mlsanityData to 7 Oct 2026

Analyzing Quality, Bias, and Performance in Text-to-Image Generative Models

arXiv 2407.00138 ↗First posted 28 Jun 2024cs.AI cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

Advances in generative models have led to significant interest in image synthesis, demonstrating the ability to generate high-quality images for a diverse range of text prompts. Despite this progress, most studies ignore the presence of bias. In this paper, we examine several text-to-image models not only by qualitatively assessing their performance in generating accurate images of human faces, groups, and specified numbers of objects but also by presenting a social bias analysis. As expected, models with larger capacity generate higher-quality images. However, we also document the inherent gender or social biases these models possess, offering a more complete understanding of their impact and limitations.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 40 of its 57 references that are in the map. First posted on arXiv 28 Jun 2024.

Builds on

40 of 57 references.

References · 40

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  5. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  6. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  7. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  8. 2016Improved Techniques for Training GANscited by 2,938
  9. 2015Show, Attend and Tell: Neural Image Caption Generation with Visual Attentioncited by 1,421
  10. 2015Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Modelscited by 1,352
  11. 2017Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answeringcited by 1,310
  12. 2018Demystifying MMD GANscited by 1,268
28 more
  1. 2014Deep Visual-Semantic Alignments for Generating Image Descriptionscited by 966
  2. 2016Semantics derived automatically from language corpora contain human-like biasescited by 894
  3. 2014Show and Tell: A Neural Image Caption Generatorcited by 877
  4. 2018Self-Attention Generative Adversarial Networkscited by 809
  5. 2017AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networkscited by 664
  6. 2017Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraintscited by 420
  7. 2018Assessing Generative Models via Precision and Recallcited by 401
  8. 2017Are GANs Created Equal? A Large-Scale Studycited by 267
  9. 2018Women also Snowboard: Overcoming Bias in Captioning Modelscited by 236
  10. 2018A Note on the Inception Scorecited by 225
  11. 2023Holistic Evaluation of Text-To-Image Modelscited by 160
  12. 2021LAFITE: Towards Language-Free Training for Text-to-Image Generationcited by 126
  13. 2022ERNIE-ViLG 2.0: Improving Text-to-Image Diffusion Model with Knowledge-Enhanced Mixture-of-Denoising-Expertscited by 110
  14. 2020Image Representations Learned With Unsupervised Pre-Training Contain Human-like Biasescited by 107
  15. 2022How well can Text-to-Image Generative Models understand Ethical Natural Language Interventions?cited by 92
  16. 2019Semantic Object Accuracy for Generative Text-to-Image Synthesiscited by 89
  17. 2024Survey of Bias In Text-to-Image Generation: Definition, Evaluation, and Mitigationcited by 66
  18. 2024OpenBias: Open-set Bias Detection in Text-to-Image Generative Modelscited by 61
  19. 2022Generated Faces in the Wild: Quantitative Comparison of Stable Diffusion, Midjourney and DALL-E 2cited by 55
  20. 2021Worst of Both Worlds: Biases Compound in Pre-trained Vision-and-Language Modelscited by 52
  21. 2024Revisiting Text-to-Image Evaluation with Gecko: On Metrics, Prompts, and Human Ratingscited by 44
  22. 2023Multimodal Procedural Planning via Dual Text-Image Promptingcited by 40
  23. 2023T2IAT: Measuring Valence and Stereotypical Biases in Text-to-Image Generationcited by 39
  24. 2019Exposing and Correcting the Gender Bias in Image Captioning Datasets and Modelscited by 36
  25. 2020Imperfect ImaGANation: Implications of GANs Exacerbating Biases on Facial Data Augmentation and Snapchat Selfie Lensescited by 27
  26. 2023TIAM -- A Metric for Evaluating Alignment in Text-to-Image Generationcited by 18
  27. 2022Inherent Limitations of AI Fairnesscited by 12
  28. 2023Generating Synthetic Datasets by Interpolating along Generalized Geodesicscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 3; 2026: 2.

9 papers.

  1. 2024PAK-UCB Contextual Bandit: An Online Learning Approach to Prompt-Aware Selection of Generative Models and LLMscited by 11
  2. 2024Gender Bias in Text-to-Video Generation Models: A case study of Soracited by 8
  3. 2025Religious Bias Landscape in Language and Text-to-Image Models: Analysis, Detection, and Debiasing Strategiescited by 8
  4. 2024Data Pruning in Generative Diffusion Modelscited by 3
  5. 2025Hidden Bias in the Machine: Stereotypes in Text-to-Image Modelscited by 2
  6. 2024Implicit Priors Editing in Stable Diffusion via Targeted Token Adjustmentcited by 1
  7. 2025Text-to-Image Models and Their Representation of People from Different Nationalities Engaging in Activitiescited by 0
  8. 2026GLEaN: A Text-to-image Bias Detection Approach for Public Comprehensioncited by 0
  9. 2026KG-FairDiff: Knowledge Graph-Guided Prompt Refinement for Demographically Fair Text-to-Image Generationcited by 0