TL;DR

  • TODO: 3–5 bullets summarizing the post.

Why and Wen should I tune my T2I modelsy

Tuning-Free Editing

SDEdit [1]

SDEdit Overview
SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations. SDEdit enables image editing and synthesis by leveraging stochastic differential equations, supporting both conditional (image-to-image) and unconditional (text-guided) diffusion. The pipeline allows for flexible editing while preserving content and structure of the source image. [Meng et al., 2022]

Prompt-to-Prompt [2]

Prompt-to-Prompt Overview
Prompt-to-Prompt Image Editing with Cross-Attention Control. Prompt-to-Prompt enables image editing by controlling cross-attention mechanisms in diffusion models. [Hertz et al., 2022]

DiffEdit [3]

DiffEdit Overview
DiffEdit: Diffusion-based Semantic Image Editing with Mask Guidance. DiffEdit enables semantic image editing using diffusion models with mask guidance for precise control. [Couairon et al., 2023]

NULL-text Inversion [4]

NULL-text Inversion Overview
NULL-text Inversion for Editing Real Images Using Guided Diffusion Models. NULL-text Inversion enables editing of real images using guided diffusion models through text inversion techniques. [Mokady et al., 2023]

Stable Flow [5]

Stable Flow Overview
Stable Flow: Vital Layers for Training-Free Image Editing. Stable Flow introduces vital layers for training-free image editing using flow-based models. [Avrahami et al., 2025]

Semantic Image Inversion [6]

Semantic Image Inversion Overview
Semantic Image Inversion and Editing Using Rectified Stochastic Differential Equations. Semantic Image Inversion enables image editing using rectified stochastic differential equations for semantic control. [Rout et al., 2025]

Taming Rectified Flow [7]

Taming Rectified Flow Overview
Taming Rectified Flow for Inversion and Editing. Taming Rectified Flow enables image inversion and editing using rectified flow models. [Wang et al., 2025]

Tuning-Based Editing

References

  1. Meng, Chenlin; He, Yutong; Song, Yang; Song, Jiaming; Wu, Jiajun; Zhu, Jun-Yan; Ermon, Stefano (2022). SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations. International Conference on Learning Representations (ICLR).
  2. Hertz, Amir; Mokady, Ron; Tenenbaum, Jay; Aberman, Kfir; Pritch, Yael; Cohen-or, Daniel (2022). Prompt-to-Prompt Image Editing with Cross-Attention Control. The Eleventh International Conference on Learning Representations.
  3. Couairon, Guillaume; Verbeek, Jakob; Schwenk, Holger; Cord, Matthieu (2023). DiffEdit: Diffusion-based Semantic Image Editing with Mask Guidance. The Eleventh International Conference on Learning Representations.
  4. Mokady, Ron; Hertz, Amir; Aberman, Kfir; Pritch, Yael; Cohen-Or, Daniel (2023). NULL-text Inversion for Editing Real Images Using Guided Diffusion Models. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
  5. Avrahami, Omri; Patashnik, Or; Fried, Ohad; Nemchinov, Egor; Aberman, Kfir; Lischinski, Dani; Cohen-Or, Daniel (2025). Stable Flow: Vital Layers for Training-Free Image Editing. CVPR.
  6. Rout, Litu; Chen, Yujia; Ruiz, Nataniel; Caramanis, Constantine; Shakkottai, Sanjay; Chu, Wen-Sheng (2025). Semantic Image Inversion and Editing Using Rectified Stochastic Differential Equations. The Thirteenth International Conference on Learning Representations.
  7. Wang, Jiangshan; Pu, Junfu; Qi, Zhongang; Guo, Jiayi; Ma, Yue; Huang, Nisha; Chen, Yuxin; Li, Xiu; Shan, Ying (2025). Taming Rectified Flow for Inversion and Editing. ICML.