[Bug]: SDXL error: Rendering bad and "broken" images

[zbyzfw]

Checklist

• [ ] The issue exists after disabling all extensions
• [ ] The issue exists on a clean installation of webui
• [ ] The issue is caused by an extension, but I believe it is caused by a bug in the webui
• [ ] The issue exists in the current version of the webui
• [X] The issue has not been reported before recently
• [ ] The issue has been reported before but has not been fixed yet

What happened?

SDXL generates image color garbled codes

Steps to reproduce the problem

SD1.5 generation is not a problem

What should have happened?

Generating images is normal

What browsers do you use to access the UI ?

Google Chrome

Sysinfo

1

Console logs

Python 3.10.14 (main, Mar 21 2024, 16:24:04) [GCC 11.2.0]
Version: v1.9.3
Commit hash: 1c0a0c4c26f78c32095ebc7f8af82f5c04fca8c0
Launching Web UI with arguments: --listen --xformers
/usr/local/anaconda3/envs/sdweb/lib/python3.10/site-packages/torchvision/io/image.py:13: UserWarning: Failed to load image Python extension: '/usr/local/anaconda3/envs/sdweb/lib/python3.10/site-packages/torchvision/image.so: undefined symbol: _ZN3c1017RegisterOperatorsD1Ev'If you don't plan on using image functionality from `torchvision.io`, you can ignore this warning. Otherwise, there might be something wrong with your environment. Did you have `libjpeg` or `libpng` installed before building `torchvision` from source?
  warn(
Loading weights [f4180ee85c] from /data/git_packages/stable-diffusion-webui/models/Stable-diffusion/AnythingXL_xl.safetensors
Running on local URL:  http://0.0.0.0:7860

To create a public link, set `share=True` in `launch()`.
Startup time: 9.1s (prepare environment: 2.0s, import torch: 3.4s, import gradio: 0.7s, setup paths: 1.3s, initialize shared: 0.1s, other imports: 0.3s, load scripts: 0.5s, create ui: 0.6s, gradio launch: 0.1s).
Creating model from config: /data/git_packages/stable-diffusion-webui/repositories/generative-models/configs/inference/sd_xl_base.yaml
Loading VAE weights specified in settings: /data/git_packages/stable-diffusion-webui/models/VAE/sdxl_vae.safetensors
Applying attention optimization: xformers... done.
Model loaded in 5.0s (load weights from disk: 0.7s, create model: 0.6s, apply weights to model: 2.7s, load textual inversion embeddings: 0.4s, calculate empty prompt: 0.3s)

Additional information

1

[zbyzfw]

1