mlsanityData to 7 Oct 2026

Image generation, text-to-image and editing

2,401 papers6 this weekMedium confidence in this grouping: mostly one topic, with blurry edgesMedium confidence in this grouping: mostly one topic, with blurry edges · About

Keywords: image, diffusion, images, generation, editing

Key facts. Image generation, text-to-image and editing: 2,401 papers on arXiv since 2020 (data through 7 Oct 2026). 1,089 of its 2,401 mapped papers (45%) cite “Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding” (2022, arXiv 2205.11487). 1,028 of its 2,401 mapped papers (43%) cite “Hierarchical Text-Conditional Image Generation with CLIP Latents” (2022, arXiv 2204.06125). 38 new papers 17 Sep–7 Oct.

What’s new

17 Sep – 7 Oct 2026

38 new papers, 17 Sep – 7 Oct; 6 this week.

  1. This week · 6
  2. ORCA: Hunting Compositional Failures in Text-to-Image Diffusion
  3. Personalize at Test Time: Learning User Preferences for Image Generation
  4. Local Content-Style Control for Diffusion-based Image Stylization
  5. Disentangling Dual Image References in Frequency Aware Diffusion Models for Personalized Generation
  6. Compositional Concept Erasure in Text-to-Image Diffusion Models via Hierarchically Grounded Semantic Surgery
  7. Learning to Read the Contextual Tokens in Diffusion Transformers
  8. Earlier · 32
  9. Salvation Lies Within: Eliciting Inherent Style Transfer in Step-Distilled Diffusion Models
  10. Geometry-Aware Preference Optimization for Text-to-Image Diffusion Models also fits: Diffusion foundations and sampling
  11. Traversing the Satisfaction-Diversity Frontier in Text-to-Image Diffusion
  12. RASteer: Retain-Aware Activation Steering for Concept Erasure in Diffusion Models also fits: Robustness, privacy and adversarial aspects
All 38
  1. Rethinking Memorization Mitigation in Diffusion Models: Reinforcing Text Conditioning
  2. CLASP: Continual Low-rank Adapters for Spatially Placed Concepts from One Hypernetwork
  3. Diffusion Editing with Soft Mask: Pixel Level Redo of Image and Video with Adjustable Strength also fits: Video generation
  4. Diffusable Latents from Structure-Agnostic Distillation also fits: Diffusion foundations and sampling
  5. D-Scope: Decomposing and Steering Diffusion Transformers with Sparse Autoencoders
  6. DC-SAE: Deep Compression Semantic Autoencoder for Faster Diffusion Convergence also fits: Diffusion foundations and sampling
  7. ReGain: Restoring Subject Fidelity in Personalization on Synthetic Images
  8. Targeted Visual Counterfactual Explanations for Contrastive Vision-Language Model
  9. STEPS: Scene Text Editing with Preserved Style Using Diffusion and Contrastive Style Encoding
  10. DMA2: Pixel-space Distribution Matching with Adversarial and Anchor Losses
  11. DiffReID: Discriminative Diffusion Model for Object Re-Identification also fits: Inverse problems and image restoration
  12. PreviewDiff: Multimodal Critic-Guided Search over Diffusion Latents also fits: Diffusion foundations and sampling
  13. Mind the RefGAP: Correcting Reference Attention in Diffusion-Based Visual Editing
  14. FlowTool: Controlling Tool Parameter in Image Retouching via Flow Matching
  15. eval-unlearn: Benchmarking unlearning in Text-to-Image Diffusion Models also fits: Robustness, privacy and adversarial aspects
  16. ControlTrace: Recovering Control Fields for Hidden-Content Recognition
  17. What Visual Generators Need from Teachers: Rethinking Representation Alignment also fits: Diffusion foundations and sampling
  18. TSGate: Timestep-Aware Gated Attention for Diffusion Transformers also fits: Video generation
  19. Constrained Edit Fields for Training-Free Flow Editing
  20. Background Gradients Shape Memorization in Flow Matching also fits: Video generation
  21. Beyond Temporal Smoothing: Spatial Energy Budgets Stabilize One-Step Diffusion Editing also fits: Diffusion foundations and sampling
  22. Diffu-LoRA: A Novel Low-Rank Adaptation for Personalized Diffusion Models
  23. Panoptic Scene Program Diffusion Transformer
  24. TOLA: Text-aware One-Step Latent Adaptation for Diffusion-based Text Image Super-Resolution also fits: Inverse problems and image restoration
  25. CARE: Condition-Aware Representation Regularization for Diffusion Models
  26. Semantically-Guided Domain Randomization for Industrial Object Detection in Low-Image-Budget Regimes
  27. Delving into Asymmetric Information Dynamics for High-Fidelity Virtual Try-On also fits: 3D, point cloud and scene generation
  28. SafeStyle: Calibrated Style Residual Injection for Controllable Style-Leakage Trade-off in Diffusion Stylization

