Pith. sign in

REVIEW 28 cited by

Consistency Models Made Easy

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 2406.14548 v2 pith:3MCGYVRF submitted 2024-06-20 cs.LG cs.CV

Consistency Models Made Easy

classification cs.LG cs.CV
keywords consistencymodelstrainingdiffusionefficiencyachieveseasyexample
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Consistency models (CMs) offer faster sampling than traditional diffusion models, but their training is resource-intensive. For example, as of 2024, training a state-of-the-art CM on CIFAR-10 takes one week on 8 GPUs. In this work, we propose an effective scheme for training CMs that largely improves the efficiency of building such models. Specifically, by expressing CM trajectories via a particular differential equation, we argue that diffusion models can be viewed as a special case of CMs. We can thus fine-tune a consistency model starting from a pretrained diffusion model and progressively approximate the full consistency condition to stronger degrees over the training process. Our resulting method, which we term Easy Consistency Tuning (ECT), achieves vastly reduced training times while improving upon the quality of previous methods: for example, ECT achieves a 2-step FID of 2.73 on CIFAR10 within 1 hour on a single A100 GPU, matching Consistency Distillation trained for hundreds of GPU hours. Owing to this computational efficiency, we investigate the scaling laws of CMs under ECT, showing that they obey the classic power law scaling, hinting at their ability to improve efficiency and performance at larger scales. Our code (https://github.com/locuslab/ect) is publicly available, making CMs more accessible to the broader community.

discussion (0)

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

Forward citations

Cited by 28 Pith papers

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

  1. AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation

    cs.CV 2026-05 unverdicted novelty 8.0

    AnyFlow enables any-step video diffusion by distilling flow-map transitions over arbitrary time intervals with on-policy backward simulation.

  2. How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidance

    cs.LG 2026-04 unverdicted novelty 8.0

    FMRG reformulates guidance as deterministic optimal control, deriving a single-trajectory method using the flow map that matches or exceeds baselines on reward-guided generation and inverse problems with 3 NFEs at tex...

  3. Flow-Map GRPO: Reinforcement Learning for Few-Step Flow-Map Generators via Anchored Stochastic Composition

    cs.LG 2026-07 unverdicted novelty 7.0

    Flow-Map GRPO uses anchored stochastic flow map composition to enable GRPO-based RL alignment of deterministic few-step flow-map generators while preserving their marginal paths.

  4. How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidance

    cs.LG 2026-04 unverdicted novelty 7.0

    FMRG is a training-free, single-trajectory guidance method for flow models derived from optimal control that achieves strong reward alignment with only 3 NFEs.

  5. Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation

    cs.CV 2026-02 conditional novelty 7.0

    Causal Forcing distills few-step autoregressive video generators from an autoregressive diffusion teacher rather than a bidirectional one, avoiding conditional-expectation blur and beating Self Forcing on motion and q...

  6. Stream-DiffVSR: Low-Latency Streamable Video Super-Resolution via Auto-Regressive Diffusion

    cs.CV 2025-12 conditional novelty 7.0

    Stream-DiffVSR enables practical low-latency video super-resolution by combining a four-step distilled denoiser, auto-regressive temporal guidance, and a temporal processor in a strictly causal pipeline.

  7. One Step Diffusion via Shortcut Models

    cs.LG 2024-10 conditional novelty 7.0

    Shortcut models enable high-quality single or few-step sampling in diffusion models with one network and training phase by conditioning on desired step size.

  8. Amortized Moment Matching for Visual Generation

    cs.LG 2026-07 accept novelty 6.0

    Amortized Fréchet Distance uses neural nets to match conditional means and covariances, yielding stronger one-step visual generators than explicit FD-loss or multi-step teachers.

  9. Parallel Decoding Distillation for Fast Image and Video Generation

    cs.CV 2026-07 conditional novelty 6.0

    A trajectory-based distillation method trains a student to predict multiple mean velocities per network evaluation, enabling 4-8 step generation with competitive quality and improved diversity.

  10. From Draft to Draft-Free: One-Step Video Object Removal via Privileged Distillation and Fast Planting

    cs.CV 2026-07 conditional novelty 6.0

    A one-step, draft-free video object removal model trained by distilling a ground-truth-conditioned teacher reaches comparable or better quality than multi-step diffusion methods while running in about 1 second.

  11. Flash-WAM: Modality-Aware Distillation for World Action Models

    cs.LG 2026-06 unverdicted novelty 6.0

    Flash-WAM introduces modality-specific consistency parametrizations to distill joint video-action diffusion models to single-step inference, delivering 23x speedup with preserved benchmark performance.

  12. DCFold: Efficient Protein Structure Generation with Single Forward Pass

    cs.LG 2026-05 unverdicted novelty 6.0

    DCFold achieves AlphaFold3-level protein structure prediction accuracy in a single forward pass using Dual Consistency training and a Temporal Geodesic Matching scheduler, delivering 15x inference acceleration.

