FireFlow: Fast Inversion of Rectified Flow for Image Semantic Editing

• URL: http://arxiv.org/abs/2412.07517v1
• Date: Tue, 10 Dec 2024 13:56:26 GMT
• Title: FireFlow: Fast Inversion of Rectified Flow for Image Semantic Editing
• Abstract summary: FireFlow is a simple yet effective zero-shot approach that inherits the startling capacity of ReFlow-based models.<n>We first demonstrate that a carefully designed numerical solver is pivotal for ReFlow inversion.<n>This solver achieves a $3times$ runtime speedup compared to state-of-the-art ReFlow inversion and editing techniques.
• Score: 27.57630797294312
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Though Rectified Flows (ReFlows) with distillation offers a promising way for fast sampling, its fast inversion transforms images back to structured noise for recovery and following editing remains unsolved. This paper introduces FireFlow, a simple yet effective zero-shot approach that inherits the startling capacity of ReFlow-based models (such as FLUX) in generation while extending its capabilities to accurate inversion and editing in $8$ steps. We first demonstrate that a carefully designed numerical solver is pivotal for ReFlow inversion, enabling accurate inversion and reconstruction with the precision of a second-order solver while maintaining the practical efficiency of a first-order Euler method. This solver achieves a $3\times$ runtime speedup compared to state-of-the-art ReFlow inversion and editing techniques, while delivering smaller reconstruction errors and superior editing results in a training-free mode. The code is available at $\href{https://github.com/HolmesShuan/FireFlow}{this URL}$.

