LCM-LoRA Weights - Stable Diffusion Acceleration Module - LCM for SD 1.5
精選圖片
推薦提示詞
beautiful scenery nature glass bottle landscape, purple galaxy bottle
推薦反向提示詞
text, watermark
推薦參數
samplers
steps
cfg
提示
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.
創作者贊助
Explore LCM-LoRA acceleration module with released resources:
LCM-LoRA Technical Report (GitHub)
LCM-LoRA SDXL Model (HuggingFace)
LCM-LoRA SD 1.5 Model (HuggingFace)
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