Run Stable Diffusion locally on your Mac with a simple GUI app.
A one-click installer app for running text-to-image and image-to-image generation directly on your Mac.
Diffusion Bee is a native desktop application that provides a graphical interface for running Stable Diffusion locally on Intel and Apple Silicon Macs. It is designed for graphic designers and digital artists who want to generate AI imagery without configuring command-line tools or sending data to third-party cloud services.
It wraps Stable Diffusion models into an Electron app with built-in support for text-to-image, image-to-image, inpainting, outpainting, upscaling, ControlNet, and LoRA. You can download different model checkpoints directly inside the app, manage your generation history, and apply negative prompts.
It suits macOS users who want a straightforward, privacy-focused way to experiment with Stable Diffusion models locally. It does not suit Windows users or anyone lacking a compatible Intel or M1/M2 Mac with sufficient hardware resources.
Get started immediately on macOS without needing to install Python dependencies or configure terminal commands.
Guide your image generation using structural inputs like edge maps and pose estimations directly in the app.
Modify specific regions of your images or expand canvases using targeted brush masks.
Download and switch between SD 1.x, SD 2.x, SD XL, and LoRA models right from the application interface.
Diffusion Bee is free under its open source licence, and the only cost is running it locally on your own Mac hardware.
870 open remote AI-training roles, updated November 14, 2026; most pay $20–$170 an hour. Zekai lists them free; the application goes to the employer’s platform.
These reviewed AI tools do the same job instantly — from our scored directory.
No, generation happens entirely on your local computer unless you explicitly choose to upload an image.
You need an Intel Mac running macOS 12.3.1 or later, or an M1/M2 Mac running macOS 11.0.0 or later.
Yes, the app natively supports SD 1.x, SD 2.x, SD XL, Inpainting, ControlNet, and LoRA models.
See Zekai first in Google