Foundations

Most cited by papers here

  1. Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding2022cited by 1,089 here
  2. Hierarchical Text-Conditional Image Generation with CLIP Latents2022cited by 1,028 here
  3. Adding Conditional Control to Text-to-Image Diffusion Models2023cited by 765 here
  4. GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models2021cited by 751 here
  5. DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation2022cited by 748 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2020Denoising Diffusion Probabilistic Modelscited by 1,535 here
  2. 2020Denoising Diffusion Implicit Modelscited by 1,033 here
  3. 2021Improved Denoising Diffusion Probabilistic Modelscited by 328 here
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 827 here
  5. 2021Blended Diffusion for Text-driven Editing of Natural Imagescited by 254 here
  6. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 751 here
  7. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 1,028 here
  8. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 1,089 here
  9. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 748 here
  10. 2022Imagic: Text-Based Real Image Editing with Diffusion Modelscited by 336 here
  11. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 486 here
  12. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 765 here
  13. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 684 here
  14. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 471 here
10 more it builds on, not in this chain
  1. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 514 here
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 1,868 here
  3. 2022Classifier-Free Diffusion Guidancecited by 673 here
  4. 2022Null-text Inversion for Editing Real Images using Guided Diffusion Modelscited by 361 here
  5. 2022Multi-Concept Customization of Text-to-Image Diffusioncited by 333 here
  6. 2022Scalable Diffusion Models with Transformerscited by 397 here
  7. 2023GLIGEN: Open-Set Grounded Text-to-Image Generationcited by 263 here
  8. 2023Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Modelscited by 292 here
  9. 2023T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Modelscited by 305 here
  10. 2023IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Modelscited by 309 here

The 24 most cited of 3,466.

Browse

30 of 2,401, ranked 6–35

  1. 6InstructPix2Pix: Learning to Follow Image Editing Instructions2022486
  2. 7Null-text Inversion for Editing Real Images using Guided Diffusion Models2022361
  3. 8Imagic: Text-Based Real Image Editing with Diffusion Models2022336
  4. 9Multi-Concept Customization of Text-to-Image Diffusion2022333
  5. 10IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models2023309
  6. 11T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models2023305
  7. 12Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models2023292
  8. 13GLIGEN: Open-Set Grounded Text-to-Image Generation2023263
  9. 14Blended Diffusion for Text-driven Editing of Natural Images2021254
  10. 15eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers2022250
All 30
  1. 16DiffEdit: Diffusion-based semantic image editing with mask guidance2022208
  2. 17Palette: Image-to-Image Diffusion Models2021199
  3. 18DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation2021193
  4. 19Compositional Visual Generation with Composable Diffusion Models2022180
  5. 20Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis2022167
  6. 21Blended Latent Diffusion2022140
  7. 22GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment2023128
  8. 23Paint by Example: Exemplar-based Image Editing with Diffusion Models2022125
  9. 24BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion2023113
  10. 25MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation2023112
  11. 26InstantID: Zero-shot Identity-Preserving Generation in Seconds2024109
  12. 27FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space2025107
  13. 28Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models2023103
  14. 29SpaText: Spatio-Textual Representation for Controllable Image Generation202297
  15. 30SVDiff: Compact Parameter Space for Diffusion Fine-Tuning202396
  16. 31LayoutDiffusion: Controllable Diffusion Model for Layout-to-image Generation202396
  17. 32Linguistic Binding in Diffusion Models: Enhancing Attribute Correspondence through Attention Map Alignment202396
  18. 33FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attention202395
  19. 34An Edit Friendly DDPM Noise Space: Inversion and Manipulations202392
  20. 35Inversion-Based Style Transfer with Diffusion Models202290