mlsanityData to 7 Oct 2026

RePrompt: Automatic Prompt Editing to Refine AI-Generative Art Towards Precise Expressions

arXiv 2302.09466 ↗First posted 19 Feb 2023cs.HC cs.AIcited by 43

Not on the map. Why?

Abstract (arXiv)

Generative AI models have shown impressive ability to produce images with text prompts, which could benefit creativity in visual art creation and self-expression. However, it is unclear how precisely the generated images express contexts and emotions from the input texts. We explored the emotional expressiveness of AI-generated images and developed RePrompt, an automatic method to refine text prompts toward precise expression of the generated images. Inspired by crowdsourced editing strategies, we curated intuitive text features, such as the number and concreteness of nouns, and trained a proxy model to analyze the feature effects on the AI-generated image. With model explanations of the proxy model, we curated a rubric to adjust text prompts to optimize image generation for precise emotion expression. We conducted simulation and user studies, which showed that RePrompt significantly improves the emotional expressiveness of AI-generated images, especially for negative emotions.

Key facts. Cited by 43 papers in the map (data through 7 Oct 2026). Builds on 44 of its 99 references that are in the map. First posted on arXiv 19 Feb 2023.

Builds on

44 of 99 references.

References · 44

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  5. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  6. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  7. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  8. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  9. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,120
  10. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  11. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,878
  12. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,848
32 more
  1. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  2. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  3. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  4. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  5. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  6. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,388
  7. 2021Learning to Prompt for Vision-Language Modelscited by 2,269
  8. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,222
  9. 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,065
  10. 2022Exploring CLIP for Assessing the Look and Feel of Imagescited by 974
  11. 2019How Can We Know What Language Models Know?cited by 953
  12. 2021Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigmcited by 599
  13. 2020Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performancecited by 396
  14. 2022VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidancecited by 285
  15. 2021AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Promptscited by 265
  16. 2020AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Promptscited by 246
  17. 2021Design Guidelines for Prompt Engineering Text-to-Image Generative Modelscited by 216
  18. 2021Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Littlecited by 176
  19. 2020A Theory of Usable Information Under Computational Constraintscited by 153
  20. 2016Photo Aesthetics Ranking Network with Attributes and Content Adaptationcited by 122
  21. 2016Building a Large Scale Dataset for Image Emotion Recognition: The Fine Print and The Benchmarkcited by 71
  22. 2022Interactive and Visual Prompt Engineering for Ad-hoc Task Adaptation with Large Language Modelscited by 70
  23. 2016Scalable Bayesian Rule Listscited by 64
  24. 2022CLIPasso: Semantically-Aware Object Sketchingcited by 57
  25. 2022Personalized Image Aesthetics Assessment with Rich Attributescited by 56
  26. 2020Towards Persona-Based Empathetic Conversational Modelscited by 53
  27. 2021What Context Features Can Transformer Language Models Use?cited by 49
  28. 2022Opal: Multimodal Image Generation for News Illustrationcited by 36
  29. 2021Directed Diversity: Leveraging Language Embedding Distances for Collective Creativity in Crowd Ideationcited by 23
  30. 2022Empathetic Conversational Systems: A Review of Current Advances, Gaps, and Opportunitiescited by 14
  31. 2021Interpretable Directed Diversity: Leveraging Model Explanations for Iterative Crowd Ideationcited by 12
  32. 2021AffectGAN: Affect-Based Generative Art Driven by Semanticscited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 10; 2024: 13; 2025: 10; 2026: 10.

43 papers.

Sort:

By area:

