DiffusionBee
A free, open-source Stable Diffusion app generates and edits images offline on macOS, with SDXL support and local custom model training.
DiffusionBee is an AI image app for Mac users who want to create and edit artwork locally through a visual interface. Artists and designers can work with text prompts, existing images and drawings without writing code.
- Image creation: Generate pictures from text, revise existing images with prompts or produce image variants, with control images to guide composition.
- Targeted editing: Add or remove objects with generative fill, edit selected areas with inpainting and extend images beyond their edges with outpainting.
- Drawing and upscaling: Combine drawing with prompts in the AI canvas and increase image resolution with the upscaler.
- Custom models: Train image models locally on your own pictures to generate particular people, objects or styles.
- Animation and video: Use AI tools to generate animations and videos, alongside image illusion generation.
The free app supports SD 1.x, SD 2.x, SDXL, ControlNet, LoRA and inpainting models. Generation works offline after model downloads, with processing on your Mac. It requires macOS 13.1 or later and recommends Apple Silicon. Intel Macs also work, but generation is much slower without a dedicated graphics chip.
The app uses AGPL-3.0. Stable Diffusion's CreativeML Open RAIL-M terms apply to use of its generated images.
Logotyper
