Instructions to use ByteDance/SDXL-Lightning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ByteDance/SDXL-Lightning with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("ByteDance/SDXL-Lightning", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Article - SDXL-Lightning: quick look and comparison
SDXL-Lightning is spectacular!
For anyone who wants to know more in a simple way, I've written an article explaining how it works, what improvements it brings and what is the best way to use it to get the most out of it. I have also compared it against SDXL Turbo and LCM-LoRA.
In my opinion the best checkpoint is the LoRA in 4 steps. It has no rival. The Turbo model doesn't even come close. In terms of quality nothing to envy to the Stable Diffusion XL base model.
It's been a lot of work and testing, but I'm happy with the article and I hope you enjoy it. Any feedback is appreciated!
SDXL-Lightning: quick look and comparison
Link: https://www.felixsanz.dev/articles/sdxl-lightning-quick-look-and-comparison
amazing articles, thanks for sharing and the hard work
