AUTOMATIC1111/stable-diffusion-webui

[Bug]: Custom upscaler missing

Glaudeo opened this issue · 1 comments

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
  • The issue has not been reported before recently
  • The issue has been reported before but has not been fixed yet

What happened?

I just installed automatic1111 and decided to download an upscaler model from https://openmodeldb.info/models/4x-PurePhoto-RealPLSKR.
I put .pth file into models/RealESRGAN folder, reloaded the UI but the upscaler did not appear in Hires.fix dropdown menu or in SD upscale script.
I tried different upscalers and non of them worked
What could be the problem?

Steps to reproduce the problem

  1. Install automatic1111
  2. Put custom upscaler into models/RealESRGAN folder
  3. There is no custom upscaler in web ui

What should have happened?

Custom upscaler should appear in upscalers list

What browsers do you use to access the UI ?

Firefox

Sysinfo

Windows 10 LTSC 21H2
RTX 3060 12 GB
AMD Ryzen 5 5600
32 GB RAM

Console logs

venv "D:\Neural Network\Automatic1111\stable-diffusion-webui\venv\Scripts\Python.exe"
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Version: v1.10.1
Commit hash: 82a973c04367123ae98bd9abdf80d9eda9b910e2
Launching Web UI with arguments: --xformers
D:\Neural Network\Automatic1111\stable-diffusion-webui\venv\lib\site-packages\timm\models\layers\__init__.py:48: FutureWarning: Importing from timm.models.layers is deprecated, please import via timm.layers
  warnings.warn(f"Importing from {__name__} is deprecated, please import via timm.layers", FutureWarning)
Loading weights [8440379417] from D:\Neural Network\Automatic1111\stable-diffusion-webui\models\Stable-diffusion\lustifySDXLNSFW_v40.safetensors
Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
Creating model from config: D:\Neural Network\Automatic1111\stable-diffusion-webui\repositories\generative-models\configs\inference\sd_xl_base.yaml
D:\Neural Network\Automatic1111\stable-diffusion-webui\venv\lib\site-packages\huggingface_hub\file_download.py:797: 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: 9.1s (prepare environment: 2.0s, import torch: 3.2s, import gradio: 0.7s, setup paths: 0.8s, initialize shared: 0.2s, other imports: 0.3s, list SD models: 0.3s, load scripts: 0.9s, create ui: 0.3s, gradio launch: 0.4s).
Applying attention optimization: xformers... done.
Model loaded in 4.4s (load weights from disk: 0.4s, create model: 0.7s, apply weights to model: 2.9s, calculate empty prompt: 0.1s).

Additional information

No response

Sorry, I was stupid. The correct folder's name is "ESRGAN" not "RealESRGAN"