DiffusionBee allows you to unlock your 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. It's easy to use, and the results can be quite stunning.

All you need is a text prompt and the AI will generate images based on your instructions.

Reimagine and transform your images

DiffusionBee offers easy-to-use tools, powered by AI, to modify your existing images. You can add/remove objects, change the style of the image, or transform the scene using text prompts.

Where are the images generated?

Images are generated locally on your computer. Nothing is sent to the cloud.

How much time does it take to generate an image?

On 8GB M1 MacBook Air, DiffusionBee takes around 30 seconds to generate an image. The speeds are much higher on computers with higher specs.

Can I freely use the generated images?

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

What are the minimum system requirements for DiffusionBee?

DiffusionBee needs macOS 12.5.1 on higher. Machines with Apple silicon are recommended.

Does DiffusionBee work with Intel based machines?

Yes, DiffusionBee works with Intel based machines. Although it is very slow compared to M1 machines if you don't have a dedicated graphics chip.


  • Text to image. Generate an image using a text prompt. Generate any image in any style.
  • Image to image. Modify existing images using text prompts. Create a new image based on a starting image
  • In-painting. Add/remove objects in an existing image at a selected region using a text prompt.
  • Out-painting. Expand an image outwards using text prompts. Select a region in the canvas and add 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/objects using DreamBooth.
  • Advanced options. Advanced options like negative prompt, diffusion steps, etc. for power users.
  • Private. All the generation happens locally and nothing is sent to the cloud.
  • Active community. An active community on Discord where you can ask us anything.

What's New

New features

  • ControlNet
  • SD2.x support
  • Fixes black screen issue with Intel
  • Ability to generate similar images
  • Multiple schedulers
  • Safetensors support