from https://huggingface.co/docs/diffusers/main/en/using-diffusers/inference_with_lcm_lora
Latent Consistency Models (LCM) enable quality image generation in typically 2-4 steps making it possible to use diffusion models in almost real-time settings.
From the official website:
LCMs can be distilled from any pre-trained Stable Diffusion (SD) in only 4,000 training steps (~32 A100 GPU Hours) for generating high quality 768 x 768 resolution images in 2~4 steps or even one step, significantly accelerating text-to-image generation. We employ LCM to distill the Dreamshaper-V7 version of SD in just 4,000 training iterations.
My parameters on PixAI:
This LoRA's Weight: 0.3
CFG Scale: 3
Steps: 5~8
Sampling method: "DPM++ 2S a Karras" or "Eular a"
