# Oscillation Inversion: Understand the structure of Large Flow Model through the Lens of Inversion Method

arXiv: https://arxiv.org/abs/2411.11135 · HTML: https://mlsanity.com/paper/2411.11135/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 31 of its 37 references that are in the map.
- First posted on arXiv 17 Nov 2024.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 30 of 31)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Neural Ordinary Differential Equations](https://mlsanity.com/paper/1806.07366/) (2018)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://mlsanity.com/paper/2108.01073/) (2021)
- [Consistency Models](https://mlsanity.com/paper/2303.01469/) (2023)
- [IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2308.06721/) (2023)
- [Null-text Inversion for Editing Real Images using Guided Diffusion Models](https://mlsanity.com/paper/2211.09794/) (2022)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2108.02938/) (2021)
- [EDICT: Exact Diffusion Inversion via Coupled Transformations](https://mlsanity.com/paper/2211.12446/) (2022)
- [Generative Diffusion Prior for Unified Image Restoration and Enhancement](https://mlsanity.com/paper/2304.01247/) (2023)
- [Negative-prompt Inversion: Fast Image Inversion for Editing with Text-guided Diffusion Models](https://mlsanity.com/paper/2305.16807/) (2023)
- [ReNoise: Real Image Inversion Through Iterative Noising](https://mlsanity.com/paper/2403.14602/) (2024)
- [Parallel Diffusion Models of Operator and Image for Blind Inverse Problems](https://mlsanity.com/paper/2211.10656/) (2022)
- [Improving Tuning-Free Real Image Editing with Proximal Guidance](https://mlsanity.com/paper/2306.05414/) (2023)
- [Effective Real Image Editing with Accelerated Iterative Diffusion Inversion](https://mlsanity.com/paper/2309.04907/) (2023)
- [Zero-shot Image Editing with Reference Imitation](https://mlsanity.com/paper/2406.07547/) (2024)
- [On Exact Inversion of DPM-Solvers](https://mlsanity.com/paper/2311.18387/) (2023)
- [Stable-Makeup: When Real-World Makeup Transfer Meets Diffusion Model](https://mlsanity.com/paper/2403.07764/) (2024)
- [Exact Diffusion Inversion via Bi-directional Integration Approximation](https://mlsanity.com/paper/2307.10829/) (2023)
- [Blind Image Restoration via Fast Diffusion Inversion](https://mlsanity.com/paper/2405.19572/) (2024)
- [Source Prompt Disentangled Inversion for Boosting Image Editability with Diffusion Models](https://mlsanity.com/paper/2403.11105/) (2024)
- [Content-Style Decoupling for Unsupervised Makeup Transfer without Generating Pseudo Ground Truth](https://mlsanity.com/paper/2405.17240/) (2024)

## Built on by (most cited first, 4 of 4)

- [Training-Free Text-Guided Image Editing with Visual Autoregressive Model](https://mlsanity.com/paper/2503.23897/) (2025)
- [GenHSI: Controllable Generation of Human-Scene Interaction Videos](https://mlsanity.com/paper/2506.19840/) (2025)
- [Art3D: Training-Free 3D Generation from Flat-Colored Illustration](https://mlsanity.com/paper/2504.10466/) (2025)
- [Mastering Regional 3DGS: Locating, Initializing, and Editing with Diverse 2D Priors](https://mlsanity.com/paper/2507.05426/) (2025)

## Abstract (arXiv)

We explore the oscillatory behavior observed in inversion methods applied to large-scale text-to-image diffusion models, with a focus on the "Flux" model. By employing a fixed-point-inspired iterative approach to invert real-world images, we observe that the solution does not achieve convergence, instead oscillating between distinct clusters. Through both toy experiments and real-world diffusion models, we demonstrate that these oscillating clusters exhibit notable semantic coherence. We offer theoretical insights, showing that this behavior arises from oscillatory dynamics in rectified flow models. Building on this understanding, we introduce a simple and fast distribution transfer technique that facilitates image enhancement, stroke-based recoloring, as well as visual prompt-guided image editing. Furthermore, we provide quantitative results demonstrating the effectiveness of our method for tasks such as image enhancement, makeup transfer, reconstruction quality, and guided sampling quality. Higher-quality examples of videos and images are available at hrefhttps://yanyanzheng96.github.io/oscillationinversion/this link.