# Towards Evaluating Robustness of Prompt Adherence in Text to Image Models

arXiv: https://arxiv.org/abs/2507.08039 · HTML: https://mlsanity.com/paper/2507.08039/

## Key facts

- Cited by 1 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 22 of its 33 references that are in the map.
- First posted on arXiv 9 Jul 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, 22 of 22)

- [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)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [SPICE: Semantic Propositional Image Caption Evaluation](https://mlsanity.com/paper/1607.08822/) (2016)
- [Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling](https://mlsanity.com/paper/2501.17811/) (2025)
- [PaLI: A Jointly-Scaled Multilingual Language-Image Model](https://mlsanity.com/paper/2209.06794/) (2022)
- [Evaluating Text-to-Visual Generation with Image-to-Text Generation](https://mlsanity.com/paper/2404.01291/) (2024)
- [TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering](https://mlsanity.com/paper/2303.11897/) (2023)
- [JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation](https://mlsanity.com/paper/2411.07975/) (2024)
- [Playground v3: Improving Text-to-Image Alignment with Deep-Fusion Large Language Models](https://mlsanity.com/paper/2409.10695/) (2024)
- [What You See is What You Read? Improving Text-Image Alignment Evaluation](https://mlsanity.com/paper/2305.10400/) (2023)
- [Benchmarking Spatial Relationships in Text-to-Image Generation](https://mlsanity.com/paper/2212.10015/) (2022)
- [Semantic Object Accuracy for Generative Text-to-Image Synthesis](https://mlsanity.com/paper/1910.13321/) (2019)
- [TIGEr: Text-to-Image Grounding for Image Caption Evaluation](https://mlsanity.com/paper/1909.02050/) (2019)
- [Divide, Evaluate, and Refine: Evaluating and Improving Text-to-Image Alignment with Iterative VQA Feedback](https://mlsanity.com/paper/2307.04749/) (2023)
- [X-IQE: eXplainable Image Quality Evaluation for Text-to-Image Generation with Visual Large Language Models](https://mlsanity.com/paper/2305.10843/) (2023)
- [TIAM -- A Metric for Evaluating Alignment in Text-to-Image Generation](https://mlsanity.com/paper/2307.05134/) (2023)
- [TISE: Bag of Metrics for Text-to-Image Synthesis Evaluation](https://mlsanity.com/paper/2112.01398/) (2021)
- [Explaining latent representations of generative models with large multimodal models](https://mlsanity.com/paper/2402.01858/) (2024)

## Built on by (most cited first, 1 of 1)

- [From Image Generation to Infrastructure Design: a Multi-agent Pipeline for Street Design Generation](https://mlsanity.com/paper/2509.05469/) (2025)

## Abstract (arXiv)

The advancements in the domain of LLMs in recent years have surprised many, showcasing their remarkable capabilities and diverse applications. Their potential applications in various real-world scenarios have led to significant research on their reliability and effectiveness. On the other hand, multimodal LLMs and Text-to-Image models have only recently gained prominence, especially when compared to text-only LLMs. Their reliability remains constrained due to insufficient research on assessing their performance and robustness. This paper aims to establish a comprehensive evaluation framework for Text-to-Image models, concentrating particularly on their adherence to prompts. We created a novel dataset that aimed to assess the robustness of these models in generating images that conform to the specified factors of variation in the input text prompts. Our evaluation studies present findings on three variants of Stable Diffusion models: Stable Diffusion 3 Medium, Stable Diffusion 3.5 Large, and Stable Diffusion 3.5 Large Turbo, and two variants of Janus models: Janus Pro 1B and Janus Pro 7B. We introduce a pipeline that leverages text descriptions generated by the gpt-4o model for our ground-truth images, which are then used to generate artificial images by passing these descriptions to the Text-to-Image models. We then pass these generated images again through gpt-4o using the same system prompt and compare the variation between the two descriptions. Our results reveal that these models struggle to create simple binary images with only two factors of variation: a simple geometric shape and its location. We also show, using pre-trained VAEs on our dataset, that they fail to generate images that follow our input dataset distribution.