mlsanityData to 14 Oct 2026

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

arXiv 2304.06470 ↗First posted 29 Mar 2023cs.CV cs.AIcited by 31

Not on the map. Why?

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.

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

25 of 39 references.

References · 25

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  3. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  4. 2022Generative Adversarial Networkscited by 5,627
  5. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  6. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  7. 2016Improved Techniques for Training GANscited by 2,970
  8. 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,295
  9. 2019CNN-generated images are surprisingly easy to spot... for nowcited by 847
  10. 2018MesoNet: a Compact Facial Video Forgery Detection Networkcited by 409
  11. 2018Assessing Generative Models via Precision and Recallcited by 406
  12. 2022DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Modelscited by 379
13 more
  1. 2018Exposing DeepFake Videos By Detecting Face Warping Artifactscited by 319
  2. 2018Pros and Cons of GAN Evaluation Measurescited by 224
  3. 2020Media Forensics and DeepFakes: an overviewcited by 209
  4. 2023A Categorical Archive of ChatGPT Failurescited by 168
  5. 2019Detecting GAN generated Fake Images using Co-occurrence Matricescited by 124
  6. 2021Pros and Cons of GAN Evaluation Measures: New Developmentscited by 123
  7. 2018ForensicTransfer: Weakly-supervised Domain Adaptation for Forgery Detectioncited by 104
  8. 2019Deep Learning for Deepfakes Creation and Detection: A Surveycited by 102
  9. 2022A very preliminary analysis of DALL-E 2cited by 82
  10. 2022Generated Faces in the Wild: Quantitative Comparison of Stable Diffusion, Midjourney and DALL-E 2cited by 55
  11. 2022Perspective (In)consistency of Paint by Textcited by 34
  12. 2017Statistics of Deep Generated Imagescited by 4
  13. 2023Large Scale Qualitative Evaluation of Generative Image Model Outputscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 10; 2025: 12; 2026: 6.

31 papers.

Sort:

By area:

  1. 2024Understanding Hallucinations in Diffusion Models through Mode Interpolationcited by 91
  2. 2024Detecting Multimedia Generated by Large AI Models: A Surveycited by 76
  3. 2024FakeBench: Probing Explainable Fake Image Detection via Large Multimodal Modelscited by 36
  4. 2024PhyBench: A Physical Commonsense Benchmark for Evaluating Text-to-Image Modelscited by 36
  5. 2025A Survey of Multimodal Hallucination Evaluation and Detectioncited by 27
  6. 2024Robust CLIP-Based Detector for Exposing Diffusion Model-Generated Imagescited by 20
  7. 2023The Age of Synthetic Realities: Challenges and Opportunitiescited by 15
  8. 2025Characterizing Photorealism and Artifacts in Diffusion Model-Generated Imagescited by 14
  9. 2025Mitigating Hallucinations in Diffusion Models through Adaptive Attention Modulationcited by 11
  10. 2025Towards Understanding Text Hallucination of Diffusion Models via Local Generation Biascited by 11
  11. 2024RAGDiffusion: Faithful Cloth Generation via External Knowledge Assimilationcited by 9
  12. 2023AVTENet: A Human-Cognition-Inspired Audio-Visual Transformer-Based Ensemble Network for Video Deepfake Detectioncited by 8
19 more
  1. 2024Creativity in AI: Progresses and Challengescited by 7
  2. 2025Counting Hallucinations in Diffusion Modelscited by 6
  3. 2024Repairing Catastrophic-Neglect in Text-to-Image Diffusion Models via Attention-Guided Feature Enhancementcited by 5
  4. 2025Mitigating Diffusion Model Hallucinations with Dynamic Guidancecited by 5
  5. 2025Beyond Artificial Misalignment: Detecting and Grounding Semantic-Coordinated Multimodal Manipulationscited by 4
  6. 2024Synthetic Photography Detection: A Visual Guidance for Identifying Synthetic Images Created by AIcited by 3
  7. 2025RODS: Robust Optimization Inspired Diffusion Sampling for Detecting and Reducing Hallucination in Generative Modelscited by 3
  8. 2026A Difference-in-Difference Approach to Detecting AI-Generated Imagescited by 2
  9. 2024Interactive Visual Assessment for Text-to-Image Generation Modelscited by 1
  10. 2025A Practical Synthesis of Detecting AI-Generated Textual, Visual, and Audio Contentcited by 1
  11. 2026The Art That Poses Back: Assessing AI Pastiches after Contemporary Artworkscited by 1
  12. 2026SMAL-pets: SMAL Based Avatars of Pets from Single Imagecited by 1
  13. 2026SalArt-VQA: Diagnosing Whether VLMs Understand Salient Artifacts in Generated Imagescited by 1
  14. 2023FLORIDA: Fake-looking Real Images Datasetcited by 0
  15. 2025Beyond Anonymization: Object Scrubbing for Privacy-Preserving 2D and 3D Vision Taskscited by 0
  16. 2025Enhancing AI Face Realism: Cost-Efficient Quality Improvement in Distilled Diffusion Models with a Fully Synthetic Datasetcited by 0
  17. 2025Robustness in AI-Generated Detection: Enhancing Resistance to Adversarial Attackscited by 0
  18. 2026AI-Generated Images: What Humans and Machines See When They Look at the Same Imagecited by 0
  19. 2026RAGDiffusion++: From Macro-Retrieval to Micro-Fidelity Alignment for Garment Generationcited by 0