Yinan Chen ^1★ . Jiangning Zhang ^1,2★ . Yali Bi ³ . Xiaobin Hu ² . Teng Hu ⁴ .
Zhucun Xue ¹ . Ran Yi ⁴ . Yong Liu ^1† . Ying Tai ⁵

¹College of Control Science and Engineering, Zhejiang University     ²YouTu Lab, Tencent     ³College of Computer and Information Science, Southwest University
⁴Department of Computer Science & Engineering, Shanghai Jiao Tong University     ⁵School of Intelligence Science and Technology, Nanjing University

Introduction

This repository is a comprehensive collection of resources for Image Inversion, If you find any work missing or have any suggestions, feel free to pull requests or contact us. We will promptly add the missing papers to this repository.

✨Highlight!!!

1. Comprehensive Coverage of Image Inversion Techniques: Includes methods ranging from GANs and diffusion models to emerging frameworks like DiT and rectified flow.

2. Mainstream Applications: Supports applications such as object editing, attribute editing, style transfer, image restoration, and personalized generation.

3. Other Domain Generative Model Inversion: Extends to other domains, showcasing the versatility of generative model inversion techniques.

✨Survey pipeline

Summary of Contents

• Introduction

• Summary of Contents

• Image Inversion Methods

  • Diffusion Model
    • Training-free
    • Fine-tune
    • Extra Trainable Module
  • GANs
    • Encoder-based
    • Latent Optimization
    • Hybrid
  • Promising Technologies
    • DiT
    • Rectified Flow

