mlsanityData to 14 Oct 2026

LCM-LoRA: A Universal Stable-Diffusion Acceleration Module

arXiv 2311.05556 ↗First posted 9 Nov 2023cs.CV cs.LGcited by 211

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Latent Consistency Models (LCMs) have achieved impressive performance in accelerating text-to-image generative tasks, producing high-quality images with minimal inference steps. LCMs are distilled from pre-trained latent diffusion models (LDMs), requiring only ~32 A100 GPU training hours. This report further extends LCMs' potential in two aspects: First, by applying LoRA distillation to Stable-Diffusion models including SD-V1.5, SSD-1B, and SDXL, we have expanded LCM's scope to larger models with significantly less memory consumption, achieving superior image generation quality. Second, we identify the LoRA parameters obtained through LCM distillation as a universal Stable-Diffusion acceleration module, named LCM-LoRA. LCM-LoRA can be directly plugged into various Stable-Diffusion fine-tuned models or LoRAs without training, thus representing a universally applicable accelerator for diverse image generation tasks. Compared with previous numerical PF-ODE solvers such as DDIM, DPM-Solver, LCM-LoRA can be viewed as a plug-in neural PF-ODE solver that possesses strong generalization abilities. Project page: https://github.com/luosiallen/latent-consistency-model.

Key facts. Cited by 211 papers in the map (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 16 of its 19 references that are in the map. First posted on arXiv 9 Nov 2023.

Builds on

16 of 19 references.

Closest ancestors · 9

Same direction, newest first

  1. 2023Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference6 Oct
  2. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis4 Jul
  3. 2023Consistency Models2 Mar
  4. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models2 Nov
  5. 2022On Distillation of Guided Diffusion Models6 Oct
  6. 2022Classifier-Free Diffusion Guidance26 Jul
  7. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps2 Jun
  8. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  9. 2020Denoising Diffusion Implicit Models6 Oct

Other references · 7

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  2. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,236
  3. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
  4. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,355
  5. 2022Editing Models with Task Arithmeticcited by 1,120
  6. 2023Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Modelscited by 221
  7. 2023Composing Parameter-Efficient Modules with Arithmetic Operationscited by 156

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 14; 2024: 100; 2025: 57; 2026: 40.

211 papers.

Sort:

By area:

  1. 2023One-step Diffusion with Distribution Matching Distillationcited by 1,019
  2. 2023Adversarial Diffusion Distillationcited by 759
  3. 2024Improved Distribution Matching Distillation for Fast Image Synthesiscited by 684
  4. 2024Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Surveycited by 656
  5. 2024Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillationcited by 279
  6. 2024SDXL-Lightning: Progressive Adversarial Diffusion Distillationcited by 266
  7. 2024One-Step Effective Diffusion Network for Real-World Image Super-Resolutioncited by 246
  8. 2023LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenescited by 231
  9. 2024Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generationcited by 214
  10. 2024ControlNeXt: Powerful and Efficient Control for Image and Video Generationcited by 159
  11. 2025Diffusion Adversarial Post-Training for One-Step Video Generationcited by 151
  12. 2024PIXART-δ: Fast and Controllable Image Generation with Latent Consistency Modelscited by 141
38 more
  1. 2024Localizing Task Information for Improved Model Merging and Compressioncited by 131
  2. 2024ReNoise: Real Image Inversion Through Iterative Noisingcited by 128
  3. 2024DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Modelscited by 98
  4. 2024PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Acceleratorcited by 97
  5. 2023VideoLCM: Video Latent Consistency Modelcited by 92
  6. 2024T2V-Turbo: Breaking the Quality Bottleneck of Video Consistency Model with Mixed Reward Feedbackcited by 87
  7. 2024Dreamitate: Real-World Visuomotor Policy Learning via Video Generationcited by 87
  8. 2025Align Your Flow: Scaling Continuous-Time Flow Map Distillationcited by 87
  9. 2024V-Express: Conditional Dropout for Progressive Training of Portrait Video Generationcited by 86
  10. 2024Distilling Diffusion Models into Conditional GANscited by 78
  11. 2024An Overview of Diffusion Models: Applications, Guided Generation, Statistical Rates and Optimizationcited by 73
  12. 2024A Survey on LoRA of Large Language Modelscited by 67
  13. 2026Helios: Real Real-Time Long Video Generation Modelcited by 65
  14. 2023DiffusionLight: Light Probes for Free by Painting a Chrome Ballcited by 64
  15. 2024TurboEdit: Text-Based Image Editing Using Few-Step Diffusion Modelscited by 64
  16. 2024EM Distillation for One-step Diffusion Modelscited by 62
  17. 2026Context Forcing: Consistent Autoregressive Video Generation with Long Contextcited by 59
  18. 2023StreamDiffusion: A Pipeline-level Solution for Real-time Interactive Generationcited by 58
  19. 2024ManiCM: Real-time 3D Diffusion Policy via Consistency Model for Robotic Manipulationcited by 57
  20. 2025Learning Few-Step Diffusion Models by Trajectory Distribution Matchingcited by 57
  21. 2024Flash Diffusion: Accelerating Any Conditional Diffusion Model for Few Steps Image Generationcited by 56
  22. 2024Community Forensics: Using Thousands of Generators to Train Fake Image Detectorscited by 50
  23. 2025SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Trainingcited by 50
  24. 2024LCM-Lookahead for Encoder-based Text-to-Image Personalizationcited by 48
  25. 2024Trajectory Consistency Distillation: Improved Latent Consistency Distillation by Semi-Linear Consistency Function with Trajectory Mappingcited by 46
  26. 2024AquaLoRA: Toward White-box Protection for Customized Stable Diffusion Models via Watermark LoRAcited by 46
  27. 2025Decoupled DMD: CFG Augmentation as the Spear, Distribution Matching as the Shieldcited by 45
  28. 2023Boosting Latent Diffusion with Flow Matchingcited by 44
  29. 2024MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantizationcited by 43
  30. 2024LinFusion: 1 GPU, 1 Minute, 16K Imagecited by 43
  31. 2023MobileDiffusion: Instant Text-to-Image Generation on Mobile Devicescited by 42
  32. 2024Efficient Diffusion Models: A Comprehensive Survey from Principles to Practicescited by 41
  33. 2024HiCo: Hierarchical Controllable Diffusion Model for Layout-to-image Generationcited by 41
  34. 2024LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Mergingcited by 41
  35. 2025Adversarial Distribution Matching for Diffusion Distillation Towards Efficient Image and Video Synthesiscited by 41
  36. 2024SF-V: Single Forward Video Generation Modelcited by 40
  37. 2024Curriculum Direct Preference Optimization for Diffusion and Consistency Modelscited by 36
  38. 2025LBM: Latent Bridge Matching for Fast Image-to-Image Translationcited by 36

50 most cited of 211 All 211 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Glance: Accelerating Diffusion Models with 1 Sample
  2. 2024TLCM: Training-efficient Latent Consistency Model for Image Generation with 2-8 Steps
  3. 2024Simplifying, Stabilizing and Scaling Continuous-Time Consistency Models
  4. 2024Phased Consistency Models
  5. 2023LoRA-Enhanced Distillation on Guided Diffusion Models
  6. 2024SCott: Accelerating Diffusion Models with Stochastic Consistency Distillation
  7. 2024EdgeFusion: On-Device Text-to-Image Generation
  8. 2025CDM-QTA: Quantized Training Acceleration for Efficient LoRA Fine-Tuning of Diffusion Model