  1. 2023Promptify: Text-to-Image Generation through Interactive Prompt Exploration with Large Language Modelscited by 67
  2. 2024PromptCharm: Text-to-Image Generation through Multi-modal Prompting and Refinementcited by 61
  3. 2023PromptMagician: Interactive Prompt Engineering for Text-to-Image Creationcited by 58
  4. 2023PromptPaint: Steering Text-to-Image Generation Through Paint Medium-like Interactionscited by 34
  5. 2024Alignment of Diffusion Models: Fundamentals, Challenges, and Futurecited by 34
  6. 2023ConstitutionMaker: Interactively Critiquing Large Language Models by Converting Feedback into Principlescited by 33
  7. 2023Generative Disco: Text-to-Video Generation for Music Visualizationcited by 19
  8. 2023A Data Perspective on Enhanced Identity Preservation for Diffusion Personalizationcited by 18
  9. 2024Designing for Human-Agent Alignment: Understanding what humans want from their agentscited by 18
  10. 2023ABScribe: Rapid Exploration & Organization of Multiple Writing Variations in Human-AI Co-Writing Tasks using Large Language Modelscited by 17
  11. 2025Generative AI for Film Creation: A Survey of Recent Advancescited by 17
  12. 2024Human-Guided Image Generation for Expanding Small-Scale Training Image Datasetscited by 10
31 more
  1. 2025AI with Emotions: Exploring Emotional Expressions in Large Language Modelscited by 10
  2. 2023Prompt Evolution for Generative AI: A Classifier-Guided Approachcited by 9
  3. 2024Noise Diffusion for Enhancing Semantic Faithfulness in Text-to-Image Synthesiscited by 9
  4. 2025PromptMap: An Alternative Interaction Style for AI-Based Image Generationcited by 8
  5. 2024A User-Friendly Framework for Generating Model-Preferred Prompts in Text-to-Image Synthesiscited by 7
  6. 2025VisualPrompter: Semantic-Aware Prompt Optimization with Visual Feedback for Text-to-Image Synthesiscited by 6
  7. 2024A Human-Computer Collaborative Tool for Training a Single Large Language Model Agent into a Network through Few Examplescited by 5
  8. 2025GenTune: Toward Traceable Prompts to Improve Controllability of Image Refinement in Environment Designcited by 5
  9. 2024"When He Feels Cold, He Goes to the Seahorse"-Blending Generative AI into Multimaterial Storymaking for Family Expressive Arts Therapycited by 3
  10. 2024A Preliminary Exploration of YouTubers' Use of Generative-AI in Content Creationcited by 3
  11. 2024CodeCloak: A Method for Evaluating and Mitigating Code Leakage by LLM Code Assistantscited by 3
  12. 2024From Fake Perfects to Conversational Imperfects: Exploring Image-Generative AI as a Boundary Object for Participatory Design of Public Spacescited by 3
  13. 2025Asynchronous Denoising Diffusion Models for Aligning Text-to-Image Generationcited by 3
  14. 2024Enabling Generative Design Tools with LLM Agents for Mechanical Computation Devices: A Case Studycited by 2
  15. 2025On the Design and Evaluation of Human-centered Explainable AI Systems: A Systematic Review and Taxonomycited by 2
  16. 2026EmoStyle: Affective Conditioning of Style-Specialist Experts for Emotional Image Generationcited by 2
  17. 2023Detecting Spurious Correlations via Robust Visual Concepts in Real and AI-Generated Image Classificationcited by 1
  18. 2023The Contemporary Art of Image Search: Iterative User Intent Expansion via Vision-Language Modelcited by 1
  19. 2024POEM: Interactive Prompt Optimization for Enhancing Multimodal Reasoning of Large Language Modelscited by 1
  20. 2025"Shall We Dig Deeper?": Designing and Evaluating Strategies for LLM Agents to Advance Knowledge Co-Construction in Asynchronous Online Discussionscited by 1
  21. 2025AnimAgents: Coordinating Multi-Stage Animation Pre-Production with Human-Multi-Agent Collaborationcited by 1
  22. 2026ScribbleSense: Generative Scribble-Based Texture Editing with Intent Predictioncited by 1
  23. 2026Face-Guided Sentiment Boundary Enhancement for Weakly-Supervised Temporal Sentiment Localizationcited by 1
  24. 2026Auditing and Controlling AI Agent Actions in Spreadsheetscited by 1
  25. 2026EPIG: Emotion-Based Prompting for Personalised Image Generationcited by 1
  26. 2026One Rewrite to Fix Them All? Type-Aware Repair Allocation for Text-to-Image Prompt Optimizationcited by 1
  27. 2025IPGO: Indirect Prompt Gradient Optimization for Parameter-Efficient Prompt-level Fine-Tuning on Text-to-Image Modelscited by 0
  28. 2026PromptHelper: A Prompt Recommender System for Encouraging Creativity in AI Chatbot Interactionscited by 0
  29. 2026SketchXplain: Intuitive Visual Explanations of Image Classifiers with Sketchescited by 0
  30. 2026Beyond Emotion Prompts: Fine-Grained Text-to-Image Generation Driven by Valence-Arousal-Dominancecited by 0
  31. 2026PE-OPSD: Internalizing Prompt Enhancement into Flow-matching Models via On-Policy Self-Distillationcited by 0