DiffusionBee is a tool that facilitates the creation of AI art on your computer using Stable Diffusion. The software is free of charge, can be used offline, and does not have usage limits. It offers several cutting-edge features to generate AI art in an easy-to-use package. These features include:
- Text to image: Generate an image using a text prompt, allowing for the creation of images in any style.
- Image to image: Modify existing images using text prompts to create a new image based on a starting image.
- In-painting: Add or remove objects in an existing image at a selected region using a text prompt.
- Out-painting: Expand an image outwards using text prompts, selecting a region in the canvas and adding objects.
- Upscaling: Use AI to automatically increase the resolution of the generated image.
- Custom models: Use external Stable Diffusion models which are trained on specific styles or objects using DreamBooth.
- Advanced options: Includes options like negative prompt, diffusion steps, etc. for power users.
- Private: All the generation happens locally, and nothing is sent to the cloud.
DiffusionBee allows users to unlock their imagination by providing tools to generate AI art in a few seconds. You can use it to edit existing images or create new ones from scratch. All you need is a text prompt, and the AI will generate images based on your instructions. Furthermore, DiffusionBee offers easy-to-use tools, powered by AI, to modify your existing images. You can add or remove objects, change the style of the image, or transform the scene using text prompts.
The images generated by DiffusionBee are created locally on your computer, with nothing being sent to the cloud. On an 8GB M1 MacBook Air, it takes around 30 seconds to generate an image, but the speed can be higher on computers with better specs. The generated images can be freely used as long as users comply with the CreativeML Open RAIL-M license. DiffusionBee requires macOS 12.5.1 or higher and is recommended for machines with Apple silicon. However, it can also work with Intel-based machines, though it is considerably slower on these machines if they don’t have a dedicated graphics chip.
