Stable Diffusion is loading.... #2056

Running engine 3.5 or 4.0 start.sh runs and brings up the webpage. In the upper right it states Stable Diffusion is loading .... and it never loads.
I can not generate any images.
On the terminal screen I get the following
╭────────────────────────── Easy Diffusion is ready ───────────────────────────╮
│ │
│ Easy Diffusion is ready to serve requests. │
│ │
│ A new browser tab should have been opened by now. │
│ If not, please open your web browser and navigate to http://localhost:9000/ │
│ │
╰──────────────────────────────────────────────────────────────────────────────╯

To Reproduce
Steps to reproduce the behavior:
I change the settings to V 3.5 or V 4 and restart and it does not finish loading.
I used V3.0 and restart, it works fine

Expected behavior
I expect to behave as in V3.0 and state stable diffusion is ready.
And then I expect to be able to generate an image

Screenshots
If applicable, add screenshots to help explain your problem.

Desktop (please complete the following information):

• OS: Linux - Pop!_OS 22.04 LTS
• Browser: Google Chrome
• Version: Version 151.0.7922.108 (Official Build) (x86_64)

Additional context
Adding Terminal data from the start.sh when using V3.5:

/usr/bin/curl
/usr/bin/tar
/usr/bin/bzip2
/usr/bin/git
/home/jurrel/AI-Image-Generator/easy-diffusion/installer_files/env/bin/conda

Easy Diffusion - v3

git version 2.34.1
Easy Diffusion's git repository was already installed. Updating from main..
No local changes to save
HEAD is now at 19c805e Pin sdkit3 to 3.3.0 for now, until regressions are fixed
Branch 'main' set up to track remote branch 'main' from 'origin'.
Already on 'main'
Your branch is up to date with 'origin/main'.
conda 23.9.0
Already up to date.
Current torch version: (2, 4, 1) (2.4.1+rocm6.1)
torchruntime: 2.4.0
torch: 2.4.1+rocm6.1
torchvision: 0.20.0+rocm6.1
sdkit: 2.1.1
stable-diffusion-sdkit: 2.1.5
diffusers: 0.28.2
{'backend': 'webui',
'backend_config': {},
'model': {'stable-diffusion': 'indigoFurryMix_v120Hybrid',
'vae': 'vae-ft-mse-840000-ema-pruned'},
'models_dir': '/home/jurrel/AI-Image-Generator/easy-diffusion/models',
'net': {'listen_port': 9000, 'listen_to_network': True},
'render_devices': ['cuda'],
'ui': {'open_browser_on_start': True},
'update_branch': 'main',
'use_v3_engine': False,
'vram_usage_level': 'balanced'}

Easy Diffusion installation complete, starting the server!

[WARNING] Support for Python 3.8 was dropped in ROCm 6.2. torchruntime will default to using ROCm 6.1 instead, but consider switching to a newer Python version to use the latest ROCm!
[INFO] Setting env variable HSA_OVERRIDE_GFX_VERSION=10.3.0
[INFO] Setting env variable HIP_VISIBLE_DEVICES=0
--- GPUs ---
PYTHONPATH=/home/jurrel/AI-Image-Generator/easy-diffusion/installer_files/env/lib/python3.8/site-packages
Python: /home/jurrel/AI-Image-Generator/easy-diffusion/installer_files/env/bin/python
Version: 3.8.5
Checking network settings
Set listen port to 9000
Set bind_ip to 0.0.0.0

Launching uvicorn

0. GPU(vendor_id='1002', vendor_name='Advanced Micro Devices, Inc. [AMD/ATI]', device_id='73ef', device_name='Navi 23 [Radeon RX 6650 XT / 6700S / 6800S]', is_discrete=True)

--- RECOMMENDED TORCH PLATFORM ---
[WARNING] Support for Python 3.8 was dropped in ROCm 6.2. torchruntime will default to using ROCm 6.1 instead, but consider switching to a newer Python version to use the latest ROCm!
rocm6.1

--- CONFIGURATION ---
[WARNING] Support for Python 3.8 was dropped in ROCm 6.2. torchruntime will default to using ROCm 6.1 instead, but consider switching to a newer Python version to use the latest ROCm!
[INFO] Setting env variable HSA_OVERRIDE_GFX_VERSION=10.3.0
[INFO] Setting env variable HIP_VISIBLE_DEVICES=0
01:04:24.372 INFO MainThread started in server.py:33
/home/jurrel/AI-Image-Generator/easy-diffusion/stable-diffusion
01:04:24.374 INFO MainThread started at 08/13/26 01:04:24 server.py:34
/home/jurrel/AI-Image-Generator/easy-diffusion/installer_files/env/lib/python3.8/site-packages/pydantic/_internal/_config.py:345: UserWarning: Valid config keys have changed in V2:

