Discover and explore top open-source AI tools and projects—updated daily.
Multimodal AI hackathon kit for dynamic visual creation
New!
Top 40.6% on SourcePulse
Summary
This repository serves as the official starter kit and resource hub for the Nano Banana 48 Hour Challenge, hosted by Google DeepMind. It equips participants with everything needed to build applications using Gemini 2.5 Flash Image Preview, a state-of-the-art image model. The kit aims to accelerate development for hackers and developers, enabling them to create innovative visual interaction experiences and compete for significant prizes.
How It Works
The core of the kit is Gemini 2.5 Flash Image Preview (Nano Banana), a model designed for dynamic creation through text prompts. It allows users to generate and edit images, blend realities, and access Gemini's world knowledge. This approach enables novel applications that transform how users interact with visuals, focusing on areas like dynamic storytelling, e-commerce visualization, automated creative workflows, and advanced photo editing.
Quick Start & Requirements
https://ai.google.dev/gemini-api/docs/image-generation
, Prompting Guide & Strategies: https://ai.google.dev/gemini-api/docs/image-generation#prompt-guide
. Kaggle Competition Page: https://www.kaggle.com/competitions/banana
.Highlighted Details
Maintenance & Community
Licensing & Compatibility
Limitations & Caveats
1 week ago
Inactive