Pith. sign in

REVIEW 17 cited by

LCM-LoRA: A Universal Stable-Diffusion Acceleration Module

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 2311.05556 v1 pith:R63Q4AP6 submitted 2023-11-09 cs.CV cs.LG

Simian Luo , Yiqin Tan , Suraj Patil , Daniel Gu , Patrick von Platen , Apolinário Passos , Longbo Huang , Jian Li
show 1 more author
Hang Zhao
This is my paper
classification cs.CVcs.LG
keywords modelslcm-lorastable-diffusionlcmsaccelerationdistillationgenerationimage
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

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.

Discussion (0). Sign in to comment.

Forward citations

Cited by 17 Pith papers

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

  1. Inverting the Streaming-Diffusion Bottleneck: Video-Rate MLLM-Conditioned Edit Diffusion on a Consumer GPU

    cs.CV 2026-06 unverdicted novelty 7.0 of 10

    Reports a streaming pipeline with asymmetric CUDA pipelining and batched MLLM amortization that sustains 27.4 fps at 512x512 on RTX 3090 Ti for oil-painting stylization.

  2. A Decomposable Probe for Few-Step Diffusion Models: Prompt, Latent, and Score Selectivity across Backbone Families and Distillation Paradigms

    cs.CV 2026-07 conditional novelty 6.5 of 10

    A three-layer perturbation probe shows latent selectivity is a near-binary rectified-flow fingerprint that survives ADD distillation, while score selectivity tracks distillation objective across 23 T2I models.

  3. FARI: Robust One-Step Inversion for Watermarking in Diffusion Models

    cs.CR 2026-07 accept novelty 6.0 of 10

    One-step adversarially LoRA-tuned inversion exploits low-curvature reverse trajectories to beat 50-step DDIM on watermark robustness after ~20 minutes of fine-tuning.

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

    cs.CV 2026-07 conditional novelty 6.0 of 10

    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.

  5. UPLiFT: Efficient Pixel-Dense Feature Upsampling with Local Attenders

    cs.CV 2026-01 conditional novelty 6.0 of 10

    UPLiFT shows that iterative 2× feature upsampling with a locally-defined attention operator beats cross-attention-based upsamplers on dense prediction while scaling linearly with token count.

  6. Null-Space Diffusion Distillation Unlocks Speed, Fidelity and Realism in Lensless Imaging

    cs.CV 2025-11 conditional novelty 6.0 of 10

    A single-pass network, Null-Space Diffusion Distillation (NSDD), distills a slow DDNM+ teacher and reaches near-teacher perceptual quality at 0.034 s/image on Lensless FFHQ without paired lensed supervision.

  7. Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation

    cs.LG 2025-09 conditional novelty 6.0 of 10

    PrunedLoRA tunes large-rank LoRA adapters and progressively structurally prunes A and B to a target low rank, empirically closing much of the LoRA-to-full-fine-tuning gap.

  8. Inpaint4Drag: Repurposing Inpainting Models for Drag-Based Image Editing via Bidirectional Warping

    cs.CV 2025-09 conditional novelty 6.0 of 10

    Drag-based editing becomes pixel-space bidirectional warping plus inpainting, giving real-time previews and 0.3s final edits at 512x512.

  9. Adversarial Distribution Matching for Diffusion Distillation Towards Efficient Image and Video Synthesis

    cs.CV 2025-07 conditional novelty 6.0 of 10

    A new adversarial distribution matching loss for diffusion distillation gives one-step and few-step generators that match or exceed prior distillation methods on SDXL, SD3, and CogVideoX.

  10. Revisiting Diffusion Models: From Generative Pre-training to One-Step Generation

    cs.LG 2025-06 conditional novelty 6.0 of 10

    Fine-tuning a pretrained diffusion model with a GAN objective and most weights frozen yields a one-step generator that matches or beats prior distillation methods on several datasets.

  11. Dual-Expert Consistency Model for Efficient and High-Quality Video Generation

    cs.CV 2025-06 conditional novelty 6.0 of 10

    By training a semantic expert and a LoRA-based detail expert, DCM reaches nearly teacher-level VBench scores with 4-step video sampling on HunyuanVideo and CogVideoX.

  12. EMPURPLE: A Free Lunch for Diffusion Distillation based on the Information Bottleneck

    cs.CV 2026-07 conditional novelty 5.0 of 10

    Recycling teacher intermediate latents into distilled samplers reduces early train–test mismatch and improves FID 7–20% without retraining, at a small CLIP cost.

  13. JuZhou 1.0 Technical Report: The First Edge-Native Text-to-Image Foundation Model Trained Entirely on China-Developed AI Accelerators

    cs.CV 2026-06 unverdicted novelty 5.0 of 10

    JuZhou 1.0 is a 0.387B-parameter T2I diffusion model with 4-step inference achieving 0.69 GenEval, trained on 9M Chinese pairs using Sugon K100 accelerators and deployable on Android/iOS devices.

  14. Non-invasive Assessment of Pancreatic Duct Hypertension Using Computational Flow Modeling

    physics.med-ph 2025-08 unverdicted novelty 5.0 of 10

    A computational model estimates pancreatic duct pressure non-invasively from MRCP geometry, with reported agreement against ERCP pressure measurements.

  15. Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment

    cs.CV 2025-06 conditional novelty 5.0 of 10

    A reparameterization recipe that lets pre-trained Stable Diffusion checkpoints be finetuned as flow matching models, giving faster convergence and better performance under parameter-efficient constraints.

  16. 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...

  17. Interactive Drawing Guidance for Anime Illustrations with Diffusion Model

    cs.GR 2025-07 conditional novelty 4.0 of 10

    A diffusion-based drawing guidance system improves anime sketching, and a side-positioned, selectable guidance interface outperforms a fixed underlying reference in user preference.

Pith tools