# Lighting (In)consistency of Paint by Text

arXiv: https://arxiv.org/abs/2207.13744 · HTML: https://mlsanity.com/paper/2207.13744/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 22 references that are in the map.
- First posted on arXiv 27 Jul 2022.

## Builds on (most cited first, 6 of 6)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [Scaling Autoregressive Models for Content-Rich Text-to-Image Generation](https://mlsanity.com/paper/2206.10789/) (2022)
- [Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image](https://mlsanity.com/paper/1607.08128/) (2016)
- [Paint by Word](https://mlsanity.com/paper/2103.10951/) (2021)
- [Perspective (In)consistency of Paint by Text](https://mlsanity.com/paper/2206.14617/) (2022)

## Built on by (most cited first, 30 of 35)

- [The Stable Signature: Rooting Watermarks in Latent Diffusion Models](https://mlsanity.com/paper/2303.15435/) (2023)
- [On the detection of synthetic images generated by diffusion models](https://mlsanity.com/paper/2211.00680/) (2022)
- [Raising the Bar of AI-generated Image Detection with CLIP](https://mlsanity.com/paper/2312.00195/) (2023)
- [AEROBLADE: Training-Free Detection of Latent Diffusion Images Using Autoencoder Reconstruction Error](https://mlsanity.com/paper/2401.17879/) (2024)
- [Intriguing properties of synthetic images: from generative adversarial networks to diffusion models](https://mlsanity.com/paper/2304.06408/) (2023)
- [Towards the Detection of Diffusion Model Deepfakes](https://mlsanity.com/paper/2210.14571/) (2022)
- [Any-Resolution AI-Generated Image Detection by Spectral Learning](https://mlsanity.com/paper/2411.19417/) (2024)
- [Zero-Shot Detection of AI-Generated Images](https://mlsanity.com/paper/2409.15875/) (2024)
- [FakeBench: Probing Explainable Fake Image Detection via Large Multimodal Models](https://mlsanity.com/paper/2404.13306/) (2024)
- [PhyBench: A Physical Commonsense Benchmark for Evaluating Text-to-Image Models](https://mlsanity.com/paper/2406.11802/) (2024)
- [Deep Image Fingerprint: Towards Low Budget Synthetic Image Detection and Model Lineage Analysis](https://mlsanity.com/paper/2303.10762/) (2023)
- [Weakly-supervised deepfake localization in diffusion-generated images](https://mlsanity.com/paper/2311.04584/) (2023)
- [Robust CLIP-Based Detector for Exposing Diffusion Model-Generated Images](https://mlsanity.com/paper/2404.12908/) (2024)
- [Enhancing Diffusion Models with 3D Perspective Geometry Constraints](https://mlsanity.com/paper/2312.00944/) (2023)
- [The Age of Synthetic Realities: Challenges and Opportunities](https://mlsanity.com/paper/2306.11503/) (2023)
- [Characterizing Photorealism and Artifacts in Diffusion Model-Generated Images](https://mlsanity.com/paper/2502.11989/) (2025)
- [Synthetic Image Verification in the Era of Generative AI: What Works and What Isn't There Yet](https://mlsanity.com/paper/2405.00196/) (2024)
- [Survey on AI-Generated Media Detection: From Non-MLLM to MLLM](https://mlsanity.com/paper/2502.05240/) (2025)
- [A Survey on Responsible Generative AI: What to Generate and What Not](https://mlsanity.com/paper/2404.05783/) (2024)
- [NS-Net: Decoupling CLIP Semantic Information through NULL-Space for Generalizable AI-Generated Image Detection](https://mlsanity.com/paper/2508.01248/) (2025)
- [Local Statistics for Generative Image Detection](https://mlsanity.com/paper/2310.16684/) (2023)
- [Synthetic images aid the recognition of human-made art forgeries](https://mlsanity.com/paper/2312.14998/) (2023)
- [Trinity Detector:text-assisted and attention mechanisms based spectral fusion for diffusion generation image detection](https://mlsanity.com/paper/2404.17254/) (2024)
- [Synthetic Photography Detection: A Visual Guidance for Identifying Synthetic Images Created by AI](https://mlsanity.com/paper/2408.06398/) (2024)
- [Diffusion Epistemic Uncertainty with Asymmetric Learning for Diffusion-Generated Image Detection](https://mlsanity.com/paper/2601.14625/) (2026)
- [Where's the liability in the Generative Era? Recovery-based Black-Box Detection of AI-Generated Content](https://mlsanity.com/paper/2505.01008/) (2025)
- [PRADA: Probability-Ratio-Based Attribution and Detection of Autoregressive-Generated Images](https://mlsanity.com/paper/2511.20068/) (2025)
- [A parameter-efficient three-branch architecture for multimodal misinformation detection with limited annotations](https://mlsanity.com/paper/2512.20257/) (2025)
- [Fake3DGS: A Benchmark for 3D Manipulation Detection in Neural Rendering](https://mlsanity.com/paper/2604.27590/) (2026)
- [Shedding Light: A Benchmark for Evaluating Lighting Understanding in Generative Image Models](https://mlsanity.com/paper/2609.10787/) (2026)

## Abstract (arXiv)

Whereas generative adversarial networks are capable of synthesizing highly realistic images of faces, cats, landscapes, or almost any other single category, paint-by-text synthesis engines can -- from a single text prompt -- synthesize realistic images of seemingly endless categories with arbitrary configurations and combinations. This powerful technology poses new challenges to the photo-forensic community. Motivated by the fact that paint by text is not based on explicit geometric or physical models, and the human visual system's general insensitivity to lighting inconsistencies, we provide an initial exploration of the lighting consistency of DALL-E-2 synthesized images to determine if physics-based forensic analyses will prove fruitful in detecting this new breed of synthetic media.