ByteDance

/

SDXL-Lightning

like 1.93k

Follow

ByteDance 793

Hi guys and girls,

I just don't get it, what should I do to generate image like in the Model Card?

Do I also need some 3rd party extensions or it should work out of the box?

I have just updated Web UI and running on 3070ti. I have 32GB RAM.
Model card has some scripts, where do I put them?

Here is my startup log

Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Version: v1.9.3
Commit hash: 1c0a0c4c26f78c32095ebc7f8af82f5c04fca8c0
Launching Web UI with arguments: --xformers --no-half
Loading weights [471d8260fd] from C:\StableDiffusionWebUI\sd.webui\webui\models\Stable-diffusion\SDXL\sdxl_lightning_8step_unet.safetensors
Creating model from config: C:\StableDiffusionWebUI\sd.webui\webui\configs\v1-inference.yaml
Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
C:\StableDiffusionWebUI\sd.webui\system\python\lib\site-packages\huggingface_hub\file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
  warnings.warn(
Startup time: 9.9s (prepare environment: 1.8s, import torch: 3.0s, import gradio: 0.7s, setup paths: 0.8s, initialize shared: 1.6s, other imports: 0.6s, load scripts: 0.7s, create ui: 0.3s, gradio launch: 0.3s).
Applying attention optimization: xformers... done.
Model loaded in 3.2s (load weights from disk: 0.4s, create model: 1.5s, apply weights to model: 0.2s, calculate empty prompt: 1.1s).