Stable Diffusion Tutorial: Install and Use SDXL 1.0 Base and Refiner Models with Troubleshoot Tips!

SDXL 1.0 is finally released! This video will show you how to download, install, and use the SDXL 1.0 Base and Refiner models in Automatic 1111 Web UI. We will also compare images generated with SDXL 1.0 to images generated with fine-tuned version 1.5 models. Is this the beginning of the end for version 1.5 models? Let’s find out!

00:00 Intro
01:14 Overview of Topics
01:58 Download SDXL 1.0 Base and Refiner models
02:45 Try loading SDXL 1.0 in A1111
03:22 How to Update A1111 web UI with ‘git pull’
04:00 Troubleshooting: how to set tracking information to master branch
04:54 Load SDXL 1.0 base model
06:00 Set ‘–no-half-vae’ command line flag
07:16 SD v1.5 models vs. SDXL 1.0
07:52 How to save prompts as ‘Styles’
08:30 Generating the XY plot of Models vs. Styles
09:53 Resulting images review
14:16 And the winner is…
14:50 How to use SDXL 1.0 Refiner model in A1111
15:42 Base images vs. Refined images

Links to Previous Tutorials:
Stable Diffusion Tutorial: 4 Easy Steps to Install Automatic1111 on your PC! Start creating fast!

Stable Diffusion Tutorial:Using XYZ plots to Optimize Parameters and Get the Most Out of your Model!

Here are useful links below:
SDXL 1.0 base model hugging face page:
SDXL 1.0 refiner model hugging face page:

Do not switch the VAE model to 16-bit floats.

Enable xformers for cross attention layers; makes your image generation a LOT faster.

On startup, notifies whether or not your web UI version (commit) is up-to-date with the current master branch.

On startup, it pulls the latest updates for all extensions you have installed.

Automatically start WebUI in your default browser; so you don’t have to copy and paste the URL into your browser manually.

Turns your WebUI into a black background with white letters; easier on the eyes.

The Styles.csv file that I used to do the SD v1.5 vs. SDXL test.

  • URLをコピーしました!
  • URLをコピーしました!