Related papers

• ScaleResfusion: Residual Rectified Flow based on Residual Vector Field [24.544037828084154]
  Real-world Image Restoration (Real-IR) aims to recover high-quality (HQ) images from complex and unknown degradations.<n>Recent diffusion-based methods have substantially improved perceptual quality, but their current designs leave two key challenges unresolved.<n>We present ScaleResfusion, a scalable diffusion framework for real-world image restoration built on pre-trained text-to-image rectified-flow models.
  arXiv  Detail & Related papers  (2026-07-28T04:26:05Z)
• SlerpFlow: Spherical Trajectory Correction for Rectified Flow Inversion [9.245733921560813]
  SlerpFlow is a zero-shot approach for high-fidelity inversion and editing.<n>SlerpFlow integrates Spherical Linear Interpolation (Slerp) to rectify flow velocity directions on the hypersphere.<n>Experiments on FLUX-based reconstruction and editing tasks demonstrate that SlerpFlow improves reconstruction fidelity and stronger semantic alignment.
  arXiv  Detail & Related papers  (2026-07-23T13:55:21Z)
• AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation [70.80207977907908]
  We introduce AnyFlow, the first any-step video diffusion distillation framework based on flow maps.<n>We show that AnyFlow achieves performance matches or surpasses consistency-based counterparts in the few-step regime.
  arXiv  Detail & Related papers  (2026-05-13T16:06:34Z)
• FastFlow: Accelerating The Generative Flow Matching Models with Bandit Inference [10.34801095627052]
  Flow-matching models deliver state-of-the-art fidelity in image and video generation, but the inherent sequential denoising process renders them slower.<n>We propose FastFlow, a plug-and-play adaptive inference framework that accelerates generation in flow matching models.<n> Experiments demonstrate a speedup of over 2.6x while maintaining high-quality outputs.
  arXiv  Detail & Related papers  (2026-02-11T18:21:11Z)
• Trajectory Stitching for Solving Inverse Problems with Flow-Based Models [68.36374645801901]
  Flow-based generative models have emerged as powerful priors for solving inverse problems.<n>We propose MS-Flow, which represents the trajectory as a sequence of intermediate latent states rather than a single initial code.<n>We demonstrate the effectiveness of MS-Flow over existing methods on image recovery and inverse problems, including inpainting, super-resolution, and computed tomography.
  arXiv  Detail & Related papers  (2026-02-09T11:36:41Z)
• Flow Straighter and Faster: Efficient One-Step Generative Modeling via MeanFlow on Rectified Trajectories [14.36205662558203]
  Rectified MeanFlow is a framework that models the mean velocity field along the rectified trajectory using only a single reflow step.<n>Experiments on ImageNet at 64, 256, and 512 resolutions show that Re-MeanFlow consistently outperforms prior one-step flow distillation and Rectified Flow methods in both sample quality and training efficiency.
  arXiv  Detail & Related papers  (2025-11-28T16:50:08Z)
• FlowOpt: Fast Optimization Through Whole Flow Processes for Training-Free Editing [37.12178941086993]
  FlowOpt is a zero-order (gradient-free) optimization framework that treats the entire flow process as a black box.<n>We show how FlowOpt can be used for image editing, showcasing two options: (i) inversion (determining the initial noise that generates a given image), and (ii) directly steering the edited image to be similar to the source image.
  arXiv  Detail & Related papers  (2025-10-24T20:24:26Z)
• ProReflow: Progressive Reflow with Decomposed Velocity [52.249464542399636]
  Flow matching aims to reflow the diffusion process of diffusion models into a straight line for a few-step and even one-step generation. We introduce progressive reflow, which progressively reflows the diffusion models in local timesteps until the whole diffusion progresses. We also introduce aligned v-prediction, which highlights the importance of direction matching in flow matching over magnitude matching.
  arXiv  Detail & Related papers  (2025-03-05T04:50:53Z)
• Taming Rectified Flow for Inversion and Editing [57.3742655030493]
  Rectified-flow-based diffusion transformers like FLUX and OpenSora have demonstrated outstanding performance in the field of image and video generation.<n>Despite their robust generative capabilities, these models often struggle with inaccuracies.<n>We propose RF-r, a training-free sampler that effectively enhances inversion precision by mitigating the errors in the inversion process of rectified flow.
  arXiv  Detail & Related papers  (2024-11-07T14:29:02Z)
• Simple ReFlow: Improved Techniques for Fast Flow Models [68.32300636049008]
  Diffusion and flow-matching models achieve remarkable generative performance but at the cost of many sampling steps. We propose seven improvements for training dynamics, learning and inference. We achieve state-of-the-art FID scores (without / with guidance, resp.) for fast generation via neural ODEs.
  arXiv  Detail & Related papers  (2024-10-10T11:00:55Z)
• Rectified Diffusion: Straightness Is Not Your Need in Rectified Flow [65.51671121528858]
  Diffusion models have greatly improved visual generation but are hindered by slow generation speed due to the computationally intensive nature of solving generative ODEs. Rectified flow, a widely recognized solution, improves generation speed by straightening the ODE path. We propose Rectified Diffusion, which generalizes the design space and application scope of rectification to encompass the broader category of diffusion models.
  arXiv  Detail & Related papers  (2024-10-09T17:43:38Z)
• COT Flow: Learning Optimal-Transport Image Sampling and Editing by Contrastive Pairs [7.542892664684078]
  Contrastive Optimal Transport Flow (COT Flow) is a new method that achieves fast and high-quality generation with improved zero-shot editing flexibility. In terms of quality, COT Flow can generate competitive results in merely one step compared to previous state-of-the-art unpaired image-to-image (I2I) translation methods. COT Flow can generate competitive results in merely one step compared to previous state-of-the-art unpaired image-to-image (I2I) translation methods.
  arXiv  Detail & Related papers  (2024-06-17T23:02:20Z)
• Improving the Training of Rectified Flows [14.652876697052156]
  Diffusion models have shown great promise for image and video generation, but sampling from state-of-the-art models requires expensive numerical integration of a generative ODE. One approach for tackling this problem is rectified flows, which iteratively learn smooth ODE paths that are less susceptible to truncation error. We propose improved techniques for training rectified flows, allowing them to compete with emphknowledge distillation methods even in the low NFE setting. Our improved rectified flow outperforms the state-of-the-art distillation methods such as consistency distillation and progressive distillation in both one-step and two
  arXiv  Detail & Related papers  (2024-05-30T17:56:04Z)
• Lightning-Fast Image Inversion and Editing for Text-to-Image Diffusion Models [46.729930784279645]
  We formulate the problem by finding the roots of an implicit equation and devlop a method to solve it efficiently. Our solution is based on Newton-Raphson (NR), a well-known technique in numerical analysis. We show improved results in image and generation of rare objects.
  arXiv  Detail & Related papers  (2023-12-19T19:19:19Z)
• InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation [33.70116170511312]
  We propose a novel text-conditioned pipeline to turn Stable Diffusion (SD) into an ultra-fast one-step model. We create the first one-step diffusion-based text-to-image generator with SD-level image quality, achieving an FID of $23.3$ on MS COCO 2017-5k.
  arXiv  Detail & Related papers  (2023-09-12T16:42:09Z)
• GMFlow: Learning Optical Flow via Global Matching [124.57850500778277]
  We propose a GMFlow framework for learning optical flow estimation. It consists of three main components: a customized Transformer for feature enhancement, a correlation and softmax layer for global feature matching, and a self-attention layer for flow propagation. Our new framework outperforms 32-iteration RAFT's performance on the challenging Sintel benchmark.
  arXiv  Detail & Related papers  (2021-11-26T18:59:56Z)
• DeFlow: Learning Complex Image Degradations from Unpaired Data with Conditional Flows [145.83812019515818]
  We propose DeFlow, a method for learning image degradations from unpaired data. We model the degradation process in the latent space of a shared flow-decoder network. We validate our DeFlow formulation on the task of joint image restoration and super-resolution.
  arXiv  Detail & Related papers  (2021-01-14T18:58:01Z)
• LiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimation [99.19322851246972]
  We introduce LiteFlowNet3, a deep network consisting of two specialized modules to address the problem of optical flow estimation. LiteFlowNet3 not only achieves promising results on public benchmarks but also has a small model size and a fast runtime.
  arXiv  Detail & Related papers  (2020-07-18T03:30:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.