1 Click Installer for Automatic1111 SD Web UI, SDXL, ControlNet, All ControlNet Models, Full xFormers and Latest Libraries Support for RTX 5000 Series GPUs and All Other GPUs With Torch 2.8 and CUDA 12.9

This is not an issue - Since there is still demand here RTX 5000 series updated installers

1 Click Installer for Automatic1111 SD Web UI, SDXL, ControlNet, All ControlNet Models, Full xFormers and Latest Libraries Support for RTX 5000 Series GPUs and All Other GPUs With Torch 2.8 and CUDA 12.9

https://www.patreon.com/posts/86307255

=======

Latest installer zip file : https://www.patreon.com/posts/86307255

• I have modified Automatic1111, ControlNet and ADetailer with minimal amount to make them work with latest GPUs and xFormers
  • Now our installer and apps supports starting from RTX 1000 series to RTX 5000 series including cloud GPUs like H100, B200, RTX PRO 6000 etc
  • Making them work with newest libraries were so hard but now we are using Torch 2.8, CUDA 12.9, xFormers 0.33
• The installer will install ADetailer and ControlNet by default but you have to download ControlNet models manually or run Windows_Optional_Download_ControlNet_Models.bat file after install
• Default Sampler set to UniPc and default steps count set to 40
• Tested on RTX 5090 and works perfect and amazingly fast with xFormers
• The app will start with xFormers by default both on Linux (MassedCompute and RunPod) and Windows
  • On MassedCompute and RunPod it will also auto start with Gradio live share to access from your computer
• Put Stable Diffusion models into stable-diffusion-webui\models\Stable-diffusion
• ControlNet models into stable-diffusion-webui\extensions\sd-webui-controlnet\models
• The app won't download any model like before when you first time start and you can start the app without loading any model - this was not possible before i fixed both

Windows Requirements

• Python 3.10, FFmpeg, CUDA 12.9, cuDNN 9.12 , C++ tools and Git
• If it doesn't work make sure to below tutorial and install everything exactly as shown in this below tutorial
• https://youtu.be/DrhUHnYfwC0

How To Install and Use:

Windows:

• Just run Windows_Install_or_Update.bat
• Then run Windows_Start_Automatic1111_Web_UI.bat

Massed Compute (Recommend Cloud) :

• Please register via this link : https://vm.massedcompute.com/signup?linkId=lp_034338&sourceId=secourses&tenantId=massed-compute
  • Use our coupon SECourses
  • Our coupon works on all GPUs now
    • RTX 6000 PRO has amazing price and speed but you can use like RTX A6000 ADA or L40S as well
    • Full details here : https://www.patreon.com/posts/26671823
  • Then select our image SECourses from Creator dropdown
  • Then follow Massed_Compute_Instructions_READ.txt
  • Same as my any other Massed Compute installer script
  • Example tutorial for learn how to install and use Massed Compute
    • (Starts at 12:58) : https://youtu.be/KW-MHmoNcqo?si=G1WbG-Qw4ujWvOtG&t=778

RunPod (Cloud):

• Please register via this link : https://get.runpod.io/955rkuppqv4h
  • Then follow Runpod_Instructions_READ.txt
  • Same as my any other RunPod installer script
  • Use the template written in Runpod_Instructions_READ.txt file
  • Example tutorial for learn how to install and use RunPod
    • (starts at 22:03) : https://youtu.be/KW-MHmoNcqo?si=QN8X8Sjn13ZYu-EU&t=1323

The post explicitly says it is not an issue and points to an external Patreon installer, with no repository file, test, or concrete change named. Start by checking whether maintainers want this closed or redirected; the payload provides no repository-based completion criteria.