DiffusionBee

DiffusionBee is a local Stable Diffusion app for creating and editing AI images on macOS, running offline on-device and free of charge.

AI Photo & Image Generator AI Photo & Image Editor AI Art Generator Image to Image Text to Image

Visit Website

Overview

DiffusionBee is a Stable Diffusion app for generating AI art locally on a Mac. It packages several image-generation and editing tools into a single desktop workflow, with support for text-to-image, image-to-image, generative fill, upscaling, model training, control images, variants, and video-related tools.

The product emphasizes local processing: prompts, models, and generated images stay on your device, and the site describes the app as running 100% offline. The download page shows macOS builds for Apple silicon and Intel 64-bit Macs, plus a Windows 64-bit waitlist.

Features

Text to Image

Generate images from text prompts using Stable Diffusion on your own computer, without sending prompts or outputs to a cloud service.

Generative Fill

Edit existing images by adding or removing objects in selected areas with prompt-guided generative fill.

Image to Image

Transform one image into another using text prompts, which is useful for restyling or iterating on an existing composition.

Image Upscaler

Increase image sharpness and resolution with an AI upscaler for cleaner outputs or larger exports.

Train Models

Create custom image generation models from your own images and use them locally on-device.

Additional Creative Tools

Generate animations, videos, image variants, control-image outputs, and AI illusions from the same local app.

Use Cases

Generate AI Art on a Mac
Use text prompts to create new images locally when you want Stable Diffusion output without sending data to a cloud service.
Edit and Transform Existing Images
Start from an existing image and adjust it with prompts, whether you want to restyle the image or change specific regions.
Upscale Outputs
Improve resolution or sharpness before sharing or reusing an image in another workflow.
Create Custom Models
Train a custom model from your own images when you need outputs tied to a specific object, person, or style.
Explore Advanced AI Workflows
Use the app’s control-image, variants, and video-related tools when you need multiple local creative workflows in one desktop tool.

Pros and Cons

Pros

Runs locally on the user's device, so prompts, models, and generated images do not leave the computer.
Combines multiple Stable Diffusion workflows in one app, including generation, editing, upscaling, and training.
Supports macOS on both Apple silicon and Intel 64-bit Macs.
Includes an offline workflow, which suits users who want local control over their assets and outputs.
Provides a built-in path to train custom models from user-supplied images.

Cons

The source says Windows 64-bit is only on a waitlist, so the product is not fully available there yet.
Intel Macs are supported, but the site notes they can be much slower than Apple silicon machines, especially without a dedicated graphics chip.
The source does not provide pricing or tier details beyond describing the app as free of charge.

FAQ

Where are images generated?

Images are generated locally on your computer. The source states that nothing is sent to the cloud.

How long does image generation take?

The source says an 8GB M1 MacBook Air takes around 30 seconds per image, and faster computers can generate images more quickly.

Can I use the generated images commercially or freely?

Yes. The source says you can freely use generated images as long as you comply with the CreativeML Open RAIL-M license.

What are the minimum system requirements?

DiffusionBee needs macOS 13.1 or later. Apple silicon is recommended, and the source also says it works on Intel-based Macs, though more slowly without a dedicated graphics chip.

Does DiffusionBee support Windows?

The download page lists separate macOS builds for Apple silicon and Intel 64-bit Macs, and a Windows 64-bit option that is currently a waitlist.