Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
siva7
8 days ago
|
parent
|
context
|
favorite
| on:
Gemini 3 Pro: the frontier of vision AI
What's the difference? I thought the vision ai component of gemini 3 is called nano banana?
IanCal
8 days ago
|
next
[–]
That’s about generating images, the other side is about understanding images.
reply
brokensegue
8 days ago
|
prev
[–]
i assumed nano banana was just a tool that gemini 3 used though i don't know
reply
minimaxir
8 days ago
|
parent
[–]
Gemini 3 Pro's text encoder powers Nano Banana Pro, but it has its own image decoding model that decodes the generated image tokens into an actual image, which appears to be the more pertinent issue in this case.
reply
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: