lzyuan1006
Joined 1 year ago
Karma
7
Submissions
13
Member since
Aug 13
nanobananas.ai
View on Hacker NewsRecent submissions
Comment · 1 year ago
We’ve been experimenting with combining three emerging AI tools: *NanoBanana, Sora2, and Veo3*.
The idea is to enable a complete creative pipeline:
- *Text → Image* (NanoBanana) - *Image → Enhanced Visuals* (Sora2) - *Visuals → Full Video* (Veo3)
This way, a user can start from plain text and end up with a polished video — without switching platforms.
The main question we’re exploring: When these models are chained together, what kind of results can we expect, and how far can this go in terms of creative workflows?
We’ve seen some early outputs that look promising (and sometimes mind-blowing). But we’d love to hear thoughts from the community: - What practical use cases do you see? - What potential limitations or risks should we be mindful of? - How would you imagine using this in your own projects?
Demo link: [https://nanobananas.ai?channel=SEEVPM8D]
Looking forward to your feedback!
Comment · 1 year ago
Can we leave it to Claude Code to do this?
Comment · 1 year ago
Interesting, it takes a lot of imagination to do it
Comment · 1 year ago
Expecting good things to happen, I prefer games like The Sims
Comment · 1 year ago
Me too
Comment · 1 year ago
After reading this book, old things will eventually be eliminated
Comment · 1 year ago
Safety still needs to be paid attention to, and children must still be classified