# Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?

arXiv: https://arxiv.org/abs/2509.03516 · HTML: https://mlsanity.com/paper/2509.03516/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Builds on 67 of its 99 references that are in the map.
- First posted on arXiv 3 Sep 2025.

## Builds on (most cited first, 30 of 67)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (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)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [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)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis](https://mlsanity.com/paper/2405.21075/) (2024)
- [Qwen-Image Technical Report](https://mlsanity.com/paper/2508.02324/) (2025)
- [Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction](https://mlsanity.com/paper/2404.02905/) (2024)
- [GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment](https://mlsanity.com/paper/2310.11513/) (2023)
- [Emerging Properties in Unified Multimodal Pretraining](https://mlsanity.com/paper/2505.14683/) (2025)
- [PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis](https://mlsanity.com/paper/2310.00426/) (2023)
- [Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling](https://mlsanity.com/paper/2501.17811/) (2025)
- [Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation](https://mlsanity.com/paper/2406.06525/) (2024)
- [Multimodal Chain-of-Thought Reasoning in Language Models](https://mlsanity.com/paper/2302.00923/) (2023)
- [Show-o: One Single Transformer to Unify Multimodal Understanding and Generation](https://mlsanity.com/paper/2408.12528/) (2024)
- [Autoregressive Image Generation without Vector Quantization](https://mlsanity.com/paper/2406.11838/) (2024)
- [ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment](https://mlsanity.com/paper/2403.05135/) (2024)
- [TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering](https://mlsanity.com/paper/2303.11897/) (2023)
- [BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset](https://mlsanity.com/paper/2505.09568/) (2025)

