# FineGRAIN: Evaluating Failure Modes of Text-to-Image Models with Vision Language Model Judges

arXiv: https://arxiv.org/abs/2512.02161 · HTML: https://mlsanity.com/paper/2512.02161/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in MLLM training and visual instruction tuning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 24 of its 34 references that are in the map.
- First posted on arXiv 1 Dec 2025.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM training and visual instruction tuning](https://mlsanity.com/mllm/mllm-training-and-visual-instruction-tuning/)

## Builds on (most cited first, 24 of 24)

- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [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)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [Scaling Autoregressive Models for Content-Rich Text-to-Image Generation](https://mlsanity.com/paper/2206.10789/) (2022)
- [Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2305.01569/) (2023)
- [Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis](https://mlsanity.com/paper/2306.09341/) (2023)
- [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)
- [EvalCrafter: Benchmarking and Evaluating Large Video Generation Models](https://mlsanity.com/paper/2310.11440/) (2023)
- [T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-image Generation](https://mlsanity.com/paper/2307.06350/) (2023)
- [Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image Inpainting](https://mlsanity.com/paper/2212.06909/) (2022)
- [Davidsonian Scene Graph: Improving Reliability in Fine-grained Evaluation for Text-to-Image Generation](https://mlsanity.com/paper/2310.18235/) (2023)
- [Holistic Evaluation of Text-To-Image Models](https://mlsanity.com/paper/2311.04287/) (2023)
- [GenAI-Bench: Evaluating and Improving Compositional Text-to-Visual Generation](https://mlsanity.com/paper/2406.13743/) (2024)
- [ConceptMix: A Compositional Image Generation Benchmark with Controllable Difficulty](https://mlsanity.com/paper/2408.14339/) (2024)
- [Commonsense-T2I Challenge: Can Text-to-Image Generation Models Understand Commonsense?](https://mlsanity.com/paper/2406.07546/) (2024)
- [Revisiting Text-to-Image Evaluation with Gecko: On Metrics, Prompts, and Human Ratings](https://mlsanity.com/paper/2404.16820/) (2024)
- [IllusionVQA: A Challenging Optical Illusion Dataset for Vision Language Models](https://mlsanity.com/paper/2403.15952/) (2024)
- [UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling](https://mlsanity.com/paper/2408.04810/) (2024)
- [ConMe: Rethinking Evaluation of Compositional Reasoning for Modern VLMs](https://mlsanity.com/paper/2406.08164/) (2024)
- [SonicDiffusion: Audio-Driven Image Generation and Editing with Pretrained Diffusion Models](https://mlsanity.com/paper/2405.00878/) (2024)

## Built on by (most cited first, 7 of 7)

- [DiRotQ: Rotation-Aware Quantization for 4-bit Diffusion Transformers](https://mlsanity.com/paper/2605.16732/) (2026)
- [FAGER: Factually Grounded Evaluation and Refinement of Text-to-Image Models](https://mlsanity.com/paper/2605.19111/) (2026)
- [Benchmarking Frontier Text-to-Image Models on Image-Description Prompts](https://mlsanity.com/paper/2608.14976/) (2026)
- [Skill-Aligned Annotation for Reliable Evaluation in Text-to-Image Generation](https://mlsanity.com/paper/2605.13223/) (2026)
- [The Safeguard Worked. Is the LLM System Safer?](https://mlsanity.com/paper/2609.00519/) (2026)
- [Pinocchio: Fast Uncertainty Estimates for Black-Box Language Models](https://mlsanity.com/paper/2609.24881/) (2026)
- [VisExMEM: Visual Evidence-Based Explainable Multimodal Evaluation Metric](https://mlsanity.com/paper/2610.16441/) (2026)

## Abstract (arXiv)

Text-to-image (T2I) models are capable of generating visually impressive images, yet they often fail to accurately capture specific attributes in user prompts, such as the correct number of objects with the specified colors. The diversity of such errors underscores the need for a hierarchical evaluation framework that can compare prompt adherence abilities of different image generation models. Simultaneously, benchmarks of vision language models (VLMs) have not kept pace with the complexity of scenes that VLMs are used to annotate. In this work, we propose a structured methodology for jointly evaluating T2I models and VLMs by testing whether VLMs can identify 27 specific failure modes in the images generated by T2I models conditioned on challenging prompts. Our second contribution is a dataset of prompts and images generated by 5 T2I models (Flux, SD3-Medium, SD3-Large, SD3.5-Medium, SD3.5-Large) and the corresponding annotations from VLMs (Molmo, InternVL3, Pixtral) annotated by an LLM (Llama3) to test whether VLMs correctly identify the failure mode in a generated image. By analyzing failure modes on a curated set of prompts, we reveal systematic errors in attribute fidelity and object representation. Our findings suggest that current metrics are insufficient to capture these nuanced errors, highlighting the importance of targeted benchmarks for advancing generative model reliability and interpretability.