modelos/LCM-LoRA Weights - Stable Diffusion Acceleration Module - LCM for SD 1.5

LCM-LoRA Weights - Stable Diffusion Acceleration Module - LCM for SD 1.5

|
7/10/2025
|
11:35:18 AM
| Discussion

Prompts Recomendados

beautiful scenery nature glass bottle landscape, purple galaxy bottle

Prompts Negativos Recomendados

text, watermark

Parâmetros Recomendados

samplers

Euler a

steps

3

cfg

1 - 1.5

Dicas

Use LCM-LoRA alongside any SDXL or Stable Diffusion 1.5 model for fast acceleration.

Set CFG to approximately 1.5 and steps to 3 for optimal fast generation.

Generate images nearly instantaneously on an Nvidia 4090 GPU.

Workflow example for ComfyUI is provided as a zip file labeled 'Training Images'.

Check the LCM-LoRA Technical Report and HuggingFace model pages for more details.

Patrocinadores do Criador

LCM-LoRA - Acceleration Module!


Tested with ComfyUI, although I hear it's working with Auto1111 now!

Step 1) Download LoRA

Step 2) Add LoRA alongside any SDXL Model (or 1.5 model, if using the SD 1.5 version)

Step 3) Set CFG to ~1.5 and Steps to 3

Step 4) Generate images in ~<1 second (instantaneously on a 4090)

Basic LCM Comfy workflow attached as "Training Images" in zip format.

Read more about the concept here;
https://github.com/luosiallen/latent-consistency-model/blob/main/LCM-LoRA%20Technical%20Report/LCM-LoRA-Technical-Report.pdf

Original HF link - SDXL; https://huggingface.co/latent-consistency/lcm-lora-sdxl/tree/main

Original HF link - SD 1.5; https://huggingface.co/latent-consistency/lcm-lora-sdv1-5

Anterior
Midjourney V6.1 meets FLUX šŸ–¼ļø [+ILLUSTRIOUS / SDXL] - FLUX v0.4
Próximo
Flux vividizer | Flux enhancer - v1.0

Detalhes do Modelo

Tipo de modelo

LORA

Modelo base

SD 1.5

Versão do modelo

LCM for SD 1.5

Hash do modelo

8f90d840e0

Criador

Discussão

Por favor, faƧa log in para deixar um comentƔrio.