# Dunkoma

- **Event:** [Gemini 4 NYC Hackathon](https://cerebralvalley.ai/e/gemini-4-nyc)
- **When:** Sat, Nov 21 at 9:00 AM – 10:00 PM (EST)
- **Where:** New York, NY
- **Team:** [Allen Lu](https://cerebralvalley.ai/u/allen-lu-1), [David Zhang](https://cerebralvalley.ai/u/daviii), [Alex Yen](https://cerebralvalley.ai/u/Alexyen04), [James Chen](https://cerebralvalley.ai/u/jchen137)
- **GitHub:** https://github.com/Alexyen04/Gemini-4-Hackathon
- **Demo video:** https://drive.google.com/file/d/1318GxKE7vd4Zao2-9yYAPGC9G01VnR73/view?usp=sharing
- **Gallery:** https://cerebralvalley.ai/e/gemini-4-nyc/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/gemini-4-nyc/hackathon/gallery/44

Dunkoma turns basketball footage into a story driven manga instead of a conventional highlight reel. Upload a game video or clips and choose a focus such as a player or comeback. The pipeline scouts the footage, scores moments for both visual spectacle and narrative importance, and builds a manga arc from the selected plays. Each illustrated panel is tied to a source clip and timestamp, so readers can click through to see the real play behind the artwork. A deterministic, frame guided renderer provides a fallback when AI illustration is unavailable. The result is an interactive, editable manga reader that makes a game’s story engaging without losing its connection to the footage.

## More from Gemini 4 NYC Hackathon

- [Pour Labs](https://cerebralvalley.ai/e/gemini-4-nyc/hackathon/gallery/41)
- [Agent Boost](https://cerebralvalley.ai/e/gemini-4-nyc/hackathon/gallery/42)
- [@labs](https://cerebralvalley.ai/e/gemini-4-nyc/hackathon/gallery/43)
- [INTERLOCK](https://cerebralvalley.ai/e/gemini-4-nyc/hackathon/gallery/45)
- [Glint](https://cerebralvalley.ai/e/gemini-4-nyc/hackathon/gallery/46)
- [Mozart](https://cerebralvalley.ai/e/gemini-4-nyc/hackathon/gallery/47)

---

Markdown version of https://cerebralvalley.ai/e/gemini-4-nyc/hackathon/gallery/44. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt
