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?

Infinity loading with try use upscale ESRGAN_4x and 4x-UltraSharp. Loading to 49% and stoped.

My PC: MSI 4070 TI Super 16 gb VRAM 64gb DDR5 AMD Ryzen 9 7950X3D ssd 1tb

Steps to reproduce the problem

1. PNG info
2. Upload generated image
3. TextToImage
4. Setup setting from image
5. Generate with hires. fix
6. Ininity loading

What should have happened?

Should ganarated image

What browsers do you use to access the UI ?

Google Chrome

Sysinfo

sysinfo-2025-06-11-17-57.json

Console logs

venv "D:\Git\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:
D:\Git\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)
no module 'xformers'. Processing without...
no module 'xformers'. Processing without...
No module 'xformers'. Proceeding without it.
Loading weights [aaee0efd7c] from D:\Git\stable-diffusion-webui\models\Stable-diffusion\nova3DCGXL_illustriousV30.safetensors
Running on local URL:  http://127.0.0.1:7860
Creating model from config: D:\Git\stable-diffusion-webui\repositories\generative-models\configs\inference\sd_xl_base.yaml

To create a public link, set `share=True` in `launch()`.
D:\Git\stable-diffusion-webui\venv\lib\site-packages\huggingface_hub\file_download.py:943: 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: 6.8s (prepare environment: 1.5s, import torch: 2.5s, import gradio: 0.6s, setup paths: 0.4s, initialize shared: 0.2s, other imports: 0.3s, load scripts: 0.5s, create ui: 0.2s, gradio launch: 0.5s).
Applying attention optimization: Doggettx... done.
Model loaded in 4.1s (load weights from disk: 0.4s, create model: 0.3s, apply weights to model: 3.0s, calculate empty prompt: 0.1s).
100%|██████████████████████████████████████████████████████████████████████████████████| 50/50 [00:08<00:00,  5.60it/s]
==========================================================================================0/75 [00:09<00:04,  5.60it/s]
A tensor with all NaNs was produced in VAE.
Web UI will now convert VAE into 32-bit float and retry.
To disable this behavior, disable the 'Automatically revert VAE to 32-bit floats' setting.
To always start with 32-bit VAE, use --no-half-vae commandline flag.
==========================================================================================
tiled upscale: 100%|███████████████████████████████████████████████████████████████████| 25/25 [00:02<00:00,  9.63it/s]

Additional information

No response