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
Art Style Style selector invalid?
#27
by junguang - opened
After using the lightning model, the nodes with similar artistic styles are invalid, and if you choose cartoon, it can only produce realistic pictures. Do you need any special prompt words?
We have heard such feedback. Likely because we only used LAION and COYO public dataset for model distillation, so it works better on realistic data instead of anime and artistic styles.
Right now the workaround is use CFG and CFG-rescale. Some people even explored using other sampler and schedulers to get desirable results. But do expect some artifacts.