• 'orm_mode' has been renamed to 'from_attributes'
  warnings.warn(message, UserWarning)
  01:04:24.588 INFO MainThread Loading backend: webui backend_manager.py:99
  conda: /home/jurrel/AI-Image-Generator/easy-diffusion/installer_files/env/bin/conda
  01:04:24.613 INFO MainThread Loaded backend: <module backend_manager.py:69
  'webui' from
  '/home/jurrel/AI-Image-Generator/easy-diffusion/ui/easydif
  fusion/backends/webui.py'>
  01:04:24.619 INFO MainThread Backend dir: webui.py:94
  /home/jurrel/AI-Image-Generator/easy-diffusion/webui
  Traceback (most recent call last):
  File "/home/jurrel/AI-Image-Generator/easy-diffusion/installer_files/env/bin/conda", line 12, in
  from conda.cli import main
  File "/home/jurrel/AI-Image-Generator/easy-diffusion/installer_files/env/lib/python3.8/site-packages/conda/cli/init.py", line 3, in
  from .main import main # NOQA
  File "/home/jurrel/AI-Image-Generator/easy-diffusion/installer_files/env/lib/python3.8/site-packages/conda/cli/main.py", line 6, in
  from ..deprecations import deprecated
  File "/home/jurrel/AI-Image-Generator/easy-diffusion/installer_files/env/lib/python3.8/site-packages/conda/deprecations.py", line 13, in
  from packaging.version import Version, parse
  File "/home/jurrel/AI-Image-Generator/easy-diffusion/webui/system/lib/python3.10/site-packages/packaging/version.py", line 69, in
  LocalType = tuple[Union[int, str], ...]
  TypeError: 'type' object is not subscriptable
  Traceback (most recent call last):
  File "/home/jurrel/AI-Image-Generator/easy-diffusion/installer_files/env/bin/conda", line 12, in
  from conda.cli import main
  File "/home/jurrel/AI-Image-Generator/easy-diffusion/installer_files/env/lib/python3.8/site-packages/conda/cli/init.py", line 3, in
  from .main import main # NOQA
  File "/home/jurrel/AI-Image-Generator/easy-diffusion/installer_files/env/lib/python3.8/site-packages/conda/cli/main.py", line 6, in
  from ..deprecations import deprecated
  File "/home/jurrel/AI-Image-Generator/easy-diffusion/installer_files/env/lib/python3.8/site-packages/conda/deprecations.py", line 13, in
  from packaging.version import Version, parse
  File "/home/jurrel/AI-Image-Generator/easy-diffusion/webui/system/lib/python3.10/site-packages/packaging/version.py", line 69, in
  LocalType = tuple[Union[int, str], ...]
  TypeError: 'type' object is not subscriptable
  Traceback (most recent call last):
  File "/home/jurrel/AI-Image-Generator/easy-diffusion/installer_files/env/bin/conda", line 12, in
  from conda.cli import main
  File "/home/jurrel/AI-Image-Generator/easy-diffusion/installer_files/env/lib/python3.8/site-packages/conda/cli/init.py", line 3, in
  from .main import main # NOQA
  File "/home/jurrel/AI-Image-Generator/easy-diffusion/installer_files/env/lib/python3.8/site-packages/conda/cli/main.py", line 6, in
  from ..deprecations import deprecated
  File "/home/jurrel/AI-Image-Generator/easy-diffusion/installer_files/env/lib/python3.8/site-packages/conda/deprecations.py", line 13, in
  from packaging.version import Version, parse
  File "/home/jurrel/AI-Image-Generator/easy-diffusion/webui/system/lib/python3.10/site-packages/packaging/version.py", line 69, in
  LocalType = tuple[Union[int, str], ...]
  TypeError: 'type' object is not subscriptable
  01:04:25.635 ERROR MainThread Traceback (most recent call backend_manager.py:105
  last):
  File
  "/home/jurrel/AI-Image-Generator/easy-diffusion/ui/easydi
  ffusion/backend_manager.py", line 103, in start_backend
  backend.start_backend()
  File
  "/home/jurrel/AI-Image-Generator/easy-diffusion/ui/easydi
  ffusion/backends/webui.py", line 96, in start_backend
