Pith. sign in

REVIEW 4 cited by

FireFlow: Fast Inversion of Rectified Flow for Image Semantic Editing

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2412.07517 v1 pith:ADNDFDDO submitted 2024-12-10 cs.CV

Yingying Deng , Xiangyu He , Changwang Mei , Peisong Wang , Fan Tang This is my paper · ORCID
classification cs.CV
keywords inversioneditingfastfireflowsolverwhileaccuratereconstruction
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
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 $\href{https://github.com/HolmesShuan/FireFlow}{this URL}$.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

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

  1. ReFlex: Text-Guided Editing of Real Images in Rectified Flow via Mid-Step Feature Extraction and Attention Adaptation

    cs.CV 2025-07 conditional novelty 7.0 of 10

    ReFlex edits real images with FLUX by extracting attention and residual features from a mid-step latent and adapting them during generation, improving text alignment while preserving structure.

  2. DNAEdit: Direct Noise Alignment for Text-Guided Rectified Flow Editing

    cs.CV 2025-06 conditional novelty 7.0 of 10

    Direct Noise Alignment iteratively moves a random Gaussian noise until the model's predicted velocity matches the straight-line velocity to the image, reducing inversion drift and giving the best reported fidelity-edi...

  3. BiFM: Bidirectional Flow Matching for Few-Step Image Editing and Generation

    cs.CV 2026-03 conditional novelty 6.0 of 10

    A single flow-matching model can learn bidirectional average velocities under a shared instantaneous field and a consistency loss, improving few-step image editing and generation over prior few-step baselines.

  4. FlowSteer: Conditioning Flow Field for Consistent Image Restoration

    eess.IV 2025-12 conditional novelty 5.0 of 10

    A sparse mid-to-late schedule of null-space fidelity updates lets a frozen text-to-image flow model restore images with high measurement consistency.

Pith tools