# Chibi Nano

- **Event:** [Nano Banana Hackathon](https://cerebralvalley.ai/e/nano-banana)
- **When:** Sat, Sep 6 at 9:00 AM – 9:00 PM (PDT)
- **Where:** 365 Toni Stone Crossing, San Francisco, CA
- **Team:** [Selali Adobor](https://cerebralvalley.ai/u/selali), [Sharon Tan](https://cerebralvalley.ai/u/sharonxh), [Kaiwei Chen](https://cerebralvalley.ai/u/kaiwei)
- **GitHub:** https://github.com/selalipop/chibi-robo
- **Demo video:** https://www.loom.com/share/04e759de03444b00b4e5ecfff7305318?sid=59ed6b19-56d1-405f-a8d0-6a40042428d1
- **Gallery:** https://cerebralvalley.ai/e/nano-banana/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/nano-banana/hackathon/gallery/39

“Chibi Nano” is an embodied photo booth for creating memorable and hyper-customized personal or corporate gifts. Starting with a selfie, our pipeline orchestrates between Gemini 2.5 Pro, Gemini 2.5 Flash Preview (Nano Banana), and FAL Hunyuan3D to transform that 2d input into 3D-printed Chibi characters arranged in a compelling scene. 

Specifically:
Gemini 2.5 Pro analyzes the input photo, and generates prompts for each person or object detected
Gemini 2.5 Flash Preview takes in those prompts to generate Chibi images
From each of those images, FAL Hunyuan3D generates a 3D mesh file.
Gemini 2.5 Flash Preview also takes in all of those images and composes them into an “Artists’ Impression” scene suggesting how the user could arrange their 3D-printed models. 
We then transfer the 3D mesh files to Bambu Studio for on-the-spot printing. In future iterations, this step will be automated as well.

---

Markdown version of https://cerebralvalley.ai/e/nano-banana/hackathon/gallery/39. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt