LCM-LoRA SDXL is a distilled consistency adapter for Stable Diffusion XL. It attaches to an SDXL base model and uses an LCM scheduler to reduce generation to roughly two to eight denoising steps. The adapter supports text-to-image and inpainting workflows and can be combined with compatible style LoRAs; the official repository includes weights and usage examples.
Latent Consistency Model (LCM) LoRA was proposed in LCM-LoRA: A universal Stable-Diffusion Acceleration Module by Simian Luo, Yiqin Tan, Suraj Patil, Daniel Gu et al.
