About the Project
Inspiration
We were inspired by the rise of weird and unexpected food combinations that constantly appear on social media. Platforms, foe example Tiktok, are full of viral trends where people mix unusual ingredients just to see what happens, sometimes it works, sometimes it’s completely chaotic.
We thought: what if we could use AI to take this idea even further?
That’s how FoodieGenie was born — a project where we let artificial intelligence generate creative, surprising, and sometimes “cursed” food combinations. Our goal was to turn randomness and curiosity into a fun, interactive experience.
How We Built It
We designed FoodieGenie as a full-stack application combining a modern frontend with powerful AI tools.
On the frontend, we used React to create an interactive and visually engaging interface where users can select their preferences and generate food combos.
On the backend, we used Node.js and Express to handle API requests and connect with Google's Gemini and Imagen models.
The core idea can be summarized as:
$$ \text{User Input} \xrightarrow{\text{Gemini AI}} \text{Creative Recipe} \xrightarrow{\text{Imagen}} \text{Generated Food Image} $$
We used:
- Gemini 2.5 Flash to generate the recipe, ingredients, and descriptions
- Imagen 4 to generate realistic food images
- A structured API flow to connect everything smoothly
All of this allowed us to transform simple user inputs into a complete, AI-generated food experience.
What We Learned
This project taught us a lot in a very short time.
We learned how to:
- Work effectively as a team and divide tasks efficiently
- Build a complete full-stack project under time pressure
- Integrate AI models into a real application
- Debug and fix issues quickly when things didn’t work
We also improved our ability to turn a simple idea into a working product that feels interactive and fun.
Challenges We Faced
One of the main challenges we faced was choosing the right AI model.
We spent time experimenting with different versions of Gemini to find the one that best fits our needs in terms of speed, creativity, and response quality.
This process required trial and error, testing outputs, and refining prompts until we achieved satisfying results.
We also faced typical development challenges such as debugging errors, handling API responses, and making sure the frontend and backend communicated correctly.
Conclusion
In the end, FoodieGenie represents a combination of creativity, teamwork, and technology.
We didn’t just build a generator, we created an experience where:
$$ \text{Creativity} + \text{AI} \rightarrow \text{Viral, Shareable Fun} $$
And most importantly, we had fun building something that reflects current trends while pushing them a step further.
Log in or sign up for Devpost to join the conversation.