mlsanityData to 14 Oct 2026

Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack

arXiv 2309.15807 ↗First posted 27 Sep 2023cs.CVcited by 279

Not on the map. Why?

Cited by 154 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Training text-to-image models with web scale image-text pairs enables the generation of a wide range of visual concepts from text. However, these pre-trained models often face challenges when it comes to generating highly aesthetic images. This creates the need for aesthetic alignment post pre-training. In this paper, we propose quality-tuning to effectively guide a pre-trained model to exclusively generate highly visually appealing images, while maintaining generality across visual concepts. Our key insight is that supervised fine-tuning with a set of surprisingly small but extremely visually appealing images can significantly improve the generation quality. We pre-train a latent diffusion model on 1.1 billion image-text pairs and fine-tune it with only a few thousand carefully selected high-quality images. The resulting model, Emu, achieves a win rate of 82.9% compared with its pre-trained only counterpart. Compared to the state-of-the-art SDXLv1.0, Emu is preferred 68.4% and 71.3% of the time on visual appeal on the standard PartiPrompts and our Open User Input benchmark based on the real-world usage of text-to-image models. In addition, we show that quality-tuning is a generic approach that is also effective for other architectures, including pixel diffusion and masked generative transformer models.

Key facts. Cited by 279 papers in the map (data through 14 Oct 2026). Builds on 34 of its 36 references that are in the map. First posted on arXiv 27 Sep 2023.

Builds on

34 of 36 references.

References · 34

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2022Training language models to follow instructions with human feedbackcited by 15,971
  5. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  6. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  7. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  8. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  9. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  10. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  11. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  12. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
22 more
  1. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  2. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  3. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,300
  4. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,025
  5. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,611
  6. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,245
  7. 2022Make-A-Video: Text-to-Video Generation without Text-Video Datacited by 1,742
  8. 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,295
  9. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,290
  10. 2020RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Modelscited by 1,255
  11. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,219
  12. 2023Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generationcited by 977
  13. 2021Ethical and social risks of harm from Language Modelscited by 966
  14. 2021CogView: Mastering Text-to-Image Generation via Transformerscited by 694
  15. 2023Muse: Text-To-Image Generation via Masked Generative Transformerscited by 648
  16. 2023Scaling up GANs for Text-to-Image Synthesiscited by 492
  17. 2022Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priorscited by 487
  18. 2019Billion-scale semi-supervised learning for image classificationcited by 232
  19. 2023StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesiscited by 212
  20. 2023Noise2Music: Text-conditioned Music Generation with Diffusion Modelscited by 173
  21. 2023Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuningcited by 170
  22. 2022CM3: A Causal Masked Multimodal Model of the Internetcited by 142

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 30; 2024: 142; 2025: 80; 2026: 27.

279 papers.

Sort:

By area:

  1. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
  2. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,581
  3. 2024Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Predictioncited by 1,023
  4. 2025Cosmos World Foundation Model Platform for Physical AIcited by 864
  5. 2023Diffusion Model Alignment Using Direct Preference Optimizationcited by 790
  6. 2023Adversarial Diffusion Distillationcited by 759
  7. 2023VideoCrafter1: Open Diffusion Models for High-Quality Video Generationcited by 535
  8. 2024Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Modelcited by 483
  9. 2024ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignmentcited by 475
  10. 2024Evaluating Text-to-Visual Generation with Image-to-Text Generationcited by 474
  11. 2025Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Modelscited by 393
  12. 2024Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllabilitycited by 347
38 more
  1. 2024SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformerscited by 340
  2. 2023Emu Edit: Precise Image Editing via Recognition and Generation Taskscited by 324
  3. 2024Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesiscited by 304
  4. 2024Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillationcited by 279
  5. 2023Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioningcited by 255
  6. 2024Deep Compression Autoencoder for Efficient High-Resolution Diffusion Modelscited by 217
  7. 2024Diffusion Model-Based Image Editing: A Surveycited by 212
  8. 2024An Introduction to Vision-Language Modelingcited by 178
  9. 2023SparseCtrl: Adding Sparse Controls to Text-to-Video Diffusion Modelscited by 175
  10. 2023Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Modelscited by 169
  11. 2025Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Modelcited by 168
  12. 2024DragAnything: Motion Control for Anything using Entity Representationcited by 159
  13. 2023Cache Me if You Can: Accelerating Diffusion Models through Block Cachingcited by 151
  14. 2024MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captionscited by 146
  15. 2024MeshLRM: Large Reconstruction Model for High-Quality Meshescited by 139
  16. 2024GenAI-Bench: Evaluating and Improving Compositional Text-to-Visual Generationcited by 135
  17. 2024Recent Advances in 3D Gaussian Splattingcited by 131
  18. 2024Scalable High-Resolution Pixel-Space Image Synthesis with Hourglass Diffusion Transformerscited by 118
  19. 2024Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Imagecited by 116
  20. 2025VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Modelscited by 113
  21. 2024Seeing and Hearing: Open-domain Visual-Audio Generation with Diffusion Latent Alignerscited by 111
  22. 2024Adaptive Caching for Faster Video Generation with Diffusion Transformerscited by 108
  23. 2024VideoDPO: Omni-Preference Alignment for Video Diffusion Generationcited by 108
  24. 2024Aligning Diffusion Models by Optimizing Human Utilitycited by 101
  25. 2024DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Modelscited by 98
  26. 2023Finetuning Text-to-Image Diffusion Models for Fairnesscited by 92
  27. 2024Improving Text-to-Image Consistency via Automatic Prompt Optimizationcited by 90
  28. 2024Self-Play Fine-Tuning of Diffusion Models for Text-to-Image Generationcited by 85
  29. 2024IM-3D: Iterative Multiview Diffusion and Reconstruction for High-Quality 3D Generationcited by 84
  30. 2023GenTron: Diffusion Transformers for Image and Video Generationcited by 82
  31. 2023FlowVid: Taming Imperfect Optical Flows for Consistent Video-to-Video Synthesiscited by 79
  32. 2024Large-scale Reinforcement Learning for Diffusion Modelscited by 78
  33. 2025All-atom Diffusion Transformers: Unified generative modelling of molecules and materialscited by 75
  34. 2024CogView3: Finer and Faster Text-to-Image Generation via Relay Diffusioncited by 72
  35. 2024Vlogger: Make Your Dream A Vlogcited by 70
  36. 2024CV-VAE: A Compatible Video VAE for Latent Generative Video Modelscited by 70
  37. 2024Ctrl-Adapter: An Efficient and Versatile Framework for Adapting Diverse Controls to Any Diffusion Modelcited by 66
  38. 2024Meta 3D AssetGen: Text-to-Mesh Generation with High-Quality Geometry, Texture, and PBR Materialscited by 66

50 most cited of 279 All 279 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generation
  2. 2025Enhancing Reward Models for High-quality Image Generation: Beyond Text-Image Alignment
  3. 2026Pareto-Enhanced Portrait Generation: Vision-Aligned Text Supervision for Alignment, Realism, and Aesthetics
  4. 2022A Novel Sampling Scheme for Text- and Image-Conditional Image Synthesis in Quantized Latent Spaces
  5. 2024ArtAug: Enhancing Text-to-Image Generation through Synthesis-Understanding Interaction
  6. 2026LGTM: Training-Free Light-Guided Text-to-Image Diffusion Model via Initial Noise Manipulation
  7. 2024Image Regeneration: Evaluating Text-to-Image Model via Generating Identical Image with Multimodal Large Language Models
  8. 2024Conditional Balance: Improving Multi-Conditioning Trade-Offs in Image Generation