mlsanityData to 7 Oct 2026

DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models

arXiv 2210.14896 ↗First posted 26 Oct 2022cs.CV cs.AI cs.HCcited by 376

On the map: Diffusion models → Image generation, text-to-image and editing

Abstract (arXiv)

With recent advancements in diffusion models, users can generate high-quality images by writing text prompts in natural language. However, generating images with desired details requires proper prompts, and it is often unclear how a model reacts to different prompts or what the best prompts are. To help researchers tackle these critical challenges, we introduce DiffusionDB, the first large-scale text-to-image prompt dataset totaling 6.5TB, containing 14 million images generated by Stable Diffusion, 1.8 million unique prompts, and hyperparameters specified by real users. We analyze the syntactic and semantic characteristics of prompts. We pinpoint specific hyperparameter values and prompt styles that can lead to model errors and present evidence of potentially harmful model usage, such as the generation of misinformation. The unprecedented scale and diversity of this human-actuated dataset provide exciting research opportunities in understanding the interplay between prompts and generative models, detecting deepfakes, and designing human-AI interaction tools to help users more easily use these models. DiffusionDB is publicly available at: https://poloclub.github.io/diffusiondb.

Key facts. Cited by 376 papers in the map (data through 7 Oct 2026). Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models. Builds on 24 of its 57 references that are in the map. First posted on arXiv 26 Oct 2022.

Builds on

24 of 57 references.

Closest ancestors · 3

Same direction, newest first

  1. 2022Best Prompts for Text-to-Image Models and How to Find Them23 Sep
  2. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding23 May
  3. 2022Hierarchical Text-Conditional Image Generation with CLIP Latents13 Apr

Other references · 21

  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. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  4. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  5. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  6. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,841
  7. 2022Imagen Video: High Definition Video Generation with Diffusion Modelscited by 1,765
  8. 2018Datasheets for Datasetscited by 1,371
  9. 2021Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivitycited by 1,122
  10. 2016Bag of Tricks for Efficient Text Classificationcited by 869
  11. 2021Learning To Retrieve Prompts for In-Context Learningcited by 641
  12. 2021Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigmcited by 599
9 more
  1. 2022PromptSource: An Integrated Development Environment and Repository for Natural Language Promptscited by 288
  2. 2020The Creation and Detection of Deepfakes: A Surveycited by 246
  3. 2021Design Guidelines for Prompt Engineering Text-to-Image Generative Modelscited by 216
  4. 2018DeepFakes: a New Threat to Face Recognition? Assessment and Detectioncited by 208
  5. 2018Explaining Explanations in AIcited by 136
  6. 2022Adapting Pretrained Vision-Language Foundational Models to Medical Imaging Domainscited by 85
  7. 2022Interactive and Visual Prompt Engineering for Ad-hoc Task Adaptation with Large Language Modelscited by 70
  8. 2022Generated Faces in the Wild: Quantitative Comparison of Stable Diffusion, Midjourney and DALL-E 2cited by 55
  9. 2022A Taxonomy of Prompt Modifiers for Text-To-Image Generationcited by 54

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 68; 2024: 132; 2025: 105; 2026: 69.

376 papers.

Sort:

By area:

  1. 2023ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generationcited by 1,010
  2. 2023Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generationcited by 950
  3. 2023Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesiscited by 847
  4. 2023Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Modelscited by 696
  5. 2023Directly Fine-Tuning Diffusion Models on Differentiable Rewardscited by 431
  6. 2024MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmarkcited by 362
  7. 2023GenImage: A Million-Scale Benchmark for Detecting AI-Generated Imagecited by 318
  8. 2024Open-Sora Plan: Open-Source Large Video Generation Modelcited by 286
  9. 2023Human Preference Score: Better Aligning Text-to-Image Models with Human Preferencecited by 284
  10. 2023Understanding and Mitigating Copying in Diffusion Modelscited by 205
  11. 2022Optimizing Prompts for Text-to-Image Generationcited by 204
  12. 2023JourneyDB: A Benchmark for Generative Image Understandingcited by 203
38 more
  1. 2024A Sanity Check for AI-generated Image Detectioncited by 187
  2. 2023Power Hungry Processing: Watts Driving the Cost of AI Deployment?cited by 186
  3. 2023Making LLaMA SEE and Draw with SEED Tokenizercited by 184
  4. 2023MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learningcited by 171
  5. 2023Davidsonian Scene Graph: Improving Reliability in Fine-grained Evaluation for Text-to-Image Generationcited by 159
  6. 2023AGIQA-3K: An Open Database for AI-Generated Image Quality Assessmentcited by 142
  7. 2023Re-imagine the Negative Prompt Algorithm: Transform 2D Diffusion into 3D, alleviate Janus problem and Beyondcited by 139
  8. 2023Invisible Image Watermarks Are Provably Removable Using Generative AIcited by 124
  9. 2024VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Modelscited by 124
  10. 2023Receler: Reliable Concept Erasing of Text-to-Image Diffusion Models via Lightweight Eraserscited by 118
  11. 2024ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimizationcited by 115
  12. 2023Navigating Text-To-Image Customization: From LyCORIS Fine-Tuning to Model Evaluationcited by 108
  13. 2024Learning Multi-dimensional Human Preference for Text-to-Image Generationcited by 102
  14. 2023BOOT: Data-free Distillation of Denoising Diffusion Models with Bootstrappingcited by 96
  15. 2025Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridgingcited by 95
  16. 2023HRS-Bench: Holistic, Reliable and Scalable Benchmark for Text-to-Image Modelscited by 94
  17. 2023Leaving Reality to Imagination: Robust Classification via Generated Datasetscited by 91
  18. 2023Finetuning Text-to-Image Diffusion Models for Fairnesscited by 90
  19. 2024WAVES: Benchmarking the Robustness of Image Watermarkscited by 89
  20. 2024DeMamba: AI-Generated Video Detection on Million-Scale GenVideo Benchmarkcited by 85
  21. 2023Divide & Bind Your Attention for Improved Generative Semantic Nursingcited by 80
  22. 2023Generating images of rare concepts using pre-trained diffusion modelscited by 78
  23. 2023A-STAR: Test-time Attention Segregation and Retention for Text-to-image Synthesiscited by 78
  24. 2024Large-scale Reinforcement Learning for Diffusion Modelscited by 78
  25. 2023ImagenHub: Standardizing the evaluation of conditional image generation modelscited by 75
  26. 2024Detecting Multimedia Generated by Large AI Models: A Surveycited by 73
  27. 2024Not All Noises Are Created Equally:Diffusion Noise Selection and Optimizationcited by 70
  28. 2023Promptify: Text-to-Image Generation through Interactive Prompt Exploration with Large Language Modelscited by 67
  29. 2024Survey of Bias In Text-to-Image Generation: Definition, Evaluation, and Mitigationcited by 66
  30. 2023AntifakePrompt: Prompt-Tuned Vision-Language Models are Fake Image Detectorscited by 64
  31. 2024AesBench: An Expert Benchmark for Multimodal Large Language Models on Image Aesthetics Perceptioncited by 63
  32. 2025Safety at Scale: A Comprehensive Survey of Large Model and Agent Safetycited by 63
  33. 2024PromptCharm: Text-to-Image Generation through Multi-modal Prompting and Refinementcited by 61
  34. 2024FakeInversion: Learning to Detect Images from Unseen Text-to-Image Models by Inverting Stable Diffusioncited by 61
  35. 2023PromptMagician: Interactive Prompt Engineering for Text-to-Image Creationcited by 58
  36. 2023DreamSync: Aligning Text-to-Image Generation with Image Understanding Feedbackcited by 57
  37. 2023CONFORM: Contrast is All You Need For High-Fidelity Text-to-Image Diffusion Modelscited by 54
  38. 2023TIBET: Identifying and Evaluating Biases in Text-to-Image Generative Modelscited by 51

50 most cited of 376 All 376 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023Prompt-Free Diffusion: Taking "Text" out of Text-to-Image Diffusion Models
  2. 2023Prompting Hard or Hardly Prompting: Prompt Inversion for Text-to-Image Diffusion Models
  3. 2023Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts
  4. 2025Reusing Computation in Text-to-Image Diffusion for Efficient Generation of Image Sets
  5. 2025Decoder-Only LLMs are Better Controllers for Diffusion Models
  6. 2025Text-to-Image Diffusion Models Cannot Count, and Prompt Refinement Cannot Help
  7. 2023LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models
  8. 2024Prompt Diffusion Robustifies Any-Modality Prompt Learning