• Related Research Domains

  • Video
  • 3D
  • Audio

• Cite The Survey

• Contact

Image Inversion Methods

Diffusion Model

Training-free

Year	Venue	Task	Paper Title	Code
2025	NIPS	Object & Attribute Editing	FreeInv: Free Lunch for Improving DDIM Inversion	code
2025	ICCV	Object & Attribute Editing	EEdit: Rethinking the Spatial and Temporal Redundancy for Efficient Image Editing	code
2025	CVPR	Style Transfer	StyleSSP: Sampling StartPoint Enhancement for Training-free Diffusion-based Method for Style Transfer	code
2025	ICLR	Object & Attribute Editing	Semantic Image Inversion and Editing using Rectified Stochastic Differential Equations	code
2025	ICLR	Image Restoration	HD-Painter: High-Resolution and Prompt-Faithful Text-Guided Image Inpainting with Diffusion Models	Code
2025	ICLR	Object & Attribute Editing	GNRI: Lightning-Fast Image Inversion and Editing for Text-to-Image Diffusion Models	Code
2025	ICML	Object & Attribute Editing	EasyInv: Toward Fast and Better DDIM Inversion	code
2025	ICML	Object & Attribute Editing	FireFlow: Fast Inversion of Rectified Flow for Image Semantic Editing	[code]
2025	AAAI	Spatial-Aware Editing	DesignEdit: Multi-Layered Latent Decomposition and Fusion for Unified & Accurate Image Editing	Code
2024	CVPR	Object & Attribute Editing	An Edit Friendly DDPM Noise Space: Inversion and Manipulations	Code
2024	NN	Object & Attribute Editing	PFB-Diff: Progressive Feature Blending Diffusion for Text-driven Image Editing	Code
2024	NIPS	Object & Attribute Editing	Energy-Based Cross Attention for Bayesian Context Update in Text-to-Image Diffusion Models	Code
2024	WACV	Object & Attribute Editing	ProxEdit: Improving Tuning-Free Real Image Editing with Proximal Guidance	Code
2024	ECCV	Object & Attribute Editing	Source Prompt Disentangled Inversion for Boosting Image Editability with Diffusion Models	code
2024	ECCV	Object & Attribute Editing	ReNoise: Real Image Inversion Through Iterative Noising	-
2024	ECCV	Object & Attribute Editing	Exact Diffusion Inversion via Bi-directional Integration Approximation	Code
2024	ICLR	Object & Attribute Editing	Magicremover: Tuning-free Text-guided Image inpainting with Diffusion Models	-
2024	ICLR	Object & Attribute Editing	PnP Inversion: Boosting Diffusion-based Editing with 3 Lines of Code	Code
2024	ICLR	Object & Attribute Editing	Object-aware Inversion and Reassembly for Image Editing	Code
2024	CVPR	Object & Attribute Editing	LEDITS++: Limitless Image Editing using Text-to-Image Models	Code
2024	CVPR	Object & Attribute Editing	Contrastive Denoising Score for Text-guided Latent Diffusion Image Editing	Code
2024	CVPR	Object & Attribute Editing	Focus on Your Instruction: Fine-grained and Multi-instruction Image Editing by Attention Modulation	Code
2024	ICLR	Object & Attribute Editing	Noise Map Guidance: Inversion with Spatial Context for Real Image Editing	Code
2024	CVPR	Object & Attribute Editing	Towards Understanding Cross and Self-Attention in Stable Diffusion for Text-Guided Image Editing	Code
2024	Arxiv	Object & Attribute Editing	Ground-A-Score: Scaling Up the Score Distillation for Multi-Attribute Editing	Code
2024	ACM MM	Object & Attribute Editing	LoMOE: Localized Multi-Object Editing via Multi-Diffusion	Code
2024	ICLR	Spatial-Aware Editing	DragonDiffusion: Enabling Drag-style Manipulation on Diffusion Models	Code
2024	CVPR	Style Transfer	Z∗: Zero-shot Style Transfer via Attention Rearrangement	Code
2024	CVPR	Style Transfer	Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfer	Code
2024	CVPR	Controllable Image Generation	FreeControl: Training-Free Spatial Control of Any Text-to-Image Diffusion Model with Any Condition	Code
2024	FG	Object & Attribute Editing	Discovering Interpretable Directions in the Semantic Latent Space of Diffusion Models	Code
2024	NIPS	Image Restoration	Blind Image Restoration via Fast Diffusion Inversion	Code
2024	SIGGRAPH	Image Fusion	Cross-Image Attention for Zero-Shot Appearance Transfer	Code
2024	ECCV	Image Fusion	Tuning-Free Image Customization with Image and Text Guidance	Code
2024	CVPR	Image Generation	Self-Discovering Interpretable Diffusion Latent Directions for Responsible Text-to-Image Generation.	Code
2024	ACM MM	Personalized Generation	Pick-and-Draw: Training-free Semantic Guidance for Text-to-Image Personalization	-
2024	CVPR	Personalized Generation	DreamMatcher: Appearance Matching Self-Attention for Semantically-Consistent Text-to-Image Personalization	Code
2023	ICLR	Object & Attribute Editing	Prompt-to-Prompt Image Editing with Cross Attention Control	Code
2023	ICLR	Object & Attribute Editing	DiffEdit: Diffusion-based semantic image editing with mask guidance	-
2023	CVPR	Object & Attribute Editing	Null-text Inversion for Editing Real Images using Guided Diffusion Models	Code
2023	CVPR	Object & Attribute Editing	EDICT: Exact Diffusion Inversion via Coupled Transformations	Code
2023	CVPR	Object & Attribute Editing	Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation	Code
2023	CVPR	Object & Attribute Editing	Uncovering the Disentanglement Capability in Text-to-Image Diffusion Models	Code
2023	Arxiv	Object & Attribute Editing	Negative-prompt Inversion: Fast Image Inversion for Editing with Text-guided Diffusion Models	-
2023	ICCV	Object & Attribute Editing	Prompt Tuning Inversion for Text-Driven Image Editing Using Diffusion Models	Code
2023	Arxiv	Object & Attribute Editing	LEDITS: Real Image Editing with DDPM Inversion and Semantic Guidance	Code
2023	ICCV	Object & Attribute Editing	Effective Real Image Editing with Accelerated Iterative Diffusion Inversion	-
2023	NIPS	Object & Attribute Editing	Dynamic Prompt Learning: Addressing Cross-Attention Leakage for Text-Based Image Editing	Code
2023	ICCV	Attribute Editing	Localizing Object-level Shape Variations with Text-to-Image Diffusion Models	Code
2023	ICCV	Attribute Editing	MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing	Code
2023	PRCV	Attribute Editing	KV Inversion: KV Embeddings Learning for Text-Conditioned Real Image Action Editing	-
2023	AAAI	Attribute Editing	Tuning-Free Inversion-Enhanced Control for Consistent Image Editing	-
2023	TOG	Image Restoration	Blended Latent Diffusion	Code
2023	Arxiv	Image Restoration	Differential Diffusion: Giving Each Pixel Its Strength	Code
2023	ICCV	Object & Attribute Editing	TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition	Code
2023	NIPS	Spatial-Aware Editing	Diffusion Self-Guidance for Controllable Image Generation	-
2023	ICCV	Object & Attribute Editing	Unifying Diffusion Models' Latent Space, with Applications to CycleDiffusion and Guidance	Code
2023	ICLR	Personalized Generation	An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion	Code
2023	Arxiv	Personalized Generation	Highly Personalized Text Embedding for Image Manipulation by Stable Diffusion	Code
2023	Arixv	Personalized Generation	P+: Extended Textual Conditioning in Text-to-Image Generation	Code
2022	CVPR	Image Restoration	Blended Diffusion for Text-driven Editing of Natural Images	Code
2022	NIPS	Image Restoration	High-Resolution Image Editing via Multi-Stage Blended Diffusion	Code

