# Test-time Prompt Refinement for Text-to-Image Models

arXiv: https://arxiv.org/abs/2507.22076 · HTML: https://mlsanity.com/paper/2507.22076/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 54 references that are in the map.
- First posted on arXiv 22 Jul 2025.

## Builds on (most cited first, 30 of 45)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [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)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment](https://mlsanity.com/paper/2310.11513/) (2023)
- [eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers](https://mlsanity.com/paper/2211.01324/) (2022)
- [GLIGEN: Open-Set Grounded Text-to-Image Generation](https://mlsanity.com/paper/2301.07093/) (2023)
- [Generative Adversarial Text to Image Synthesis](https://mlsanity.com/paper/1605.05396/) (2016)
- [CogView: Mastering Text-to-Image Generation via Transformers](https://mlsanity.com/paper/2105.13290/) (2021)
- [Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models](https://mlsanity.com/paper/2303.04671/) (2023)
- [StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks](https://mlsanity.com/paper/1612.03242/) (2016)
- [MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation](https://mlsanity.com/paper/2302.08113/) (2023)
- [Paint by Example: Exemplar-based Image Editing with Diffusion Models](https://mlsanity.com/paper/2211.13227/) (2022)
- [DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models](https://mlsanity.com/paper/2305.16381/) (2023)
- [Blended Latent Diffusion](https://mlsanity.com/paper/2206.02779/) (2022)
- [Aligning Text-to-Image Models using Human Feedback](https://mlsanity.com/paper/2302.12192/) (2023)
- [LayoutGPT: Compositional Visual Planning and Generation with Large Language Models](https://mlsanity.com/paper/2305.15393/) (2023)
- [Training-Free Layout Control with Cross-Attention Guidance](https://mlsanity.com/paper/2304.03373/) (2023)
- [DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis](https://mlsanity.com/paper/1904.01310/) (2019)

## Built on by (most cited first, 16 of 16)

- [WoW: Towards a World omniscient World model Through Embodied Interaction](https://mlsanity.com/paper/2509.22642/) (2025)
- [Show, Don't Tell: Morphing Latent Reasoning into Image Generation](https://mlsanity.com/paper/2602.02227/) (2026)
- [RAISE: Requirement-Adaptive Evolutionary Refinement for Training-Free Text-to-Image Alignment](https://mlsanity.com/paper/2603.00483/) (2026)
- [World-To-Image: Grounding Text-to-Image Generation with Agent-Driven World Knowledge](https://mlsanity.com/paper/2510.04201/) (2025)
- [Guiding What Not to Generate: Automated Negative Prompting for Text-Image Alignment](https://mlsanity.com/paper/2512.07702/) (2025)
- [EPIC: Efficient Predicate-Guided Inference-Time Control for Compositional Text-to-Image Generation](https://mlsanity.com/paper/2605.11722/) (2026)
- [Generative AI for Visualizing Highway Construction Hazards Through Synthetic Images and Temporal Sequences](https://mlsanity.com/paper/2605.11276/) (2026)
- [DuET: Dual Expert Trajectories for Diffusion Image Editing](https://mlsanity.com/paper/2606.13303/) (2026)
- [Don't Settle at the Mode! Mitigating Diversity Collapse in Pretrained Flow Models via Feature Self-Guidance](https://mlsanity.com/paper/2606.27371/) (2026)
- [Agentic Visual Generation: From Generative Models to Agentic Control](https://mlsanity.com/paper/2609.06758/) (2026)
- [No Concept Left Behind: Test-Time Optimization for Compositional Text-to-Image Generation](https://mlsanity.com/paper/2509.23457/) (2025)
- [Evolutionary Token-Level Prompt Optimization for Diffusion Models](https://mlsanity.com/paper/2604.09861/) (2026)
- [UniRect-CoT: Enhancing Generation in Unified Multimodal Models via Reflective Rectification with Inherent Understanding](https://mlsanity.com/paper/2604.13540/) (2026)
- [WarpI2I: Image Warping for Image-to-Image Translation](https://mlsanity.com/paper/2606.31018/) (2026)
- [Reasoning with Image Generation](https://mlsanity.com/paper/2609.16409/) (2026)
- [PreviewDiff: Multimodal Critic-Guided Search over Diffusion Latents](https://mlsanity.com/paper/2609.36199/) (2026)

## Abstract (arXiv)

Text-to-image (T2I) generation models have made significant strides but still struggle with prompt sensitivity: even minor changes in prompt wording can yield inconsistent or inaccurate outputs. To address this challenge, we introduce a closed-loop, test-time prompt refinement framework that requires no additional training of the underlying T2I model, termed TIR. In our approach, each generation step is followed by a refinement step, where a pretrained multimodal large language model (MLLM) analyzes the output image and the user's prompt. The MLLM detects misalignments (e.g., missing objects, incorrect attributes) and produces a refined and physically grounded prompt for the next round of image generation. By iteratively refining the prompt and verifying alignment between the prompt and the image, TIR corrects errors, mirroring the iterative refinement process of human artists. We demonstrate that this closed-loop strategy improves alignment and visual coherence across multiple benchmark datasets, all while maintaining plug-and-play integration with black-box T2I models. Code is available at https://github.com/hafeezkhan909/Test-time-Image-Refinement.