Closed m1-x3m closed 7 months ago
Hi, you'll need to download the installer and run it again, selecting GPU.
Note: You mentioned you are on v2.3.5. This is a very old version of the app.
Hi, you'll need to download the installer and run it again, selecting GPU.
Note: You mentioned you are on v2.3.5. This is a very old version of the app.
Thank you very much! It worked As for the version: my bad, it’s 3.7
Is there an existing issue for this problem?
Operating system
Windows
GPU vendor
Nvidia (CUDA)
GPU model
RTX 4060
GPU VRAM
8GB
Version number
2.3.5
Browser
Brave 1.62.165
Python dependencies
No response
What happened
when invokeai.bat launched, I wanted to change the Generation Device from CPU to GPu. but when I launch it again it shows the following error: Starting the InvokeAI browser-based UI.. [2024-02-21 22:57:15,411]::[InvokeAI]::INFO --> Patchmatch initialized Traceback (most recent call last): File "C:\Users\m1-x3\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 196, in _run_module_as_main return _run_code(code, main_globals, None, File "C:\Users\m1-x3\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 86, in _run_code exec(code, run_globals) File "C:\Users\m1-x3\invokeai.venv\Scripts\invokeai-web.exe__main.py", line 4, in
from invokeai.app.api_app import invoke_api
File "C:\Users\m1-x3\invokeai.venv\lib\site-packages\invokeai\app\api_app.py", line 43, in
from .api.dependencies import ApiDependencies
File "C:\Users\m1-x3\invokeai.venv\lib\site-packages\invokeai\app\api\dependencies.py", line 12, in
from ..services.board_images.board_images_default import BoardImagesService
File "C:\Users\m1-x3\invokeai.venv\lib\site-packages\invokeai\app\services\board_images\board_images_default.py", line 3, in
from invokeai.app.services.invoker import Invoker
File "C:\Users\m1-x3\invokeai.venv\lib\site-packages\invokeai\app\services\invoker.py", line 9, in
from .shared.graph import Graph, GraphExecutionState
File "C:\Users\m1-x3\invokeai.venv\lib\site-packages\invokeai\app\services\shared\graph.py", line 12, in
from invokeai.app.invocations import * # noqa: F401 F403
File "C:\Users\m1-x3\invokeai.venv\lib\site-packages\invokeai\app\invocations\latent.py", line 78, in
DEFAULT_PRECISION = choose_precision(choose_torch_device())
File "C:\Users\m1-x3\invokeai.venv\lib\site-packages\invokeai\backend\util\devices.py", line 35, in choose_precision
device_name = torch.cuda.get_device_name(device)
File "C:\Users\m1-x3\invokeai.venv\lib\site-packages\torch\cuda__init.py", line 419, in get_device_name
return get_device_properties(device).name
File "C:\Users\m1-x3\invokeai.venv\lib\site-packages\torch\cuda\init__.py", line 449, in get_device_properties
_lazy_init() # will define _get_device_properties
File "C:\Users\m1-x3\invokeai.venv\lib\site-packages\torch\cuda\ init__.py", line 289, in _lazy_init
raise AssertionError("Torch not compiled with CUDA enabled")
AssertionError: Torch not compiled with CUDA enabled
What you expected to happen
I expected to launch web GUI with CUDA
How to reproduce the problem
No response
Additional context
No response
Discord username
No response