Instructions to use openskyml/lcm-lora-stable-diffusion-xl with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use openskyml/lcm-lora-stable-diffusion-xl with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("openskyml/lcm-lora-stable-diffusion-xl") prompt = "inspired by coffee, by Edward Armitage, When everything is gone You'll wish you only heard us out Heard us out <lora:pytorch_lora_weights:0.6>" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
metadata
tags:
- text-to-image
- stable-diffusion
- lcm-lora
- lora
- diffusers
- template:sd-lora
- openskyml
widget:
- text: >-
inspired by coffee, by Edward Armitage, When everything is gone You'll
wish you only heard us out Heard us out <lora:pytorch_lora_weights:0.6>
parameters:
negative_prompt: dull, boring, error, mediocre
output:
url: images/lcm-lora-sdxl.png
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: <lora:pytorch_lora_weights:0.3>
license: mit
LCM LoRA for SDXL

- Prompt
- inspired by coffee, by Edward Armitage, When everything is gone You'll wish you only heard us out Heard us out <lora:pytorch_lora_weights:0.6>
- Negative Prompt
- dull, boring, error, mediocre
Trigger words
You should use <lora:pytorch_lora_weights:0.3> to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.