NMKD Stable Diffusion GUI is a project to get Stable Diffusion installed and working on a Windows machine with fewer steps and all dependencies included in a single package.

Supports custom Stable Diffusion models and custom VAE models, inpainting, HuggingFace concepts, upscaling, face restoration, and it's in active development for adding more features using a GUI.

NMKD's project is also one of the few to support AMD GPUs (still experimental).


  • All dependencies included, no complicated installation
  • Supports text-to-image and image-to-image (image+text prompt)
  • Prompting Features: Attention/Emphasis, negative prompt
  • Supports custom Stable Diffusion models and custom VAE models
  • Run multiple prompts at once
  • Built-in image viewer showing information about generated images
  • Built-in upscaling (RealESRGAN) and face restoration (CodeFormer or GFPGAN)
  • Prompt Queue and Prompt History
  • Option to create seamless (tileable) images, e.g. for game textures
  • Supports loading custom concepts (Textual Inversion)
  • A variety of UX features
  • As fast as your GPU (1.7 seconds per image on RTX 4090, 2.6 on RTX 3090)
  • Built-in safety measures that scan downloaded models for malware

System Requirements

OS: Windows 10/11 64-bit


  • GPU: Nvidia GPU with 4 GB VRAM, Maxwell Architecture (2014) or newer
  • Alternatively, with limited feature support: Any DirectML-capable GPU with 8 GB of VRAM
  • RAM: 8 GB RAM (Note: Pagefile must be enabled as swapping will occur with only 8 GB!)
  • Disk: 10 GB (another free 5 GB for temporary files recommended)


  • GPU: Nvidia GPU with 8 GB VRAM, Pascal Architecture (2016) or newer
  • RAM: 16 GB RAM
  • Disk: 12 GB on SSD (another free 5 GB for temporary files recommended)


  • GPU: Nvidia GPU with 24GB VRAM, Turing Architecture (2018) or newer
  • RAM: 32 GB RAM
  • Disk: 12 GB on NVME SSD (another free 25 GB for temporary files recommended), system-managed paging file enabled