Github & "Stable Diffusion 1111"

[Bebono52]

Hello, I can't get the webui to run. An error message appears:

Could you help me solve this? Thank you very much.

[w-e-w]

what GPU do you have in your system?

[Bebono52]

Hello, thank you for replying, my GPU is as follows: Intel(R) UHD Graphics 620NVIDIA GeForce MX 150 Le vendredi 27 juin 2025 à 00:26:21 UTC+2, w-e-w ***@***.***> a écrit : what GPU do you have in your system? — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: ***@***.***>

[w-e-w]

I suspect you have an old graphics driver
have you updated your Nvidia graphics driver what version are you on?

---

MX150 is a relatively poor GPU with only 2GB of VRAM

it is quite possible that it won't run because of not having enough VRAM even if you use --lowvram or --medvram see
https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Command-Line-Arguments-and-Settings
https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Optimizations
also consider Tiled VAE extension to reduce further reduce VRAM usage
https://github.com/pkuliyi2015/multidiffusion-upscaler-for-automatic1111

base on https://vladmandic.github.io/sd-extension-system-info/pages/benchmark.html
there's two entries of people using MX150 it is possible that it will work
note even you got it working the performance is going to be very poor

[Bebono52]

Thank you very much for all these details. Mine : NVIDIA GeForce MX 150 ( 4 Go GDDR5 ) I found this update , is it worth it :  Version du pilote: 576.80 - WHQL Date de sortie: Tue Jun 17, 2025 Système d’exploitation: Windows 10 64-bit, Windows 11 Langue: Français Taille du fichier: 869.34 MB Le vendredi 27 juin 2025 à 10:59:47 UTC+2, w-e-w ***@***.***> a écrit : I suspect you have an old graphics driver have you updated your Nvidia graphics driver what version are you on? MX150 is a relatively poor GPU with only 2GB of VRAM it is quite possible that it won't run because of not having enough VRAM even if you use --lowvram or --medvram see https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Command-Line-Arguments-and-Settings https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Optimizations also consider Tiled VAE extension to reduce further reduce VRAM usage https://github.com/pkuliyi2015/multidiffusion-upscaler-for-automatic1111 base on https://vladmandic.github.io/sd-extension-system-info/pages/benchmark.html there's two entries of people using MX150 it is possible that it will work note even you got it working the performance is going to be very poor — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: ***@***.***>

[pongleader]

os:windows11 RTX5070Ti
(1)python 3.11.9 + git + https://github.com/AUTOMATIC1111/stable-diffusion-webui.git
(2)edit \modules\lanch_ultil.py
....
torch_index_url = os.environ.get('TORCH_INDEX_URL', "https://download.pytorch.org/whl/cu121") fix -->cu128

torch_command = os.environ.get('TORCH_COMMAND', f"pip install torch==2.1.2 torchvision==0.16.0 --extra-index-url {torch_index_url}")
fix -->torch==2.7.1 torchvision==0.22.1
.....
xformers_package = os.environ.get('XFORMERS_PACKAGE', 'xformers==0.0.23.post1' -->xformers==0.0.31.post1

(3) webui-user.bat
set COMMANDLINE_ARGS=--xformers