Adaptive Identity Preservation for Text-to-Image Personalization](https://mlsanity.com/paper/2602.13994/) (2026)
- [Vision Bridge Transformer at Scale](https://mlsanity.com/paper/2511.23199/) (2025)
- [RSEdit: Text-Guided Image Editing for Remote Sensing](https://mlsanity.com/paper/2603.13708/) (2026)

## Abstract (arXiv)

Fine-grained control of text-to-image diffusion transformer models (DiT) remains a critical challenge for practical deployment. While recent advances such as OminiControl and others have enabled a controllable generation of diverse control signals, these methods face significant computational inefficiency when handling long conditional inputs. We present OminiControl2, an efficient framework that achieves efficient image-conditional image generation. OminiControl2 introduces two key innovations: (1) a dynamic compression strategy that streamlines conditional inputs by preserving only the most semantically relevant tokens during generation, and (2) a conditional feature reuse mechanism that computes condition token features only once and reuses them across denoising steps. These architectural improvements preserve the original framework's parameter efficiency and multi-modal versatility while dramatically reducing computational costs. Our experiments demonstrate that OminiControl2 reduces conditional processing overhead by over 90% compared to its predecessor, achieving an overall 5.9× speedup in multi-conditional generation scenarios. This efficiency enables the practical implementation of complex, multi-modal control for high-quality image synthesis with DiT models.