T2I Diffusion Models

T2I: Text-to-Image

Overview

Text-to-image diffusion models turn prompts into images by iteratively denoising a latent or pixel representation, using latent-diffusion U-Nets, diffusion transformers, and rectified-flow models. Researchers improve prompt and spatial control with classifier-free guidance, cross-attention interventions, LoRA adapters, and reference or layout conditioning, while preference learning and reinforcement learning tune outputs to human or task rewards. Another major effort distills models into few-step generators and uses caching, quantization, and latent compression to reduce inference costs; benchmarks test composition, text rendering, image quality, and human preference. A central challenge is balancing prompt fidelity and diversity with speed, quality, and safeguards: realism or alignment gains do not guarantee robust composition, fair representation, or reliable concept removal.

Latest papers

CardsList

440 papers34 papers in the last four weeks, down 46% on the four weeks before. 0.3% of all new papers.

  1. FreeFuse: Multi-Subject LoRA Fusion via Adaptive Token-Level Routing at Test Time

    Oct 27, 2025Yaoli Liu, Yao-Xiang Ding, Kun ZhouSubject-Driven Image GenerationCompositional T2I Generation

  2. D2D: Detector-to-Differentiable Critic for Improved Numeracy in Text-to-Image Generation

    Oct 22, 2025Nobline Yoo, Olga Russakovsky, Ye ZhuT2I GenerationT2I Diffusion Models

  3. How Diffusion Models Memorize

    Sep 30, 2025Juyeop Kim, Songkuk Kim, Jong-Seok LeeMemorization in Generative ModelsT2I Diffusion Models

  4. LoRAtorio: An intrinsic approach to LoRA Skill Composition

    Aug 15, 2025Niki Foteinopoulou, Ignas Budvytis, Stephan LiwickiT2I Diffusion ModelsLow-Rank Adaptation

  5. Detail++: Training-Free Detail Enhancer for T2I Diffusion Models

    Jul 23, 2025Lifeng Chen, Jiner Wang, Zihao Pan +3Diffusion Model GuidanceCompositional T2I Generation

  6. Mix-Opt: Mixed Optimization for Memory-Efficient Personalization of Text-to-Image Diffusion Models

    Jul 14, 2025Seokeon Choi, Sunghyun Park, Hyoungwoo Park +2Diffusion Model AdaptationDiffusion Model Fine-Tuning

  7. LoRAShield: Data-Free Editing Alignment for Secure Personalized LoRA Sharing

    Jul 5, 2025Jiahao Chen, Junhao Li, Yiming Wang +6Diffusion Model AlignmentT2I Diffusion Models

  8. AI's Blind Spots: Geographic Knowledge and Diversity Deficit in Generated Urban Scenario

    Jun 20, 2025Ciro Beneduce, Massimiliano Luca, Bruno LepriT2I GenerationT2I Generation Evaluation

  9. The Alignment Illusion: How BadReward Corrupts Text-to-Image Generation

    Jun 3, 2025Kaiwen Duan, Hongwei Yao, Yufei Chen +4Data Poisoning AttacksT2I Diffusion Models

  10. TraceMark-LDM: Authenticatable Watermarking for Latent Diffusion Models via Binary-Guided Rearrangement

    Mar 30, 2025Wenhao Luo, Zhangyi Shen, Ye Yao +3Diffusion Model WatermarkingLatent Diffusion Models

  11. PixelPonder: Dynamic Patch Adaptation for Enhanced Multi-Conditional Text-to-Image Generation

    Mar 9, 2025Yanjie Pan, Qingdong He, Zhengkai Jiang +9T2I GenerationControllable Image Generation

  12. PersGuard: Preventing Malicious Personalization in Text-to-Image Diffusion Models via Model Backdoors

    Feb 22, 2025Xinwei Liu, Xiaojun Jia, Yuan Xun +2T2I GenerationT2I Diffusion Models

  13. DICE: Distilling Classifier-Free Guidance into Text Embeddings

    Feb 6, 2025Zhenyu Zhou, Defang Chen, Can Wang +2Diffusion Model AlignmentDiffusion Model Guidance

  14. Text-to-Image Synthesis: A Decade Survey

    Nov 25, 2024Nonghai Zhang, Hao TangT2I GenerationT2I Diffusion Models