Hello everyone,
I recently submitted my entry for the Google AI Hackathon on devpost, and used Panda3D in my submission!
DesignMyRoom takes in a user input, and decorates a room based on that input using Google Gemini and Kenny’s Incredible Furniture Kit.
The most challenging part was definitely the prompt engineering. It was really difficult to consistently get accurate and efficient results, and combined with how little Gemini knew about the exact details of the assets it used, it often got rotations incorrect. Also Gemini kept loading in files that simply don’t exist despite listing out the files numerously.
And like every other LLM, Gemini does mess up in comprehending the exact positional instructions of each prompt, and placement of objects can be random and inconsistent. However I think I’ve managed it well compared to when I first realized its flaws for the first time.
Source code
Devpost submission
I will greatly welcome any feedback!