mlsanityData to 7 Oct 2026

Na"ive PAINE: Lightweight Text-to-Image Generation Improvement with Prompt Evaluation

arXiv 2603.12506 ↗First posted 12 Mar 2026cs.CV cs.AI cs.LGcited by 0

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

Abstract (arXiv)

Text-to-Image (T2I) generation is primarily driven by Diffusion Models (DM) which rely on random Gaussian noise. Thus, like playing the slots at a casino, a DM will produce different results given the same user-defined inputs. This imposes a gambler's burden: To perform multiple generation cycles to obtain a satisfactory result. However, even though DMs use stochastic sampling to seed generation, the distribution of generated content quality highly depends on the prompt and the generative ability of a DM with respect to it. To account for this, we propose Na"ive PAINE for improving the generative quality of Diffusion Models by leveraging T2I preference benchmarks. We directly predict the numerical quality of an image from the initial noise and given prompt. Na"ive PAINE then selects a handful of quality noises and forwards them to the DM for generation. Further, Na"ive PAINE provides feedback on the DM generative quality given the prompt and is lightweight enough to seamlessly fit into existing DM pipelines. Experimental results demonstrate that Na"ive PAINE outperforms existing approaches on several prompt corpus benchmarks.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models. Builds on 63 of its 90 references that are in the map. First posted on arXiv 12 Mar 2026.

Builds on

63 of 90 references.

Closest ancestors · 15

Same direction, newest first

  1. 2026RAISE: Requirement-Adaptive Evolutionary Refinement for Training-Free Text-to-Image Alignment28 Feb
  2. 2025SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation12 Mar
  3. 2025Characterizing Photorealism and Artifacts in Diffusion Model-Generated Images17 Feb
  4. 2024PixelMan: Consistent Object Editing with Diffusion Models via Pixel Manipulation and Generation18 Dec
  5. 2024Zigzag Diffusion Sampling: Diffusion Models Can Self-Improve via Self-Reflection14 Dec
  6. 2024HART: Efficient Visual Generation with Hybrid Autoregressive Transformer14 Oct
  7. 2024FRAP: Faithful and Realistic Text-to-Image Generation with Adaptive Prompt Weighting21 Aug
  8. 2024Good Seed Makes a Good Crop: Discovering Secret Seeds in Text-to-Image Diffusion Models23 May
  9. 2024Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding14 May
  10. 2024InitNO: Boosting Text-to-Image Diffusion Models via Initial Noise Optimization6 Apr
  11. 2024Towards Effective Usage of Human-Centric Priors in Diffusion Models for Text-based Human Image Generation8 Mar
  12. 2023GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment17 Oct
3 more
  1. 2023Adding Conditional Control to Text-to-Image Diffusion Models10 Feb
  2. 2023Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models31 Jan
  3. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding23 May

Other references · 48

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  5. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  6. 2020Denoising Diffusion Implicit Modelscited by 9,655
  7. 2022Scalable Diffusion Models with Transformerscited by 5,931
  8. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,290
  9. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  10. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  11. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,388
  12. 2023Consistency Modelscited by 1,778
36 more
  1. 2025s1: Simple test-time scalingcited by 1,311
  2. 2019An Introduction to Variational Autoencoderscited by 997
  3. 2023Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generationcited by 950
  4. 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesiscited by 854
  5. 2023Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesiscited by 847
  6. 2023Adversarial Diffusion Distillationcited by 741
  7. 2021BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstructioncited by 464
  8. 2024PixArt-Sigma: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generationcited by 326
  9. 2024The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bitscited by 289
  10. 2023Q-Diffusion: Quantizing Diffusion Modelscited by 266
  11. 2025Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformercited by 247
  12. 2020Fast Differentiable Sorting and Rankingcited by 196
  13. 2025HPSv3: Towards Wide-Spectrum Human Preference Scorecited by 196
  14. 2023PTQD: Accurate Post-Training Quantization for Diffusion Modelscited by 167
  15. 2019Neural Predictor for Neural Architecture Searchcited by 116
  16. 2024ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimizationcited by 115
  17. 2024Golden Noise for Diffusion Models: A Learning Frameworkcited by 91
  18. 2021How Powerful are Performance Predictors in Neural Architecture Search?cited by 88
  19. 2024Inference-Time Alignment of Diffusion Models with Direct Noise Optimizationcited by 51
  20. 2024HanDiffuser: Text-to-Image Generation With Realistic Hand Appearancescited by 42
  21. 2021NeuralNDCG: Direct Optimisation of a Ranking Metric via Differentiable Relaxation of Sortingcited by 39
  22. 2024BitsFusion: 1.99 bits Weight Quantization of Diffusion Modelcited by 37
  23. 2025Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Modelscited by 35
  24. 2024FIND: Fine-tuning Initial Noise Distribution with Policy Optimization for Diffusion Modelscited by 20
  25. 2025Outsourced diffusion sampling: Efficient posterior inference in latent spaces of generative modelscited by 16
  26. 2025ComfyUI-R1: Exploring Reasoning Models for Workflow Generationcited by 15
  27. 2024Immiscible Diffusion: Accelerating Diffusion Training with Noise Assignmentcited by 14
  28. 2024The Silent Assistant: NoiseQuery as Implicit Guidance for Goal-Driven Image Generationcited by 14
  29. 2025Source-Guided Flow Matchingcited by 11
  30. 2022AIO-P: Expanding Neural Performance Predictors Beyond Image Classificationcited by 8
  31. 2025NoiseAR: AutoRegressing Initial Noise Prior for Diffusion Modelscited by 8
  32. 2024Qua2SeDiMo: Quantifiable Quantization Sensitivity of Diffusion Modelscited by 6
  33. 2025ESS-Flow: Training-free guidance of flow-based models as inference in source spacecited by 6
  34. 2024Building Optimal Neural Architectures using Interpretable Knowledgecited by 5
  35. 2025Evaluating and Predicting Distorted Human Body Parts for Generated Imagescited by 4
  36. 2025Posterior Inference in Latent Space for Scalable Constrained Black-box Optimizationcited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Cost-Aware Routing for Efficient Text-To-Image Generation
  2. 2024Controllable Generation with Text-to-Image Diffusion Models: A Survey
  3. 2026ImageRAGTurbo: Towards One-step Text-to-Image Generation with Retrieval-Augmented Diffusion Models
  4. 2023Text-to-image Diffusion Models in Generative AI: A Survey
  5. 2023If at First You Don't Succeed, Try, Try Again: Faithful Diffusion-based Text-to-Image Generation by Selection
  6. 2025Reusing Computation in Text-to-Image Diffusion for Efficient Generation of Image Sets
  7. 2026Toward Early Quality Assessment of Text-to-Image Diffusion Models
  8. 2024Minority-Focused Text-to-Image Generation via Prompt Optimization