Pith. sign in

REVIEW 3 cited by

Simple ReFlow: Improved Techniques for Fast Flow Models

Not yet reviewed by Pith; the record is open.

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 2410.07815 v1 pith:FKOWDYPJ submitted 2024-10-10 cs.LG cs.CV

classification cs.LGcs.CV
keywords reflowtimesachieveafhqv2cifar10fastffhqgeneration
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
abstract

Diffusion and flow-matching models achieve remarkable generative performance but at the cost of many sampling steps, this slows inference and limits applicability to time-critical tasks. The ReFlow procedure can accelerate sampling by straightening generation trajectories. However, ReFlow is an iterative procedure, typically requiring training on simulated data, and results in reduced sample quality. To mitigate sample deterioration, we examine the design space of ReFlow and highlight potential pitfalls in prior heuristic practices. We then propose seven improvements for training dynamics, learning and inference, which are verified with thorough ablation studies on CIFAR10 $32 \times 32$, AFHQv2 $64 \times 64$, and FFHQ $64 \times 64$. Combining all our techniques, we achieve state-of-the-art FID scores (without / with guidance, resp.) for fast generation via neural ODEs: $2.23$ / $1.98$ on CIFAR10, $2.30$ / $1.91$ on AFHQv2, $2.84$ / $2.67$ on FFHQ, and $3.49$ / $1.74$ on ImageNet-64, all with merely $9$ neural function evaluations.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

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

  1. IB-Flow: Information Bottleneck-Guided CFG Distillation for Few-Step Text-to-Image Generation

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Information-Bottleneck closed forms for adaptive CFG supervisor timestep and strength yield SOTA 2-NFE text-to-image fidelity across FLUX, OpenUni, and Qwen-Image.

  2. SnapGen-V: Generating a Five-Second Video within Five Seconds on a Mobile Device

    cs.CV 2024-12 conditional novelty 6.0 of 10

    SnapGen-V prunes, searches, and adversarially distills a video diffusion model down to 0.6B parameters that generates a five-second, 512x512 video on an iPhone 16 Pro Max in under five seconds.

  3. Latent Schrodinger Bridge: Prompting Latent Diffusion for Fast Unpaired Image-to-Image Translation

    cs.CV 2024-11 conditional novelty 5.0 of 10

    Using prompt optimization and an SNR-matching change of variables, pretrained Stable Diffusion can approximate the source, target, and noise predictors of a Schrödinger bridge ODE, enabling 8-step unpaired image translation.

Pith tools