Fine-tune

Year	Venue	Task	Paper Title	Code
2025	WACV	Personalized Generation	A Data Perspective on Enhanced Identity Preservation for Diffusion Personalization	-
2024	ICLR	Spatial-Aware Editing	DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing	Code
2024	ICLR	Personalized Generation	DisenBooth: Identity-Preserving Disentangled Tuning for Subject-Driven Text-to-Image Generation	Code
2024	NIPS	Personalized Generation	Direct Consistency Optimization for Robust Customization of Text-to-Image Diffusion Models	Code
2024	CVPR	Personalized Generation	FaceChain-SuDe: Building Derived Class to Inherit Category Attributes for One-shot Subject-Driven Generation	Code
2023	CVPR	Object & Attribute Editing	Imagic: Text-Based Real Image Editing with Diffusion Models	-
2023	TOG	Object & Attribute Editing	UniTune: Text-Driven Image Editing by Fine Tuning a Diffusion Model on a Single Image	Code
2023	CVPR	Object & Attribute Editing	SINE: SINgle Image Editing with Text-to-Image Diffusion Models	Code
2023	Arxiv	Object & Attribute Editing	Forgedit: Text Guided Image Editing via Learning and Forgetting	Code
2023	NIPS	Image Fusion	Photoswap: Personalized Subject Swapping in Images	Code
2023	TMLR	Image Fusion	DreamEdit: Subject-driven Image Editing	Code
2023	CVPR	Personalized Generation	DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation	Code
2023	CVPR	Personalized Generation	Multi-Concept Customization of Text-to-Image Diffusion	Code
2023	ICML	Personalized Generation	Cones: Concept Neurons in Diffusion Models for Customized Generation	-
2023	ICCV	Personalized Generation	SVDiff: Compact Parameter Space for Diffusion Fine-Tuning	Code
2023	CVPR	Personalized Generation	Custom-Edit: Text-Guided Image Editing with Customized Diffusion Models	-

