# Reflect-DiT: Inference-Time Scaling for Text-to-Image Diffusion Transformers via In-Context Reflection

arXiv: https://arxiv.org/abs/2503.12271 · HTML: https://mlsanity.com/paper/2503.12271/

## Key facts

- Cited by 43 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion reasoning and test-time scaling, one of 17 directions in LLM reasoning.
- Builds on 61 of its 72 references that are in the map.
- First posted on arXiv 15 Mar 2025.

## Placed in

- LLM reasoning / [Diffusion reasoning and test-time scaling](https://mlsanity.com/lr/diffusion-reasoning-and-test-time-scaling/)
- 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 61)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [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)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.08453/) (2023)
- [Scaling Autoregressive Models for Content-Rich Text-to-Image Generation](https://mlsanity.com/paper/2206.10789/) (2022)
- [Multi-Concept Customization of Text-to-Image Diffusion](https://mlsanity.com/paper/2212.04488/) (2022)
- [Large Language Monkeys: Scaling Inference Compute with Repeated Sampling](https://mlsanity.com/paper/2407.21787/) (2024)
- [GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment](https://mlsanity.com/paper/2310.11513/) (2023)
- [Diffusion Model Alignment Using Direct Preference Optimization](https://mlsanity.com/paper/2311.12908/) (2023)
- [GLIGEN: Open-Set Grounded Text-to-Image Generation](https://mlsanity.com/paper/2301.07093/) (2023)
- [Generative Verifiers: Reward Modeling as Next-Token Prediction](https://mlsanity.com/paper/2408.15240/) (2024)
- [ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment](https://mlsanity.com/paper/2403.05135/) (2024)
- [BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing](https://mlsanity.com/paper/2305.14720/) (2023)
- [Training Language Models to Self-Correct via Reinforcement Learning](https://mlsanity.com/paper/2409.12917/) (2024)
- [ELITE: Encoding Visual Concepts into Textual Embeddings for Customized Text-to-Image Generation](https://mlsanity.com/paper/2302.13848/) (2023)

