# Image generation, text-to-image and editing

Area: [Diffusion models](https://mlsanity.com/diffusion/index.md). HTML: https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/

## Key facts

- Image generation, text-to-image and editing: 2,401 papers on arXiv since 2020 (data through 14 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).
- 51 new papers 17 Sep–14 Oct.

## Most cited here

- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022), cited by 1,089 papers here
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022), cited by 1,028 papers here
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023), cited by 765 papers here
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021), cited by 751 papers here
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022), cited by 748 papers here
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022), cited by 486 papers here
- [Null-text Inversion for Editing Real Images using Guided Diffusion Models](https://mlsanity.com/paper/2211.09794/) (2022), cited by 361 papers here
- [Imagic: Text-Based Real Image Editing with Diffusion Models](https://mlsanity.com/paper/2210.09276/) (2022), cited by 336 papers here
- [Multi-Concept Customization of Text-to-Image Diffusion](https://mlsanity.com/paper/2212.04488/) (2022), cited by 333 papers here
- [IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2308.06721/) (2023), cited by 309 papers here

## New (17 Sep–14 Oct)

- [Purify Before You Align: Improving Representation Alignment for Diffusion Models](https://mlsanity.com/paper/2610.20761/) (2026-10-14)
- [SaTPO: Text-to-Image Safety Alignment via Transition Preference Optimization](https://mlsanity.com/paper/2610.19563/) (2026-10-14)
- [Discovering Undisclosed Concepts in LoRA Adapters for Diffusion-Based AIGC Models](https://mlsanity.com/paper/2610.18990/) (2026-10-13)
- [MiniDog: Dog-Breed Text-to-image Flow Matching from Pretraining to Fine-Tuning on 4 Consumer GPUs](https://mlsanity.com/paper/2610.18870/) (2026-10-13)
- [LayerCanvas: Infographic Generation in AI Learning Assistants via Hybrid Layer-Set Diffusion](https://mlsanity.com/paper/2610.18763/) (2026-10-13)
- [QK-Edit: Revisiting Attention-based Injection in MM-DiT for Image and Video Editing](https://mlsanity.com/paper/2610.17829/) (2026-10-13)
- [Image Tokenizers Should Be Trained Between Images](https://mlsanity.com/paper/2610.16759/) (2026-10-12)
- [PixARG: Pixel-Asynchronous Retrieval-Augmented Diffusion for Fast and Realistic Image Generation](https://mlsanity.com/paper/2610.14713/) (2026-10-10)
- [Controllable Diverse Sampling through Pullback Directions](https://mlsanity.com/paper/2610.14294/) (2026-10-09)
- [TGSR: Text-Grounded Diffusion for Faithful Image Super-Resolution](https://mlsanity.com/paper/2610.14281/) (2026-10-09)
- [Images Talk Back: Guiding MMDiTs by Suppressing Image-to-Text Feedback](https://mlsanity.com/paper/2610.13941/) (2026-10-09)
- [CoVA: Composing VAE Representations for Generative Learning](https://mlsanity.com/paper/2610.13322/) (2026-10-09)
- [Learning Representations to Guide Pixel Diffusion Transformers](https://mlsanity.com/paper/2610.12978/) (2026-10-09)
- [ORCA: Hunting Compositional Failures in Text-to-Image Diffusion](https://mlsanity.com/paper/2610.09841/) (2026-10-07)
- [Personalize at Test Time: Learning User Preferences for Image Generation](https://mlsanity.com/paper/2610.09015/) (2026-10-06)
- [Local Content-Style Control for Diffusion-based Image Stylization](https://mlsanity.com/paper/2610.08704/) (2026-10-06)
- [Disentangling Dual Image References in Frequency Aware Diffusion Models for Personalized Generation](https://mlsanity.com/paper/2610.07684/) (2026-10-06)
- [Compositional Concept Erasure in Text-to-Image Diffusion Models via Hierarchically Grounded Semantic Surgery](https://mlsanity.com/paper/2610.07337/) (2026-10-05)
- [Learning to Read the Contextual Tokens in Diffusion Transformers](https://mlsanity.com/paper/2610.06844/) (2026-10-05)
- [Salvation Lies Within: Eliciting Inherent Style Transfer in Step-Distilled Diffusion Models](https://mlsanity.com/paper/2610.05066/) (2026-10-04)
- [Geometry-Aware Preference Optimization for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2610.04980/) (2026-10-04)
- [Traversing the Satisfaction-Diversity Frontier in Text-to-Image Diffusion](https://mlsanity.com/paper/2610.02372/) (2026-10-01)
- [RASteer: Retain-Aware Activation Steering for Concept Erasure in Diffusion Models](https://mlsanity.com/paper/2610.01969/) (2026-10-01)
- [Rethinking Memorization Mitigation in Diffusion Models: Reinforcing Text Conditioning](https://mlsanity.com/paper/2610.01723/) (2026-10-01)
- [CLASP: Continual Low-rank Adapters for Spatially Placed Concepts from One Hypernetwork](https://mlsanity.com/paper/2610.01331/) (2026-10-01)
- [Diffusion Editing with Soft Mask: Pixel Level Redo of Image and Video with Adjustable Strength](https://mlsanity.com/paper/2610.00359/) (2026-09-30)
- [Diffusable Latents from Structure-Agnostic Distillation](https://mlsanity.com/paper/2609.39657/) (2026-09-30)
- [D-Scope: Decomposing and Steering Diffusion Transformers with Sparse Autoencoders](https://mlsanity.com/paper/2609.39625/) (2026-09-30)
- [DC-SAE: Deep Compression Semantic Autoencoder for Faster Diffusion Convergence](https://mlsanity.com/paper/2609.39222/) (2026-09-30)
- [ReGain: Restoring Subject Fidelity in Personalization on Synthetic Images](https://mlsanity.com/paper/2609.38680/) (2026-09-30)