Extra Trainable Module

Year	Venue	Task	Paper Title	Code
2025	CVPR	Image Restoration	Arbitrary-steps Image Super-resolution via Diffusion Inversion	Code
2025	CVM	Object & Attribute Editing	StyleDiffusion: Prompt-Embedding Inversion for Text-Based Editing	Code
2024	CVPR	Object & Attribute Editing	ZONE: Zero-Shot Instruction-Guided Local Editing	Code
2024	CVPR	Object & Attribute Editing	Doubly Abductive Counterfactual Inference for Text-based Image Editing	Code
2024	ECCV	Object & Attribute Editing	TurboEdit: Instant text-based image editing	-
2024	CVPR	Spatial-Aware Editing	DiffEditor: Boosting Accuracy and Flexibility on Diffusion-based Image Editing	Code
2024	AAAI	Personalized Generation	Decoupled Textual Embeddings for Customized Image Generation	Code
2024	CVPR	Image Concept Decoupling	CLiC: Concept Learning in Context	Code
2023	ICLR	Object & Attribute Editing	Diffusion Models Already Have A Semantic Latent Space	Code
2023	Arxiv	Object & Attribute Editing	Region-Aware Diffusion for Zero-shot Text-driven Image Editing	Code
2023	ICCV	Object & Attribute Editing	Delta Denoising Score	Code
2023	CVPR	Style Transfer	Inversion-Based Style Transfer With Diffusion Models	Code
2023	SIGGRAPH Asia	Personalized Generation	A Neural Space-Time Representation for Text-to-Image Personalization	Code
2023	Arxiv	Personalized Generation	ViCo: Plug-and-play Visual Condition for Personalized Text-to-image Generation	Code
2023	SIGGRAPH Asia	Image Concept Decoupling	Break-A-Scene: Extracting Multiple Concepts from a Single Image	Code
2022	Arxiv	Personalized Generation	DreamArtist: Towards Controllable One-Shot Text-to-Image Generation via Positive-Negative Prompt-Tuning	Code

GANs

Hybrid Table

Year	Venue	Task	Paper Title	Code
2024	AAAI	Attribute Editing	Spatial-Contextual Discrepancy Information Compensation for GAN Inversion	Code
2024	IJCV	Image Fusion	One-Shot Neural Face Reenactment via Finding Directions in GAN’s Latent Space	-
2024	CVPR	Attribute Editing	The Devil is in the Details: StyleFeatureEditor for Detail-Rich StyleGAN Inversion and High Quality Image Editing	Code
2023	WACV	Attribute Editing	DyStyle: Dynamic Neural Network for Multi-Attribute-Conditioned Style Editing.	-
2023	AAAI	Attribute Editing	ReGANIE: Rectifying GAN Inversion Errors for Accurate Real Image Editing	-
2022	ECCV	Style Transfer	JoJoGAN: One Shot Face Stylization	Code
2022	CVPR	Attribute Editing	Spatially-Adaptive Multilayer Selection for GAN Inversion and Editing	Code
2022	ECCV	Attribute Editing	Editing Out-of-Domain GAN Inversion via Differential Activations	-
2022	NIPS	Object & Attribute Editing	Generalized One-shot Domain Adaptation of Generative Adversarial Networks	Code
2016	ECCV	Attribute Editing	Generative Visual Manipulation on the Natural Image Manifold	Code

Latent Optimization Table

Year	Venue	Task	Paper Title	Code
2024	AAAI	Object & Attribute Editing	HyperEditor: Achieving Both Authenticity and Cross-Domain Capability in Image Editing via Hypernetworks	Code
2023	CVPR	Attribute Editing	Balancing Reconstruction and Editing Quality of GAN Inversion for Real Image Editing with StyleGAN Prior Latent Space	-
2022	TOG	Attribute Editing	Pivotal Tuning for Latent-based Editing of Real Images	Code
2022	ECCV	Attribute Editing	Chunkmogrify: Real image inversion via Segments	Code
2022	CVPR	Attribute Editing	Overparameterization Improves StyleGAN Inversion	-
2019	ICCV	Attribute Editing	Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?	Code
2016	NIPS	Image Generation	Inverting the generator of a generative adversarial network	Code

