LCM-LoRA Weights - Stable Diffusion Acceleration Module - LCM for SD 1.5
Highlighted images
Recommended Prompts
beautiful scenery nature glass bottle landscape, purple galaxy bottle
Recommended Negative Prompts
text, watermark
Recommended Parameters
samplers
steps
cfg
Tips
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.
Creator Sponsors
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
Model Details
Discussion
Please log in to leave a comment.