mlsanityData to 14 Oct 2026

SCott: Accelerating Diffusion Models with Stochastic Consistency Distillation

arXiv 2403.01505 ↗First posted 3 Mar 2024cs.CVcited by 14

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

The iterative sampling procedure employed by diffusion models (DMs) often leads to significant inference latency. To address this, we propose Stochastic Consistency Distillation (SCott) to enable accelerated text-to-image generation, where high-quality and diverse generations can be achieved within just 2-4 sampling steps. In contrast to vanilla consistency distillation (CD) which distills the ordinary differential equation solvers-based sampling process of a pre-trained teacher model into a student, SCott explores the possibility and validates the efficacy of integrating stochastic differential equation (SDE) solvers into CD to fully unleash the potential of the teacher. SCott is augmented with elaborate strategies to control the noise strength and sampling process of the SDE solver. An adversarial loss is further incorporated to strengthen the consistency constraints in rare sampling steps. Empirically, on the MSCOCO-2017 5K dataset with a Stable Diffusion-V1.5 teacher, SCott achieves an FID of 21.9 with 2 sampling steps, surpassing that of the 1-step InstaFlow (23.4) and the 4-step UFOGen (22.1). Moreover, SCott can yield more diverse samples than other consistency models for high-resolution image generation, with up to 16% improvement in a qualified metric.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 49 of its 54 references that are in the map. First posted on arXiv 3 Mar 2024.

Builds on

49 of 54 references.

Closest ancestors · 26

Same direction, newest first

  1. 2023One-step Diffusion with Distribution Matching Distillation30 Nov
  2. 2023Adversarial Diffusion Distillation28 Nov
  3. 2023Improved Techniques for Training Consistency Models22 Oct
  4. 2023Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference6 Oct
  5. 2023Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion1 Oct
  6. 2023Elucidating the solution space of extended reverse-time SDE for diffusion models12 Sep
  7. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis4 Jul
  8. 2023Restart Sampling for Improving Generative Processes26 Jun
  9. 2023Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion Models29 May
  10. 2023SEEDS: Exponential SDE Solvers for Fast High-Quality Sampling from Diffusion Models23 May
  11. 2023Consistency Models2 Mar
  12. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models2 Nov
14 more
  1. 2022On Distillation of Guided Diffusion Models6 Oct
  2. 2022Classifier-Free Diffusion Guidance26 Jul
  3. 2022A Study on the Evaluation of Generative Models22 Jun
  4. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps2 Jun
  5. 2022Elucidating the Design Space of Diffusion-Based Generative Models1 Jun
  6. 2022Fast Sampling of Diffusion Models with Exponential Integrator29 Apr
  7. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  8. 2021Tackling the Generative Learning Trilemma with Denoising Diffusion GANs15 Dec
  9. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  10. 2021Maximum Likelihood Training of Score-Based Diffusion Models22 Jan
  11. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  12. 2020Denoising Diffusion Implicit Models6 Oct
  13. 2020Denoising Diffusion Probabilistic Models19 Jun
  14. 2020Improved Techniques for Training Score-Based Generative Models16 Jun

Other references · 23

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  4. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  5. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  6. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  7. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
  8. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  9. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  10. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,025
  11. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,424
  12. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,245
11 more
  1. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,937
  2. 2022Imagen Video: High Definition Video Generation with Diffusion Modelscited by 1,778
  3. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Modelscited by 1,476
  4. 2023T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Modelscited by 1,351
  5. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,219
  6. 2020Reliable Fidelity and Diversity Metrics for Generative Modelscited by 434
  7. 2023InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generationcited by 395
  8. 2023Subject-driven Text-to-Image Generation via Apprenticeship Learningcited by 212
  9. 2023UFOGen: You Forward Once Large Scale Text-to-Image Generation via Diffusion GANscited by 166
  10. 2023SwiftBrush: One-Step Text-to-Image Diffusion Model with Variational Score Distillationcited by 110
  11. 2023ControlStyle: Text-Driven Stylized Image Generation Using Diffusion Priorscited by 40

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 6; 2025: 6; 2026: 2.

14 papers.

Sort:

By area:

  1. 2025Align Your Flow: Scaling Continuous-Time Flow Map Distillationcited by 87
  2. 2024One-Step Diffusion Distillation through Score Implicit Matchingcited by 71
  3. 2024Diff-Instruct++: Training One-step Text-to-image Generator Model to Align with Human Preferencescited by 31
  4. 2024PaGoDA: Progressive Growing of a One-Step Generator from a Low-Resolution Diffusion Teachercited by 27
  5. 2024Flow Generator Matchingcited by 26
  6. 2025Efficient-vDiT: Efficient Video Diffusion Transformers With Attention Tilecited by 26
  7. 2025Dual-Expert Consistency Model for Efficient and High-Quality Video Generationcited by 21
  8. 2025Uni-Instruct: One-step Diffusion Model through Unified Diffusion Divergence Instructioncited by 13
  9. 2025Two-Steps Diffusion Policy for Robotic Manipulation via Genetic Denoisingcited by 8
  10. 2024Multi-scale Latent Point Consistency Models for 3D Shape Generationcited by 7
  11. 2024See Further When Clear: Curriculum Consistency Modelcited by 6
  12. 2025On Efficiency-Effectiveness Trade-off of Diffusion-based Recommenderscited by 3
2 more
  1. 2026MRI Cross-Modal Synthesis: A Comparative Study of Generative Models for T1-to-T2 Reconstructioncited by 1
  2. 2026From Competition to Coopetition: Coopetitive Training-Free Image Editing Based on Text Guidancecited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026Consistent Distribution Matching for Data-Free Diffusion Distillation
  2. 2024SFDDM: Single-fold Distillation for Diffusion models
  3. 2024Diffusion Models Are Innate One-Step Generators
  4. 2025ETC: training-free diffusion models acceleration with Error-aware Trend Consistency
  5. 2024Truncated Consistency Models
  6. 2025Scale-wise Distillation of Diffusion Models
  7. 2024Consistency Diffusion Bridge Models
  8. 2024DDIL: Diversity Enhancing Diffusion Distillation With Imitation Learning