## Built on by (most cited first, 30 of 34)

- [RealUnify: Do Unified Models Truly Benefit from Unification? A Comprehensive Benchmark](https://mlsanity.com/paper/2509.24897/) (2025)
- [UniREditBench: A Unified Reasoning-based Image Editing Benchmark](https://mlsanity.com/paper/2511.01295/) (2025)
- [Everything in Its Place: Benchmarking Spatial Intelligence of Text-to-Image Models](https://mlsanity.com/paper/2601.20354/) (2026)
- [GIR-Bench: Versatile Benchmark for Generating Images with Reasoning](https://mlsanity.com/paper/2510.11026/) (2025)
- [DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing](https://mlsanity.com/paper/2602.12205/) (2026)
- [RULER-Bench: Probing Rule-based Reasoning Abilities of Next-level Video Generation Models for Vision Foundation Intelligence](https://mlsanity.com/paper/2512.02622/) (2025)
- [Quantifying the Gap between Understanding and Generation within Unified Multimodal Models](https://mlsanity.com/paper/2602.02140/) (2026)
- [JoyAI-Image: Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation](https://mlsanity.com/paper/2605.04128/) (2026)
- [WiseEdit: Benchmarking Cognition- and Creativity-Informed Image Editing](https://mlsanity.com/paper/2512.00387/) (2025)
- [Unveiling Fine-Grained Visual Traces: Evaluating Multimodal Interleaved Reasoning Chains in Multimodal STEM Tasks](https://mlsanity.com/paper/2604.19697/) (2026)
- [MetaPoint: Unlocking Precise Spatial Control in Agentic Visual Generation](https://mlsanity.com/paper/2606.05031/) (2026)
- [Thinking with Frames: Generative Video Distortion Evaluation via Frame Reward Model](https://mlsanity.com/paper/2601.04033/) (2026)
- [SANEval: Open-Vocabulary Compositional Benchmarks with Failure-mode Diagnosis](https://mlsanity.com/paper/2602.00249/) (2026)
- [Envision: Benchmarking Unified Understanding & Generation for Causal World Process Insights](https://mlsanity.com/paper/2512.01816/) (2025)
- [Spatial Chain-of-Thought: Bridging Understanding and Generation Models for Spatial Reasoning Generation](https://mlsanity.com/paper/2602.11980/) (2026)
- [OmniVerifier-M1: Multimodal Meta-Verifier with Explicit Structured Recalibration](https://mlsanity.com/paper/2605.28805/) (2026)
- [ForensicConcept: Transferable Forensic Concepts for AIGI Detection](https://mlsanity.com/paper/2606.07034/) (2026)
- [Chain-of-Image Generation: Toward Monitorable and Controllable Image Generation](https://mlsanity.com/paper/2512.08645/) (2025)
- [Can Unified Generation and Understanding Models Maintain Semantic Equivalence Across Different Output Modalities?](https://mlsanity.com/paper/2602.23711/) (2026)
- [MathGen: Revealing the Illusion of Mathematical Competence through Text-to-Image Generation](https://mlsanity.com/paper/2603.27959/) (2026)
- [Pseudo-Unification: Entropy Probing Reveals Divergent Information Patterns in Unified Multimodal Models](https://mlsanity.com/paper/2604.10949/) (2026)
- [DynEval: Holistic Evaluations of T2I Generative Models in the Wild](https://mlsanity.com/paper/2607.11199/) (2026)
- [GlobalForge: Towards Robust AI-Generated Image Detection](https://mlsanity.com/paper/2607.14684/) (2026)
- [PEAK: Precise and Persistent Concept Erasure via k-Sparse Autoencoders](https://mlsanity.com/paper/2608.10985/) (2026)
- [Faithful, Enriched, and Precise: Benchmarking Natural-Science Illustration Generation by T2I models](https://mlsanity.com/paper/2606.05949/) (2026)
- [DECODE: Tackling Representation and Decision Degradation in Continual AI-Generated Image Detection](https://mlsanity.com/paper/2607.27882/) (2026)
- [TRACE-Bench: Decomposing and Diagnosing Multi-Reference Image Generation](https://mlsanity.com/paper/2608.16765/) (2026)
- [LoRC: Detecting AI-Generated Images via Low-Rank Collapse in Semantic Residuals](https://mlsanity.com/paper/2608.20882/) (2026)
- [Scalable Question-Centric Text-to-Image Evaluation: Reliable Ranking, Fine-Grained Diagnosis, and Cost-Aware Routing](https://mlsanity.com/paper/2608.24112/) (2026)
- [Presence Is Not Faithfulness: Figurative Vehicle Intrusion in Text-to-Image Generation](https://mlsanity.com/paper/2609.32188/) (2026)

## Abstract (arXiv)

Text-to-image (T2I) generation aims to synthesize images from textual prompts, which jointly specify what must be shown and imply what can be inferred, which thus correspond to two core capabilities: textbftextitcomposition and textbftextitreasoning. Despite recent advances of T2I models in both composition and reasoning, existing benchmarks remain limited in evaluation. They not only fail to provide comprehensive coverage across and within both capabilities, but also largely restrict evaluation to low scene density and simple one-to-one reasoning. To address these limitations, we propose textbftextscT2I-CoReBench, a comprehensive and complex benchmark that evaluates both composition and reasoning capabilities of T2I models. To ensure comprehensiveness, we structure composition around scene graph elements (textitinstance, textitattribute, and textitrelation) and reasoning around the philosophical framework of inference (textitdeductive, textitinductive, and textitabductive), formulating a 12-dimensional evaluation taxonomy. To increase complexity, driven by the inherent real-world complexities, we curate each prompt with higher compositional density for composition and greater reasoning intensity for reasoning. To facilitate fine-grained and reliable evaluation, we also pair each evaluation prompt with a checklist that specifies individual textityes/no questions to assess each intended element independently. In statistics, our benchmark comprises 1,080 challenging prompts and around 13,500 checklist questions. Experiments across 38 current T2I models reveal that their composition capability still remains limited in high compositional scenarios, while the reasoning capability lags even further behind as a critical bottleneck, with all models struggling to infer implicit elements from prompts.