The reviewed record of science sign in
Pith

arxiv: 2412.08629 · v2 · pith:IFGB4JQE · submitted 2024-12-11 · cs.CV · cs.LG

FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models

Vladimir Kulikov , Matan Kleiner , Inbar Huberman-Spiegelglas , Tomer Michaeli This is my paper

Reviewed by Pithpith:IFGB4JQEopen to challenge →

classification cs.CV cs.LG
keywords editingflowmodelpre-trainedresultscorrespondingdiffusionflowedit
0
0 comments X
read the original abstract

Editing real images using a pre-trained text-to-image (T2I) diffusion/flow model often involves inverting the image into its corresponding noise map. However, inversion by itself is typically insufficient for obtaining satisfactory results, and therefore many methods additionally intervene in the sampling process. Such methods achieve improved results but are not seamlessly transferable between model architectures. Here, we introduce FlowEdit, a text-based editing method for pre-trained T2I flow models, which is inversion-free, optimization-free and model agnostic. Our method constructs an ODE that directly maps between the source and target distributions (corresponding to the source and target text prompts) and achieves a lower transport cost than the inversion approach. This leads to state-of-the-art results, as we illustrate with Stable Diffusion 3 and FLUX. Code and examples are available on the project's webpage.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 12 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. RevealLayer: Disentangling Hidden and Visible Layers via Occlusion-Aware Image Decomposition

    cs.CV 2026-05 unverdicted novelty 7.0

    RevealLayer decomposes natural images into multiple RGBA layers using diffusion models with region-aware attention, occlusion-guided adaptation, and a composite loss, outperforming prior methods on a new benchmark dataset.

  2. Velocity-Space 3D Asset Editing

    cs.GR 2026-05 unverdicted novelty 7.0

    VS3D performs local 3D asset editing by injecting reconstruction-anchored source signals, partial-mean guidance, and twin-agreement residuals into the velocity sampler to control edit strength and preserve identity.

  3. Exploring Cross-Modal Flows for Few-Shot Learning

    cs.CV 2025-10 unverdicted novelty 7.0

    FMA introduces flow matching for multi-step cross-modal feature alignment in few-shot learning, using fixed coupling, noise augmentation, and early-stopping to outperform one-step PEFT methods.

  4. Delta Rectified Flow Sampling for Text-to-Image Editing

    cs.CV 2025-09 unverdicted novelty 7.0

    DRFS is a new inversion-free editing technique for rectified flow models that models source-target velocity discrepancies and applies a time-dependent shift to improve fidelity and unify prior methods like DDS and FlowEdit.

  5. In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer

    cs.CV 2025-04 unverdicted novelty 7.0

    ICEdit achieves state-of-the-art instructional image editing in Diffusion Transformers via in-context generation, requiring only 0.1% of prior training data and 1% trainable parameters.

  6. StreamEdit: Training-Free Video Editing via Few-Step Streaming Video Generation

    cs.CV 2026-05 unverdicted novelty 6.0

    StreamGVE enables high-quality training-free video editing by converting the task to noise-to-data streaming generation with dual-branch fast sampling, self-attention bridges, cross-attention grounding, source-oriente...

  7. StreamEdit: Training-Free Video Editing via Few-Step Streaming Video Generation

    cs.CV 2026-05 unverdicted novelty 6.0

    StreamEdit enables high-quality training-free video editing by adapting streaming video generation models with dual-branch fast sampling, self-attention bridge, cross-attention grounding, source-oriented guidance, and...

  8. VAGS: Velocity Adaptive Guidance Scale for Image Editing and Generation

    cs.CV 2026-05 accept novelty 6.0

    VAGS adapts the CFG scale at each ODE step using velocity alignment signals to raise structural fidelity in editing and sample quality in generation over fixed-scale baselines.

  9. Zero-Shot Generative De-identification: Inversion-Free Flow for Privacy-Preserving Skin Image Analysis

    cs.CV 2026-01 unverdicted novelty 6.0

    Zero-shot inversion-free flow method de-identifies skin images in under 20 seconds while preserving pathological features with IoU stability exceeding 0.67 using segment-by-synthesis and CIELAB decoupling.

  10. Training-Free Reward-Guided Image Editing via Trajectory Optimal Control

    cs.CV 2025-09 unverdicted novelty 6.0

    A trajectory optimal control framework for reward-guided image editing in diffusion models that balances reward maximization with source fidelity better than prior inversion-based baselines.

  11. FlashEdit: Decoupling Speed, Structure, and Semantics for Precise Image Editing

    cs.CV 2025-09 conditional novelty 6.0

    FlashEdit delivers real-time localized text-guided image editing under 0.2 seconds via cycle-consistent one-step inversion, background shield, and sparsified spatial cross-attention, achieving over 150x speedup on PIE-Bench.

  12. BindEdit: Taming Attention Leakage for Precise Multi-Object Image Editing

    cs.CV 2026-06 unverdicted novelty 5.0

    BindEdit suppresses two forms of attention leakage in diffusion-based editing by binding target tokens to regions, rebalancing cross-attention, and adding a region fidelity term, plus a new multi-object benchmark.