## Built on by (most cited first, 30 of 43)

- [From Reflection to Perfection: Scaling Inference-Time Optimization for Text-to-Image Diffusion Models via Reflection Tuning](https://mlsanity.com/paper/2504.16080/) (2025)
- [Inference-time Scaling of Diffusion Models through Classical Search](https://mlsanity.com/paper/2505.23614/) (2025)
- [PosterCraft: Rethinking High-Quality Aesthetic Poster Generation in a Unified Framework](https://mlsanity.com/paper/2506.10741/) (2025)
- [Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?](https://mlsanity.com/paper/2509.03516/) (2025)
- [ReasonEdit: Towards Reasoning-Enhanced Image Editing Models](https://mlsanity.com/paper/2511.22625/) (2025)
- [GEMS: Agent-Native Multimodal Generation with Memory and Skills](https://mlsanity.com/paper/2603.28088/) (2026)
- [Thinking-while-Generating: Interleaving Textual Reasoning throughout Visual Generation](https://mlsanity.com/paper/2511.16671/) (2025)
- [ImAgent: A Unified Multimodal Agent Framework for Test-Time Scalable Image Generation](https://mlsanity.com/paper/2511.11483/) (2025)
- [Lavida-O: Elastic Large Masked Diffusion Models for Unified Multimodal Understanding and Generation](https://mlsanity.com/paper/2509.19244/) (2025)
- [CoF-T2I: Video Models as Pure Visual Reasoners for Text-to-Image Generation](https://mlsanity.com/paper/2601.10061/) (2026)
- [MILR: Improving Multimodal Image Generation via Test-Time Latent Reasoning](https://mlsanity.com/paper/2509.22761/) (2025)
- [From Scale to Speed: Adaptive Test-Time Scaling for Image Editing](https://mlsanity.com/paper/2603.00141/) (2026)
- [RAISE: Requirement-Adaptive Evolutionary Refinement for Training-Free Text-to-Image Alignment](https://mlsanity.com/paper/2603.00483/) (2026)
- [SCOPE: Structured Decomposition and Conditional Skill Orchestration for Complex Image Generation](https://mlsanity.com/paper/2605.08043/) (2026)
- [Where and How to Perturb: On the Design of Perturbation Guidance in Diffusion and Flow Models](https://mlsanity.com/paper/2506.10978/) (2025)
- [NEP: Autoregressive Image Editing via Next Editing Token Prediction](https://mlsanity.com/paper/2508.06044/) (2025)
- [Unified Thinker: A General Reasoning Modular Core for Image Generation](https://mlsanity.com/paper/2601.03127/) (2026)
- [KDPE: A Kernel Density Estimation Strategy for Diffusion Policy Trajectory Selection](https://mlsanity.com/paper/2508.10511/) (2025)
- [Tiny Inference-Time Scaling with Latent Verifiers](https://mlsanity.com/paper/2603.22492/) (2026)
- [Stream-T1: Test-Time Scaling for Streaming Video Generation](https://mlsanity.com/paper/2605.04461/) (2026)
- [Data-Driven Loss Functions for Inference-Time Optimization in Text-to-Image](https://mlsanity.com/paper/2509.02295/) (2025)
- [Breaking Dual Bottlenecks: Evolving Unified Multimodal Models into Self-Adaptive Interleaved Visual Reasoners](https://mlsanity.com/paper/2605.14709/) (2026)
- [dMLLM-TTS: Self-Verified and Efficient Test-Time Scaling for Diffusion Multi-Modal Large Language Models](https://mlsanity.com/paper/2512.19433/) (2025)
- [EPIC: Efficient Predicate-Guided Inference-Time Control for Compositional Text-to-Image Generation](https://mlsanity.com/paper/2605.11722/) (2026)
- [Drift Flow Matching](https://mlsanity.com/paper/2605.17244/) (2026)
- [InterleaveThinker: Reinforcing Agentic Interleaved Generation](https://mlsanity.com/paper/2606.13679/) (2026)
- [OmniQuality-R: Advancing Reward Models Through All-Encompassing Quality Assessment](https://mlsanity.com/paper/2510.10609/) (2025)
- [Compositional Image Synthesis with Inference-Time Scaling](https://mlsanity.com/paper/2510.24133/) (2025)
- [Rethinking Test Time Scaling for Flow-Matching Generative Models](https://mlsanity.com/paper/2511.22242/) (2025)
- [Large Language Models are Universal Reasoners for Visual Generation](https://mlsanity.com/paper/2605.04040/) (2026)

## Abstract (arXiv)

The predominant approach to advancing text-to-image generation has been training-time scaling, where larger models are trained on more data using greater computational resources. While effective, this approach is computationally expensive, leading to growing interest in inference-time scaling to improve performance. Currently, inference-time scaling for text-to-image diffusion models is largely limited to best-of-N sampling, where multiple images are generated per prompt and a selection model chooses the best output. Inspired by the recent success of reasoning models like DeepSeek-R1 in the language domain, we introduce an alternative to naive best-of-N sampling by equipping text-to-image Diffusion Transformers with in-context reflection capabilities. We propose Reflect-DiT, a method that enables Diffusion Transformers to refine their generations using in-context examples of previously generated images alongside textual feedback describing necessary improvements. Instead of passively relying on random sampling and hoping for a better result in a future generation, Reflect-DiT explicitly tailors its generations to address specific aspects requiring enhancement. Experimental results demonstrate that Reflect-DiT improves performance on the GenEval benchmark (+0.19) using SANA-1.0-1.6B as a base model. Additionally, it achieves a new state-of-the-art score of 0.81 on GenEval while generating only 20 samples per prompt, surpassing the previous best score of 0.80, which was obtained using a significantly larger model (SANA-1.5-4.8B) with 2048 samples under the best-of-N approach.