A canvas to explore AI image models (open-source, BYOK).
Try it at koubou.app
Note: Google requires billing enabled to use Nano Banana via API. Learn More
- Image Generation: Just type any prompt in the text and submit.
- Image Editing: Select one or more images, then type your prompt and submit.
- Text-to-Image generation
- Image-to-Image editing
- Image upload & clipboard paste
- Image download (right-click)
- Infinite Canvas w/ pan & zoom
- Multi-image selection
- Delete selected images
- Resize images via drag handles
- Support for more models/services (OpenAI, Replicate, fal.ai)
- Bring-to-Front/Back
- Prompt history
- Improve experience for mobile devices
- Add "examples" section, with pre-defined prompts
- Add tests
- TBD
- Bun: A fast all-in-one JavaScript runtime.
- Vite: A next-generation frontend tooling.
- React: A JavaScript library for building user interfaces.
- TypeScript: A strongly typed superset of JavaScript.
- Shadcn UI: A collection of re-usable components built using Radix UI and Tailwind CSS.
- Tailwind CSS: A utility-first CSS framework.
To get this project up and running on your local machine, follow these steps:
-
Clone the repository:
git clone https://github.com/za01br/koubou.git cd koubou -
Install dependencies:
bun install
-
Start the development server:
bun dev
The application will be accessible at
http://localhost:5173(or another port if 5173 is in use).
Licensed under the MIT license.
If you have a feature request, bug report, or any other feedback, please open an issue.

