# Qualitative Failures of Image Generation Models and Their Application in Detecting Deepfakes

arXiv: https://arxiv.org/abs/2304.06470 · HTML: https://mlsanity.com/paper/2304.06470/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 39 references that are in the map.
- First posted on arXiv 29 Mar 2023.

## Builds on (most cited first, 25 of 25)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (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)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Scaling Autoregressive Models for Content-Rich Text-to-Image Generation](https://mlsanity.com/paper/2206.10789/) (2022)
- [CNN-generated images are surprisingly easy to spot... for now](https://mlsanity.com/paper/1912.11035/) (2019)
- [MesoNet: a Compact Facial Video Forgery Detection Network](https://mlsanity.com/paper/1809.00888/) (2018)
- [Assessing Generative Models via Precision and Recall](https://mlsanity.com/paper/1806.00035/) (2018)
- [DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models](https://mlsanity.com/paper/2210.14896/) (2022)
- [Exposing DeepFake Videos By Detecting Face Warping Artifacts](https://mlsanity.com/paper/1811.00656/) (2018)
- [Pros and Cons of GAN Evaluation Measures](https://mlsanity.com/paper/1802.03446/) (2018)
- [Media Forensics and DeepFakes: an overview](https://mlsanity.com/paper/2001.06564/) (2020)
- [A Categorical Archive of ChatGPT Failures](https://mlsanity.com/paper/2302.03494/) (2023)
- [Detecting GAN generated Fake Images using Co-occurrence Matrices](https://mlsanity.com/paper/1903.06836/) (2019)
- [Pros and Cons of GAN Evaluation Measures: New Developments](https://mlsanity.com/paper/2103.09396/) (2021)
- [ForensicTransfer: Weakly-supervised Domain Adaptation for Forgery Detection](https://mlsanity.com/paper/1812.02510/) (2018)
- [Deep Learning for Deepfakes Creation and Detection: A Survey](https://mlsanity.com/paper/1909.11573/) (2019)
- [A very preliminary analysis of DALL-E 2](https://mlsanity.com/paper/2204.13807/) (2022)
- [Generated Faces in the Wild: Quantitative Comparison of Stable Diffusion, Midjourney and DALL-E 2](https://mlsanity.com/paper/2210.00586/) (2022)
- [Perspective (In)consistency of Paint by Text](https://mlsanity.com/paper/2206.14617/) (2022)
- [Statistics of Deep Generated Images](https://mlsanity.com/paper/1708.02688/) (2017)
- [Large Scale Qualitative Evaluation of Generative Image Model Outputs](https://mlsanity.com/paper/2301.04518/) (2023)

## Built on by (most cited first, 30 of 31)

- [Understanding Hallucinations in Diffusion Models through Mode Interpolation](https://mlsanity.com/paper/2406.09358/) (2024)
- [Detecting Multimedia Generated by Large AI Models: A Survey](https://mlsanity.com/paper/2402.00045/) (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)
- [A Survey of Multimodal Hallucination Evaluation and Detection](https://mlsanity.com/paper/2507.19024/) (2025)
- [Robust CLIP-Based Detector for Exposing Diffusion Model-Generated Images](https://mlsanity.com/paper/2404.12908/) (2024)
- [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)
- [Mitigating Hallucinations in Diffusion Models through Adaptive Attention Modulation](https://mlsanity.com/paper/2502.16872/) (2025)
- [Towards Understanding Text Hallucination of Diffusion Models via Local Generation Bias](https://mlsanity.com/paper/2503.03595/) (2025)
- [RAGDiffusion: Faithful Cloth Generation via External Knowledge Assimilation](https://mlsanity.com/paper/2411.19528/) (2024)
- [AVTENet: A Human-Cognition-Inspired Audio-Visual Transformer-Based Ensemble Network for Video Deepfake Detection](https://mlsanity.com/paper/2310.13103/) (2023)
- [Creativity in AI: Progresses and Challenges](https://mlsanity.com/paper/2410.17218/) (2024)
- [Counting Hallucinations in Diffusion Models](https://mlsanity.com/paper/2510.13080/) (2025)
- [Repairing Catastrophic-Neglect in Text-to-Image Diffusion Models via Attention-Guided Feature Enhancement](https://mlsanity.com/paper/2406.16272/) (2024)
- [Mitigating Diffusion Model Hallucinations with Dynamic Guidance](https://mlsanity.com/paper/2510.05356/) (2025)
- [Beyond Artificial Misalignment: Detecting and Grounding Semantic-Coordinated Multimodal Manipulations](https://mlsanity.com/paper/2509.12653/) (2025)
- [Synthetic Photography Detection: A Visual Guidance for Identifying Synthetic Images Created by AI](https://mlsanity.com/paper/2408.06398/) (2024)
- [RODS: Robust Optimization Inspired Diffusion Sampling for Detecting and Reducing Hallucination in Generative Models](https://mlsanity.com/paper/2507.12201/) (2025)
- [A Difference-in-Difference Approach to Detecting AI-Generated Images](https://mlsanity.com/paper/2602.23732/) (2026)
- [Interactive Visual Assessment for Text-to-Image Generation Models](https://mlsanity.com/paper/2411.15509/) (2024)
- [A Practical Synthesis of Detecting AI-Generated Textual, Visual, and Audio Content](https://mlsanity.com/paper/2504.02898/) (2025)
- [The Art That Poses Back: Assessing AI Pastiches after Contemporary Artworks](https://mlsanity.com/paper/2603.06324/) (2026)
- [SMAL-pets: SMAL Based Avatars of Pets from Single Image](https://mlsanity.com/paper/2603.17131/) (2026)
- [SalArt-VQA: Diagnosing Whether VLMs Understand Salient Artifacts in Generated Images](https://mlsanity.com/paper/2606.12671/) (2026)
- [FLORIDA: Fake-looking Real Images Dataset](https://mlsanity.com/paper/2311.10931/) (2023)
- [Beyond Anonymization: Object Scrubbing for Privacy-Preserving 2D and 3D Vision Tasks](https://mlsanity.com/paper/2504.16557/) (2025)
- [Enhancing AI Face Realism: Cost-Efficient Quality Improvement in Distilled Diffusion Models with a Fully Synthetic Dataset](https://mlsanity.com/paper/2505.02255/) (2025)
- [Robustness in AI-Generated Detection: Enhancing Resistance to Adversarial Attacks](https://mlsanity.com/paper/2505.03435/) (2025)
- [AI-Generated Images: What Humans and Machines See When They Look at the Same Image](https://mlsanity.com/paper/2605.06143/) (2026)

## Abstract (arXiv)

The ability of image and video generation models to create photorealistic images has reached unprecedented heights, making it difficult to distinguish between real and fake images in many cases. However, despite this progress, a gap remains between the quality of generated images and those found in the real world. To address this, we have reviewed a vast body of literature from both academic publications and social media to identify qualitative shortcomings in image generation models, which we have classified into five categories. By understanding these failures, we can identify areas where these models need improvement, as well as develop strategies for detecting deep fakes. The prevalence of deep fakes in today's society is a serious concern, and our findings can help mitigate their negative impact.