  install_backend() # will do nothing if already
  installed
  File
  "/home/jurrel/AI-Image-Generator/easy-diffusion/ui/easydi
  ffusion/backends/webui.py", line 86, in install_backend
  run_in_conda(["python", "-m", "pip", "install",
  "torchruntime"], cwd=WEBUI_DIR, env=env)
  File
  "/home/jurrel/AI-Image-Generator/easy-diffusion/ui/easydi
  ffusion/backends/webui.py", line 219, in run_in_conda
  return run(cmds, *args, **kwargs)
  File
  "/home/jurrel/AI-Image-Generator/easy-diffusion/ui/easydi
  ffusion/backends/common.py", line 16, in run
  p = subprocess.Popen(cmds, cwd=cwd, env=env,
  stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
  File
  "/home/jurrel/AI-Image-Generator/easy-diffusion/installer
  _files/env/lib/python3.8/subprocess.py", line 854, in
  init
  self._execute_child(args, executable, preexec_fn,
  close_fds,
  File
  "/home/jurrel/AI-Image-Generator/easy-diffusion/installer
  _files/env/lib/python3.8/subprocess.py", line 1702, in
  _execute_child
  raise child_exception_type(errno_num, err_msg,
  err_filename)
  FileNotFoundError: [Errno 2] No such file or directory:
  '/home/jurrel/AI-Image-Generator/easy-diffusion/webui/web
  ui'
  Traceback (most recent call last):
  File
  "/home/jurrel/AI-Image-Generator/easy-diffusion/ui/easydi
  ffusion/backend_manager.py", line 103, in start_backend
  backend.start_backend()
  File
  "/home/jurrel/AI-Image-Generator/easy-diffusion/ui/easydi
  ffusion/backends/webui.py", line 96, in start_backend
  install_backend() # will do nothing if already
  installed
  File
  "/home/jurrel/AI-Image-Generator/easy-diffusion/ui/easydi
  ffusion/backends/webui.py", line 86, in install_backend
  run_in_conda(["python", "-m", "pip", "install",
  "torchruntime"], cwd=WEBUI_DIR, env=env)
  File
  "/home/jurrel/AI-Image-Generator/easy-diffusion/ui/easydi
  ffusion/backends/webui.py", line 219, in run_in_conda
  return run(cmds, *args, **kwargs)
  File
  "/home/jurrel/AI-Image-Generator/easy-diffusion/ui/easydi
  ffusion/backends/common.py", line 16, in run
  p = subprocess.Popen(cmds, cwd=cwd, env=env,
  stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
  File
  "/home/jurrel/AI-Image-Generator/easy-diffusion/installer
  _files/env/lib/python3.8/subprocess.py", line 854, in
  init
  self._execute_child(args, executable, preexec_fn,
  close_fds,
  File
  "/home/jurrel/AI-Image-Generator/easy-diffusion/installer
  _files/env/lib/python3.8/subprocess.py", line 1702, in
  _execute_child
  raise child_exception_type(errno_num, err_msg,
  err_filename)
  FileNotFoundError: [Errno 2] No such file or directory:
  '/home/jurrel/AI-Image-Generator/easy-diffusion/webui/web
  ui'
  stable-diffusion model(s) found.
  gfpgan model(s) found.
  realesrgan model(s) found.
  vae model(s) found.
  01:04:25.680 INFO MainThread Start new Rendering Thread on task_manager.py:420
  device: cuda
  01:04:25.681 INFO cuda Setting cuda as active, with device_manager.py:123
  precision: half
  01:04:26.715 INFO MainThread Opening browser.. app.py:332
  ╭────────────────────────── Easy Diffusion is ready ───────────────────────────╮
  │ │
  │ Easy Diffusion is ready to serve requests. │
  │ │
  │ A new browser tab should have been opened by now. │
  │ If not, please open your web browser and navigate to http://localhost:9000/ │
  │ │
  ╰──────────────────────────────────────────────────────────────────────────────╯
  [0813/010426.989800:WARNING:chrome/app/chrome_main_linux.cc:84] Read channel stable from /app/extra/CHROME_VERSION_EXTRA
  [0813/010427.134549:WARNING:chrome/app/chrome_main_linux.cc:84] Read channel stable from /app/extra/CHROME_VERSION_EXTRA
  Opening in existing browser session.