[Bug]: Upscaler in "Extra" is not working as before, PLEASE HELP

[NissanSUTUTU]

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
• [X] 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?

I've always been using the same setting for "Extras", and now after the latest changes to Stable Diffusion, the upscaler isn't working like it used to, my images are less sharp.

Old upscaler:

New uspcaler:

Only the resolution is affected, but the sharpening and creation of new pixels does not happen. I need an urgent solution.

Steps to reproduce the problem

What should have happened?

I need this:

Not this:

What browsers do you use to access the UI ?

Google Chrome

Sysinfo

sysinfo-2024-03-10-01-09.json

Console logs

No SDP backend available, likely because you are running in pytorch versions < 2.0. In fact, you are using PyTorch 1.13.1+cu116. You might want to consider upgrading.
Skipping broken symlink: /notebooks/sd/stable-diffusion-webui/models/Stable-diffusion/sd_xl_base_1.0.safetensors
Downloading face_yolov8n.pt: 100%|██████████| 6.21M/6.21M [00:00<00:00, 132MB/s]
Downloading face_yolov8s.pt: 100%|█████████| 22.5M/22.5M [00:00<00:00, 84.4MB/s]
Downloading hand_yolov8n.pt: 100%|█████████| 6.22M/6.22M [00:00<00:00, 85.0MB/s]
Downloading person_yolov8n-seg.pt: 100%|████| 6.75M/6.75M [00:00<00:00, 146MB/s]
Downloading person_yolov8s-seg.pt: 100%|███| 23.8M/23.8M [00:00<00:00, 61.7MB/s]
[-] ADetailer initialized. version: 24.1.2, num models: 11
ControlNet preprocessor location: /notebooks/sd/stable-diffusion-webui/extensions/sd-webui-controlnet/annotator/downloads
2024-03-10 00:37:16,243 - ControlNet - INFO - ControlNet v1.1.441
2024-03-10 00:37:19,111 - ControlNet - INFO - ControlNet v1.1.441
*** Error loading script: GenParamGetter.py
    Traceback (most recent call last):
      File "/notebooks/sd/stable-diffusion-webui/modules/scripts.py", line 527, in load_scripts
        script_module = script_loading.load_module(scriptfile.path)
      File "/notebooks/sd/stable-diffusion-webui/modules/script_loading.py", line 10, in load_module
        module_spec.loader.exec_module(module)
      File "<frozen importlib._bootstrap_external>", line 850, in exec_module
      File "<frozen importlib._bootstrap>", line 228, in _call_with_frames_removed
      File "/notebooks/sd/stable-diffusion-webui/extensions/sd-webui-supermerger/scripts/GenParamGetter.py", line 3, in <module>
        from scripts.mergers.mergers import smergegen, simggen
      File "/notebooks/sd/stable-diffusion-webui/extensions/sd-webui-supermerger/scripts/mergers/mergers.py", line 683, in <module>
        def extract_super(base: Tensor | None, a: Tensor, b: Tensor, alpha: float, beta: float, gamma: float) -> Tensor:
    TypeError: unsupported operand type(s) for |: 'torch._C._TensorMeta' and 'NoneType'

---
*** Error loading script: supermerger.py
    Traceback (most recent call last):
      File "/notebooks/sd/stable-diffusion-webui/modules/scripts.py", line 527, in load_scripts
        script_module = script_loading.load_module(scriptfile.path)
      File "/notebooks/sd/stable-diffusion-webui/modules/script_loading.py", line 10, in load_module
        module_spec.loader.exec_module(module)
      File "<frozen importlib._bootstrap_external>", line 850, in exec_module
      File "<frozen importlib._bootstrap>", line 228, in _call_with_frames_removed
      File "/notebooks/sd/stable-diffusion-webui/extensions/sd-webui-supermerger/scripts/supermerger.py", line 22, in <module>
        import scripts.mergers.mergers
      File "/notebooks/sd/stable-diffusion-webui/extensions/sd-webui-supermerger/scripts/mergers/mergers.py", line 683, in <module>
        def extract_super(base: Tensor | None, a: Tensor, b: Tensor, alpha: float, beta: float, gamma: float) -> Tensor:
    TypeError: unsupported operand type(s) for |: 'torch._C._TensorMeta' and 'NoneType'

---
Loading weights [4c86efd062] from /notebooks/sd/stable-diffusion-webui/models/Stable-diffusion/SDv1.5.ckpt
Creating model from config: /notebooks/sd/stable-diffusion-webui/configs/v1-inference.yaml
Loading VAE weights specified in settings: /notebooks/sd/stable-diffusion-webui/models/VAE/Counterfeit-V2.5.vae.pt
Applying attention optimization: xformers... done.
Model loaded in 31.0s (load weights from disk: 21.4s, create model: 0.9s, apply weights to model: 2.3s, load VAE: 5.5s, calculate empty prompt: 0.6s).
2024-03-10 00:37:50,998 - ControlNet - INFO - ControlNet UI callback registered.
Running on local URL: https://tensorboard-n4cqxovhn5.clg07azjl.paperspacegradient.com
✔ Connected
Startup time: 49.9s (import torch: 4.6s, import gradio: 1.1s, setup paths: 1.3s, initialize shared: 0.2s, other imports: 0.8s, list SD models: 1.9s, load scripts: 5.9s, create ui: 32.4s, gradio launch: 0.2s, add APIs: 0.8s, app_started_callback: 0.5s).
*** Unable to load ESRGAN model /notebooks/sd/stable-diffusion-webui/models/ESRGAN/4x-UltraSharp.pth
    Traceback (most recent call last):
      File "/notebooks/sd/stable-diffusion-webui/modules/esrgan_model.py", line 31, in do_upscale
        model = self.load_model(selected_model)
      File "/notebooks/sd/stable-diffusion-webui/modules/esrgan_model.py", line 49, in load_model
        return modelloader.load_spandrel_model(
      File "/notebooks/sd/stable-diffusion-webui/modules/modelloader.py", line 149, in load_spandrel_model
        import spandrel
    ModuleNotFoundError: No module named 'spandrel'

---
*** Unable to load ESRGAN model /notebooks/sd/stable-diffusion-webui/models/ESRGAN/4x_NMKD-UltraYandere_300k.pth
    Traceback (most recent call last):
      File "/notebooks/sd/stable-diffusion-webui/modules/esrgan_model.py", line 31, in do_upscale
        model = self.load_model(selected_model)
      File "/notebooks/sd/stable-diffusion-webui/modules/esrgan_model.py", line 49, in load_model
        return modelloader.load_spandrel_model(
      File "/notebooks/sd/stable-diffusion-webui/modules/modelloader.py", line 149, in load_spandrel_model
        import spandrel
    ModuleNotFoundError: No module named 'spandrel'

---

Additional information

I use Paperspace automatic1111 https://github.com/TheLastBen/fast-stable-diffusion

[missionfloyd]

https://github.com/TheLastBen/fast-stable-diffusion/issues/2771

[codespearhead]

@NissanSUTUTU Can you check whether @missionfloyd 's suggestion works?