Encoder-based Table

Year	Venue	Task	Paper Title	Code
2024	AAAI	Attribute Editing	Gradual Residuals Alignment: A Dual-Stream Framework for GAN Inversion and Image Attribute Editing	-
2023	CVPR	Image Fusion	Fine-Grained Face Swapping via Regional GAN Inversion	Code
2023	CVPR	Attribute Editing	Delving StyleGAN Inversion for Image Editing: A Foundation Latent Space Viewpoint	Code
2023	CVPR	Attribute Editing	StyleRes: Transforming the Residuals for Real Image Editing with StyleGAN	Code
2023	ICCV	Attribute Editing	Diverse Inpainting and Editing with GAN Inversion	-
2023	TOG	Object & Attribute Editing	CLIP-Guided StyleGAN Inversion for Text-Driven Real Image Editing	Code
2022	CVPR	Attribute Editing	HyperInverter: Improving StyleGAN Inversion via Hypernetwork	Code
2022	CVPR	Attribute Editing	Style Transformer for Image Inversion and Editing	Code
2022	ECCV	Attribute Editing	High-fidelity GAN Inversion with Padding Space	Code
2022	ACM MM	Attribute Editing	Everything is There in Latent Space: Attribute Editing and Attribute Style Manipulation by StyleGAN Latent Space Exploration	-
2022	NIPS	Image Restoration	Semantic uncertainty intervals for disentangled latent spaces	Code
2022	ECCV	Attribute Editing	IntereStyle: Encoding an Interest Region for Robust StyleGAN Inversion	-
2021	SIGGRAPH	Attribute Editing	Designing an Encoder for StyleGAN Image Manipulation	Code
2016	Arxiv	Attribute Editing	Invertible conditional GANs for image editing	Code

Promising Technologies

DiT

Year	Venue	Task	Paper Title	Code
2025	CVPR	Object & Attribute Editing	Stable Flow: Vital Layers for Training-Free Image Editing	Code
2024	AAAI	Object & Attribute Editing	DiT4Edit: Diffusion Transformer for Image Editing	Code

Rectified Flow

Year	Venue	Task	Paper Title	Code
2025	NIPS	Object & Attribute Editing	DNAEdit: Direct Noise Alignment for Text-Guided Rectified Flow Editing	code
2025	ICCV	Object Editing	KV-Edit: Training-Free Image Editing for Precise Background Preservation	Code
2025	ICLR	Object & Attribute Editing	Semantic Image Inversion and Editing using Stochastic Rectified Differential Equations	Code
2025	ICLR	Object & Attribute Editing	Lightning-Fast Image Inversion and Editing for Text-to-Image Diffusion Models	Code
2025	ICML	Object & Attribute Editing	Taming Rectified Flow for Inversion and Editing	Code

Related Research Domains

Video

Year	Venue	Category	Task	Paper	Code
2025	CVPR	DM	Video Editing	VideoDirector: Precise Video Editing via Text-to-Video Models	code
2025	NIPS	DM	Dynamic View Synthesis	Dynamic View Synthesis as an Inverse Problem	-
2025	ICLR	DM	Video Editing	VideoGrain: Modulating Space-Time Attention for Multi-Grained Video Editing	Code
2025	ICML	DM	Video & Image Editing	Editable Noise Map Inversion: Encoding Target-image into Noise For High-Fidelity Image Manipulation	-
2024	CVPR	GAN	Video Editing	In-N-Out: Faithful 3D GAN Inversion with Volumetric Decomposition for Face Editing	Code
2024	CVPR	DM	Video Editing	Video-P2P: Video Editing with Cross-attention Control	Code
2024	CVPR	DM	Video Editing	Space-Time Diffusion Features for Zero-Shot Text-Driven Motion Transfer	Code
2024	CVPR	DM	Video Editing	A Video is Worth 256 Bases: Spatial-Temporal Expectation-Maximization Inversion for Zero-Shot Video Editing	Code
2024	Arxiv	DM	Video Editing	Motion Inversion for Video Customization	Code
2024	ECCV	DM	Video Editing	DreamMover: Leveraging the Prior of Diffusion Models for Image Interpolation with Large Motion	Code
2024	ECCV	DM	Video Editing	Videoshop: Localized Semantic Video Editing with Noise-Extrapolated Diffusion Inversion	Code
2023	CVPR	GAN	Video Editing	VIVE3D: Viewpoint-Independent Video Editing using 3D-Aware GANs	Code
2023	ICCV	DM	Video Editing	FateZero: Fusing Attentions for Zero-shot Text-based Video Editing	Code
2023	ICCV	GAN	Video Editing	RIGID: Recurrent GAN Inversion and Editing of Real Face Videos	Code
2023	ICCV	GAN	Video Editing	StyleInV: A Temporal Style Modulated Inversion Network for Unconditional Video Generation	Code
2023	ICCV	DM	Video Editing	Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation	Code
2023	Arxiv	DM	Video Editing	Dreamix: Video Diffusion Models are General Video Editors	-
2023	ICCV	DM	Video Editing	Pix2Video: Video Editing using Image Diffusion	Code
2023	ICCV	DM	Video Editing	Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators	Code
2022	ECCV	GAN	Video Editing	Temporally Consistent Semantic Video Editing	-

