mlsanityData to 7 Oct 2026

Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generation

arXiv 2402.17245 ↗First posted 27 Feb 2024cs.CV cs.AIcited by 249

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

Abstract (arXiv)

In this work, we share three insights for achieving state-of-the-art aesthetic quality in text-to-image generative models. We focus on three critical aspects for model improvement: enhancing color and contrast, improving generation across multiple aspect ratios, and improving human-centric fine details. First, we delve into the significance of the noise schedule in training a diffusion model, demonstrating its profound impact on realism and visual fidelity. Second, we address the challenge of accommodating various aspect ratios in image generation, emphasizing the importance of preparing a balanced bucketed dataset. Lastly, we investigate the crucial role of aligning model outputs with human preferences, ensuring that generated images resonate with human perceptual expectations. Through extensive analysis and experiments, Playground v2.5 demonstrates state-of-the-art performance in terms of aesthetic quality under various conditions and aspect ratios, outperforming both widely-used open-source models like SDXL and Playground v2, and closed-source commercial systems such as DALLE 3 and Midjourney v5.2. Our model is open-source, and we hope the development of Playground v2.5 provides valuable guidelines for researchers aiming to elevate the aesthetic quality of diffusion-based image generation models.

Key facts. Cited by 249 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 16 of its 28 references that are in the map. First posted on arXiv 27 Feb 2024.

Builds on

16 of 28 references.

References · 16

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  5. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  6. 2022Scalable Diffusion Models with Transformerscited by 5,931
  7. 2022Generative Adversarial Networkscited by 5,603
  8. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  9. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  10. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
  11. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,388
  12. 2023LIMA: Less Is More for Alignmentcited by 1,080
4 more
  1. 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesiscited by 854
  2. 2023Common Diffusion Noise Schedules and Sample Steps are Flawedcited by 308
  3. 2023On the Importance of Noise Scheduling for Diffusion Modelscited by 193
  4. 2022How Much More Data Do I Need? Estimating Requirements for Downstream Taskscited by 22

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 64; 2025: 119; 2026: 66.

249 papers.

Sort:

By area:

  1. 2025Qwen-Image Technical Reportcited by 973
  2. 2025Emerging Properties in Unified Multimodal Pretrainingcited by 855
  3. 2024Autoregressive Model Beats Diffusion: Llama for Scalable Image Generationcited by 760
  4. 2024Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generationcited by 447
  5. 2024SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformerscited by 331
  6. 2024PixArt-Sigma: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generationcited by 326
  7. 2024Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesiscited by 297
  8. 2024Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understandingcited by 294
  9. 2024VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generationcited by 290
  10. 2025Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformercited by 247
  11. 2025Show-o2: Improved Native Unified Multimodal Modelscited by 242
  12. 2025Transfer between Modalities with MetaQueriescited by 231
38 more
  1. 2024Deep Compression Autoencoder for Efficient High-Resolution Diffusion Modelscited by 209
  2. 2025WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generationcited by 196
  3. 2025HPSv3: Towards Wide-Spectrum Human Preference Scorecited by 196
  4. 2024InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generationcited by 166
  5. 2025SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformercited by 165
  6. 2024JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generationcited by 162
  7. 2025T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoTcited by 162
  8. 2024SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Modelscited by 161
  9. 2025UniTok: A Unified Tokenizer for Visual Generation and Understandingcited by 148
  10. 2024HART: Efficient Visual Generation with Hybrid Autoregressive Transformercited by 128
  11. 2024SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantizationcited by 113
  12. 2025Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generationcited by 108
  13. 2025LongCat-Image Technical Reportcited by 92
  14. 2025Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learningcited by 88
  15. 2025SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillationcited by 85
  16. 2025Lumina-DiMOO: An Omni Diffusion Large Language Model for Multi-Modal Generation and Understandingcited by 83
  17. 2024GenAI Arena: An Open Evaluation Platform for Generative Modelscited by 81
  18. 2024Dual Diffusion for Unified Image Generation and Understandingcited by 76
  19. 2025PixelDiT: Pixel Diffusion Transformers for Image Generationcited by 75
  20. 2025Harmonizing Visual Representations for Unified Multimodal Understanding and Generationcited by 74
  21. 2024Allegro: Open the Black Box of Commercial-Level Video Generation Modelcited by 68
  22. 2024UltraPixel: Advancing Ultra-High-Resolution Image Synthesis to New Peakscited by 64
  23. 2024ILLUME: Illuminating Your LLMs to See, Draw, and Self-Enhancecited by 64
  24. 2025TIIF-Bench: How Does Your T2I Model Follow Your Instructions?cited by 64
  25. 2024Liquid: Language Models are Scalable and Unified Multi-modal Generatorscited by 62
  26. 2024FakeInversion: Learning to Detect Images from Unseen Text-to-Image Models by Inverting Stable Diffusioncited by 61
  27. 2025Diffusion-4K: Ultra-High-Resolution Image Synthesis with Latent Diffusion Modelscited by 61
  28. 2024CreatiLayout: Siamese Multimodal Diffusion Transformer for Creative Layout-to-Image Generationcited by 58
  29. 2024A Comprehensive Review of Multimodal Large Language Models: Performance and Challenges Across Different Taskscited by 57
  30. 2025GPT-ImgEval: A Comprehensive Benchmark for Diagnosing GPT4o in Image Generationcited by 57
  31. 2025NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scalecited by 55
  32. 2025ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinementcited by 53
  33. 2025OneCAT: Decoder-Only Auto-Regressive Model for Unified Understanding and Generationcited by 50
  34. 2025Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokenscited by 48
  35. 2025T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generationcited by 47
  36. 2024DreamStory: Open-Domain Story Visualization by LLM-Guided Multi-Subject Consistent Diffusioncited by 46
  37. 2025Unified Multimodal Discrete Diffusioncited by 46
  38. 2025FUDOKI: Discrete Flow-based Unified Understanding and Generation via Kinetic-Optimal Velocitiescited by 46

50 most cited of 249 All 249 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack
  2. 2024TypeScore: A Text Fidelity Metric for Text-to-Image Generative Models
  3. 2025Enhancing Reward Models for High-quality Image Generation: Beyond Text-Image Alignment
  4. 2022Language Does More Than Describe: On The Lack Of Figurative Speech in Text-To-Image Models
  5. 2025What Makes a Good Generated Image? Investigating Human and Multimodal LLM Image Preference Alignment
  6. 2025CHATS: Combining Human-Aligned Optimization and Test-Time Sampling for Text-to-Image Generation
  7. 2024Image Regeneration: Evaluating Text-to-Image Model via Generating Identical Image with Multimodal Large Language Models
  8. 2024ArtAug: Enhancing Text-to-Image Generation through Synthesis-Understanding Interaction