  13. A Few-Step Generative Model on Cumulative Flow Maps

    cs.LG 2026-05 unverdicted novelty 6.0

    Cumulative flow maps unify few-step generative modeling for diffusion and flow models via cumulative transport and parameterization with minimal changes to time embeddings and objectives.

  14. How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidance

    cs.LG 2026-04 unverdicted novelty 6.0

    FMRG is a training-free single-trajectory guidance framework for flow-based models that matches or exceeds baselines on reward-guided tasks and inverse problems using as few as 3 NFEs.

  15. Alice v1: Distillation-Enhanced Video Generation Surpassing Closed-Source Models

    cs.GR 2026-04 unverdicted novelty 6.0

    Alice v1 is an open video model that surpasses its teacher and closed-source systems like Veo3 and Sora2 in quality while running 7x faster through specialized distillation.

  16. Extending One-Step Image Generation from Class Labels to Text via Discriminative Text Representation

    cs.CV 2026-04 unverdicted novelty 6.0

    By requiring and using highly discriminative LLM text features, the work enables the first effective one-step text-conditioned image generation with MeanFlow.

  17. Dual-End Consistency Model

    cs.CV 2026-02 unverdicted novelty 6.0

    DE-CM reaches state-of-the-art one-step FID of 1.70 on ImageNet 256x256 by decomposing PF-ODE trajectories into three critical sub-trajectories and using flow matching plus N2N mapping for stability.

  18. Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation

    cs.CV 2026-02 conditional novelty 6.0

    Causal Forcing initializes autoregressive diffusion students from AR teachers to recover flow maps that bidirectional teachers cannot provide, delivering 19%+ gains over Self Forcing on dynamic degree and related metrics.

  19. Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation

    cs.CV 2026-02 conditional novelty 6.0

    Causal Forcing uses an autoregressive teacher for ODE initialization in diffusion distillation to close the causal attention gap and deliver better real-time video generation than Self Forcing.

  20. Transition Matching Distillation for Fast Video Generation

    cs.CV 2026-01 conditional novelty 6.0

    Splitting a video diffusion model into a fixed feature extractor and a small recurrent flow head lets TMD generate videos in one to two effective steps with better VBench scores than prior distilled models.

  21. Hierarchical Schedule Optimization for Fast and Robust Diffusion Model Sampling

    cs.LG 2025-11 unverdicted novelty 6.0

    HSO is a bi-level optimization method with Midpoint Error Proxy and Spacing-Penalized Fitness that finds robust timestep schedules for low-NFE diffusion sampling and reports SOTA FID scores such as 11.94 at NFE=5.

  22. Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistency

    cs.CV 2025-10 conditional novelty 6.0

    The work introduces rCM, a score-regularized continuous-time consistency model that matches DMD2 quality on large models up to 14B parameters while improving diversity and enabling 1-4 step sampling.

  23. MACS: Measurement-Aware Consistency Sampling for Inverse Problems

    eess.IV 2025-10 conditional novelty 6.0

    MACS replaces the variance term in aDDIM with a measurement residual, yielding better FID/KID than fast ODE baselines in two-step consistency-model inverse problems.

  24. Mean Flows for One-step Generative Modeling

    cs.LG 2025-05 unverdicted novelty 6.0

    MeanFlow uses a derived identity between average and instantaneous velocities to train one-step flow models, achieving FID 3.43 on ImageNet 256x256 with 1-NFE from scratch.

  25. SubFlow: Sub-mode Conditioned Flow Matching for Diverse One-Step Generation

    cs.LG 2026-04 unverdicted novelty 5.0

    SubFlow restores full mode coverage in one-step flow matching by conditioning on sub-modes from semantic clustering, yielding higher diversity on ImageNet-256 while preserving FID.

  26. Efficient Hierarchical Implicit Flow Q-learning for Offline Goal-conditioned Reinforcement Learning

    cs.LG 2026-04 unverdicted novelty 5.0

    Proposes mean flow policies and LeJEPA loss to overcome Gaussian policy limits and weak subgoal generation in hierarchical offline GCRL, reporting strong results on OGBench state and pixel tasks.

  27. Dual-End Consistency Model

    cs.CV 2026-02 conditional novelty 5.0

    DE-CM trains a flow-map consistency model on three sub-trajectories (coupling, instantaneous, noise-to-noisy) and reports 1.70 FID one-step on ImageNet 256.

  28. Discrete Meanflow Training Curriculum

    cs.LG 2026-04 unverdicted novelty 4.0

    A DMF curriculum initialized from pretrained flow models achieves one-step FID 3.36 on CIFAR-10 after only 2000 epochs by exploiting a discretized consistency property in the Meanflow objective.