3D

Year	Venue	Category	Task	Paper	Code
2025	CVPR	RF	3D Object Editing	SplatFlow: Multi-View Rectified Flow Model for 3D Gaussian Splatting Synthesis	code
2024	CVPR	GAN	3D Face Reconstruction	In-N-Out: Faithful 3D GAN Inversion with Volumetric Decomposition for Face Editing	Code
2024	CVPR	GAN	3D Face Reconstruction	Diffusion-driven GAN Inversion for Multi-Modal Face Image Generation	-
2024	CVPR	DM	3D Object Editing	SHAP-EDITOR: Instruction-Guided Latent 3D Editing in Seconds	Code
2024	ECCV	DM	3D Scene Editing	LatentEditor: Text Driven Local Editing of 3D Scenes	Code
2024	ECCV	GAN + DM	3D Face Reconstruction	Real-Time 3D-Aware Portrait Editing from a Single Image	Code
2023	WACV	GAN	3D Face Reconstruction	3D GAN Inversion with Pose Optimization	Code
2023	CVPR	GAN	3D Face Reconstruction	High-Fidelity 3D GAN Inversion by Pseudo-Multi-View Optimization	Code
2023	CVPR	GAN	3D Face Reconstruction	3D GAN Inversion With Facial Symmetry Prior	Code
2023	CVPR	GAN	3D Face Reconstruction	Self-Supervised Geometry-Aware Encoder for Style-Based 3D GAN Inversion	Code
2023	ICCV	DM	3D Scene Editing	Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions	Code

Audio

Year	Venue	Category	Task	Paper	Code
2024	IJCAI	DM	Audio Editing	MusicMagus: Zero-Shot Text-to-Music Editing via Diffusion Models	Code
2024	ICML	DM	Audio Editing	Zero-Shot Unsupervised and Text-Based Audio Editing Using DDPM Inversion	Code
2024	ICML	DM	Audio Editing	Prompt-guided Precise Audio Editing with Diffusion Models	-
2024	Arxiv	DM	Audio Editing	MEDIC: Zero-shot Music Editing with Disentangled Inversion Control	-
2024	Arxiv	DM	Audio Editing	AudioEditor: A Training-Free Diffusion-Based Audio Editing Framework	Code
2023	ICASSP	DM	Audio Restoration	Solving Audio Inverse Problems with a Diffusion Model	Code

Cite The Survey

If you find our survey and repository useful for your research projects, please consider citing our paper:

@article{chen2025imageinversion,
      title={Image Inversion: A Survey from GANs to Diffusion and Beyond}, 
      author={Yinan Chen and Jiangning Zhang and Yali Bi and Xiaobin Hu and Teng Hu and Zhucun Xue and Ran Yi and Yong Liu and Ying Tai},
      year={2025},
      journal={CoRR},
      url={https://arxiv.org/abs/2502.11974}, 
}

Contact

yinanchencs@outlook.com

186368@zju.edu.cn