Pith. sign in

REVIEW 11 cited by

PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator

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 2405.07510 v5 pith:UEGUKYFN submitted 2024-05-13 cs.LG

Hanshu Yan , Xingchao Liu , Jiachun Pan , Jun Hao Liew , Qiang Liu , Jiashi Feng This is my paper · ORCID
classification cs.LG
keywords modelsperflowdiffusionpiecewiseflowflowsplug-and-playrectified
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

We present Piecewise Rectified Flow (PeRFlow), a flow-based method for accelerating diffusion models. PeRFlow divides the sampling process of generative flows into several time windows and straightens the trajectories in each interval via the reflow operation, thereby approaching piecewise linear flows. PeRFlow achieves superior performance in a few-step generation. Moreover, through dedicated parameterizations, the PeRFlow models inherit knowledge from the pretrained diffusion models. Thus, the training converges fast and the obtained models show advantageous transfer ability, serving as universal plug-and-play accelerators that are compatible with various workflows based on the pre-trained diffusion models. Codes for training and inference are publicly released. https://github.com/magic-research/piecewise-rectified-flow

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 11 Pith papers

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

  1. Noise Consistency Training: A Native Approach for One-Step Generator in Learning Additional Controls

    cs.LG 2025-06 conditional novelty 7.0 of 10

    Noise Consistency Training adds new controls to pre-trained one-step generators by training a lightweight adapter with a noise-space consistency loss, matching conditional generation quality at a fraction of the compute.

  2. M4V: Multimodal Mamba for Efficient Text-to-Video Generation

    cs.CV 2025-06 conditional novelty 6.0 of 10

    M4V shows a Mamba-based text-to-video model can roughly match attention-based PyramidFlow on VBench while cutting mixer-layer FLOPs by 45% at 768x1280.

  3. FADA: Fast Diffusion Avatar Synthesis with Mixed-Supervised Multi-CFG Distillation

    cs.CV 2024-12 conditional novelty 6.0 of 10

    FADA distills a diffusion-based talking avatar model into a 6-step student that mimics multi-condition classifier-free guidance with learnable tokens, achieving 4.17 to 12.5 times NFE speedup with comparable quality.

  4. Adversarial Diffusion Compression for Real-World Image Super-Resolution

    eess.IV 2024-11 conditional novelty 6.0 of 10

    AdcSR distills OSEDiff into a pruned diffusion-GAN that cuts inference time 3.7x and parameters 74% while achieving comparable super-resolution quality.

  5. Flow Diverse and Efficient: Learning Momentum Flow Matching via Stochastic Velocity Field Sampling

    cs.CV 2025-06 conditional novelty 5.0 of 10

    Momentum Flow perturbs rectified flow velocities with a decaying random component and shows improved FID and recall on CelebA-HQ with half the sampling steps.

  6. Variational Rectified Flow Matching

    cs.LG 2025-02 conditional novelty 5.0 of 10

    Variational rectified flow matching uses a latent variable to capture multi-modal velocity fields, improving generation quality and enabling controllable sampling.

  7. EditScout: Locating Forged Regions from Diffusion-based Edited Images with Multimodal LLM

    cs.CV 2024-12 conditional novelty 5.0 of 10

    A multimodal LLM with a SAM-based mask decoder localizes diffusion-edited regions better than traditional forensic methods on MagicBrush, CocoGLIDE, and a new BrushNet dataset.

  8. NitroFusion: High-Fidelity Single-Step Diffusion through Dynamic Adversarial Training

    cs.CV 2024-12 conditional novelty 5.0 of 10

    NitroFusion trains one-step diffusion models using a dynamic pool of noise-specialized discriminator heads, achieving better aesthetic scores but mixed FID results compared with prior one-step distillation.

  9. Efficient Difficulty-Aware Dynamic Routing for Diffusion-Based Real-World Image Super-Resolution

    cs.CV 2026-07 reject novelty 4.0 of 10

    DDR-SR routes each real-world low-resolution image to one of two diffusion experts based on a high-frequency-loss difficulty score, using a low-compression VAE for hard images and a high-compression VAE for easy image...

  10. Force Matching with Relativistic Constraints: A Physics-Inspired Approach to Stable and Efficient Generative Modeling

    cs.LG 2025-02 reject novelty 4.0 of 10

    Force Matching replaces velocity matching in flow-based generative models with a relativistic force objective, but the toy experiments are designed so the model class matches the data generator exactly.

  11. One Diffusion Step to Real-World Super-Resolution via Flow Trajectory Distillation

    cs.CV 2025-02 conditional novelty 4.0 of 10

    FluxSR distills the 12B-parameter FLUX.1-dev model into a one-step real-world super-resolution model with flow trajectory matching, reporting top no-reference perceptual scores and lower full-reference fidelity.

Pith tools