# luosiallen/latent-consistency-model

Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference

Repository: https://github.com/luosiallen/latent-consistency-model
Canonical: https://ross.abutalabs.com/products/latent-consistency-model
Language: Python
License: MIT
License Family: permissive
Last push: 2024-06-14T04:54:58+00:00

## Health v2 (maintenance only)
Score: 27/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 75
- inputs: {"age_days": 1062, "days_push": 810, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4615, forks 232 (observed 2026-08-28T04:08:55.098785+00:00)

## What it is
Official implementation of Latent Consistency Models (LCM), a diffusion-based approach for synthesizing high-resolution images with few-step inference, plus LCM-LoRA acceleration modules for Stable Diffusion. It includes inference code, training/distillation scripts, and model checkpoints for SD 1.5, SSD-1B, and SDXL.

## Use cases
- generate images from text prompts in a few inference steps
- accelerate stable diffusion image generation with LCM-LoRA
- run fast text-to-image and image-to-image generation
- train or distill a latent consistency model on custom data
- build real-time image generation demos

## When to choose
- you need fast few-step Stable Diffusion inference or LoRA acceleration
- you want to reproduce or build on the LCM research papers
- you need official checkpoints and training scripts for consistency distillation

## When to avoid
- you need a production-grade maintained image generation pipeline rather than research code
- you want a general-purpose diffusion library like diffusers
- you need non-image modalities or the latest model architectures

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing
- domain: artificial-intelligence, image-processing, deep-learning
- platform: python
- tags: stable-diffusion, text-to-image, few-step-inference, lcm, lcm-lora, diffusion-models, research-code, gpu

## Member repositories
- luosiallen/latent-consistency-model (main) score 27

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:55.098785+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:19:40.938741+00:00, confidence not recorded.
  - readme: https://github.com/luosiallen/latent-consistency-model (fetched 2026-08-28T04:08:55.098785+00:00, sha 0c06517350e6)
- Data as of 2026-08-30T08:39:29.467469+00:00.