REVIEW 28 cited by
LCM-LoRA: A Universal Stable-Diffusion Acceleration Module
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
LCM-LoRA: A Universal Stable-Diffusion Acceleration Module
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.
Forward citations
Cited by 28 Pith papers
-
Beyond Trajectory Matching: Reflow with Marginal Distribution Alignment
Introduces a marginal-alignment regularizer for reflow distillation of diffusion models that aligns endpoint marginals, supported by a telescoping TV bound and benchmark experiments.
-
Semantic Browsing: Controllable Diversity for Image Generation
A technique for controllable diversity in text-to-image generation by inducing structured semantic variations at the prompt level via VLM and agentic workflow.
-
Timage: A Generative Text-in-Image Paradigm for Fine-Tuning Vision-Language Models
Timage generates text query overlays on images via Constrained Schrödinger Bridge to boost fine-grained spatial reasoning in vision-language models, outperforming larger systems on VMCBench with a 7B backbone.
-
Inverting the Streaming-Diffusion Bottleneck: Video-Rate MLLM-Conditioned Edit Diffusion on a Consumer GPU
Asymmetric CUDA-stream pipelining, a compile-friendly LLLite reformulation, and periodic conditioning refresh sustain 27-30 fps video stylization on a consumer GPU with a 2.13B MLLM text encoder and 0.39B distilled U-Net.
-
ORBIS: Output-Guided Token Reduction with Distribution-Aware Matching for Video Diffusion Acceleration
ORBIS uses output-guided token reduction and DATM to achieve 2x higher token reduction than AsymRnR, with up to 4.5x speedup and 79.3% energy savings versus A100 GPU for video DiT models.
-
LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation
LongLive-2.0 delivers an NVFP4 parallel infrastructure that enables direct training of long multi-shot autoregressive diffusion video models and achieves up to 2.15x training and 1.84x inference speedups on Blackwell ...
-
A Decomposable Probe for Few-Step Diffusion Models: Prompt, Latent, and Score Selectivity across Backbone Families and Distillation Paradigms
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.
-
FARI: Robust One-Step Inversion for Watermarking in Diffusion Models
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.
-
From Draft to Draft-Free: One-Step Video Object Removal via Privileged Distillation and Fast Planting
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.
-
ActWorld: From Explorable to Interactive World Model via Action-Aware Memory
ActWorld extends navigation-centric world models to support mid-rollout object interactions via chunk-autoregressive generation, action-aware memory routing, and a persistent memory bank, backed by a 100K annotated in...
-
Stain-Aware Wavelet Regularization for Instant Adversarial Purification in Histopathology
SAWR applies stain-aware multi-level wavelet regularization to purify adversarial perturbations in histopathology images, claiming up to 10.69% robustness gain while preserving texture and spectral properties.
-
Thermal-Only Crowd Counting with Deployment-Time Privacy Protection
A privacy-preserving thermal-only crowd counting framework extracts enhanced features from thermal images via single-step LCM denoising in a depth-to-RGB diffusion model and matches RGB-T fusion performance without RG...
-
RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPO
RAVEN aligns training and inference for causal autoregressive video diffusion via interleaved rollout repacking and introduces CM-GRPO for direct RL on consistency-model kernels, claiming better quality than recent baselines.
-
Diversity-Preserved Distribution Matching Distillation for Fast Visual Synthesis
DP-DMD preserves sample diversity in few-step image synthesis by applying a teacher-derived target-prediction objective to the first distillation step and standard DMD loss to the rest.
-
UPLiFT: Efficient Pixel-Dense Feature Upsampling with Local Attenders
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.
-
Scaling Up AI-Generated Image Detection with Generator-Aware Prototypes
GAPL learns a compact set of canonical forgery prototypes and applies two-stage LoRA training to build a low-variance feature space that improves generalization across GAN and diffusion generators.
-
Null-Space Diffusion Distillation Unlocks Speed, Fidelity and Realism in Lensless Imaging
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.
-
Adversarial Concept Distillation for One-Step Diffusion Personalization
OPAD enables reliable high-quality personalization of one-step diffusion models via multi-step teacher distillation combined with adversarial alignment losses.
-
Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation
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.
-
EMPURPLE: A Free Lunch for Diffusion Distillation based on the Information Bottleneck
Recycling teacher intermediate latents into distilled samplers reduces early train–test mismatch and improves FID 7–20% without retraining, at a small CLIP cost.
-
JuZhou 1.0 Technical Report: The First Edge-Native Text-to-Image Foundation Model Trained Entirely on China-Developed AI Accelerators
A compact Chinese-native T2I U-Net (~0.387B) trained on Sugon K100, distilled to 4 steps, reports GenEval 0.69 and ~1.6–4.5s offline mobile generation.
-
SSAFE: Simple and Strong AI-Generated Image Detection via Frozen Vision Encoders
Frozen multimodal encoders enable robust AI-generated image detection via linear classification on a 10K-image curated training set that improves generalization over larger datasets.
-
Teacher-Feature Drifting: One-Step Diffusion Distillation with Pretrained Diffusion Representations
A simplified one-step diffusion distillation uses pretrained teacher features directly for drifting loss plus a mode coverage term, achieving FID 1.58 on ImageNet-64 and 18.4 on SDXL.
-
Systematic Optimization of Real-Time Diffusion Model Inference on Apple M3 Ultra
Systematic benchmarking of diffusion model optimizations on Apple M3 Ultra produces 22.7 FPS real-time img2img at 512x512 and demonstrates that CUDA-derived techniques do not transfer directly to Apple Silicon.
-
Efficient Difficulty-Aware Dynamic Routing for Diffusion-Based Real-World Image Super-Resolution
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...
-
JuZhou 1.0 Technical Report: The First Edge-Native Text-to-Image Foundation Model Trained Entirely on China-Developed AI Accelerators
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.
-
Inverting the Streaming-Diffusion Bottleneck: Video-Rate MLLM-Conditioned Edit Diffusion on a Consumer GPU
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.
-
Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey
A comprehensive survey of PEFT algorithms for large models, covering their performance, overhead, applications, and real-world system implementations.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.