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
should i use the lora model when using SDXL Lightning models from CivitAI ?
#52
by luluxxx - opened
a little bit of confusion here.
when using models tagged as SDXL Lightning model from CivitAI (like this one for example : https://civitai.com/models/139562/realvisxl-v40?modelVersionId=361593) should i load the lora models on top (sdxl_lightning_Nstep_lora.safetensors) ?
@luluxxx hi, if the model is already tagged as sdxl lightning, that means that lightning model is already merged in the civitai models by the model creator, so you do not need to use the lora models here anymore.