FlashIn：面向实时图像编辑的快速精确图像反演
FlashIn: Fast and Accurate Image Inversion for Real-time Image Editing
把图像到初始噪声的映射做成可学习网络，用循环一致与对抗训练实现单步精确反演，可直接替换现有编辑流程中耗时的迭代反演环节，配合少步扩散模型做到秒级交互编辑。
原文依据 A learnable neural network directly maps an image to its corresponding noise.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论给定一张图像和一段描述性提示，图像反演旨在找出初始噪声，使其经去噪后能准确重建原图。这对图像编辑等应用至关重要，此类应用可通过用编辑后的提示对反演噪声进行去噪来实现。现有方法往往依赖近似，通常需要很多步，由于反演过程本身难以精确求解，导致不准确、处理缓慢以及伪影。为解决这些问题，本文提出 FlashIn，一种更快、更精确的图像反演新算法，可实现高质量实时编辑。FlashIn 有两项主要贡献：i）一个可学习的神经网络直接将图像映射到其对应噪声。该网络采用循环一致策略、利用生成数据和种子噪声进行训练，从而得到更高效、更精确的反演模型。ii）对抗训练使噪声重建的图像与真实图像对齐，提升反演精度与编辑质量。这些策略使反演过程能在单步内快速、准确地完成，并可通过增加步数进一步提升。与 Flux.1-Schnell 等少步扩散模型结合，本方法在单块 GPU 上可在一秒内完成高质量图像编辑，支持实时交互式编辑。大量实验表明，FlashIn 在多种场景与应用中均达到最优的反演精度并取得出色的编辑效果。
英文原文摘要 1536 字符
Given an image and a descriptive prompt, image inversion seeks to identify the initial noise that, when denoised, accurately reconstructs the original image. This is crucial for applications like image editing, which can be achieved by denoising the inverted noise with an edited prompt. Existing methods often rely on approximations. They often require many steps, leading to inaccuracies, slow processing, and artifacts due to the inherent intractability in the inversion process. To overcome these issues, in this work, we propose FlashIn, a novel algorithm for faster and more accurate image inversion, enabling high-quality, real-time editing. FlashIn offers two main contributions: i) A learnable neural network directly maps an image to its corresponding noise. Trained with a cycle-consistent strategy using generated data and seed noise, this approach yields a more efficient and precise inversion model. ii) Adversarial training aligns noise-reconstructed images with real ones, enhancing inversion accuracy and editing quality. These strategies enable a fast, accurate inversion process in a single step, with further improvements possible through additional steps. Integrated with few-step diffusion models such as Flux.1-Schnell, our method achieves high-quality image editing within one second on a single GPU, facilitating real-time, interactive editing. Extensive experiments demonstrate that FlashIn delivers state-of-the-art inversion precision and impressive editing results across various scenarios and applications.