How to use from the
Use from the
Diffusers library
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline

# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Vargol/sdxl-lightning-4-steps", dtype=torch.bfloat16, device_map="cuda")

prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]

This is a copy of the unet 4 step version of https://huggingface.co/ByteDance/SDXL-Lightning with the SDXL base model other bits an madebyollin's fp16 bit fixed SDXL frankensteined together

This copy has been created simply for my convience.a

Downloads last month
4
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support