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
Broken model?
#62
by mlmPenguin - opened
I tried generating an image with the 2step model, and the results I get are FAR from "high-quality."
Similar results from 4step and 8step, but let's just talk about the 2step for clarity.
When I tried to generate an image with 2 steps, I got these flat-looking images.
After those ended up looking funky, I figured I should try 4 steps. This one looks a lot less flat, but still very bad.
What's happening here?



