Gemini 2.5 Flash Image

#1

Post by meetpateltech » Tue, Aug 26, 2025, 2:01 PM UTC

Also: https://deepmind.google/models/gemini/image/, https://techcrunch.com/2025/08/26/google-geminis-ai-image-mo...

Gemini 2.5 Flash Image
developers.googleblog.com

Re: Gemini 2.5 Flash Image

#2

Post by qoez » Tue, Aug 26, 2025, 2:26 PM UTC

Anyone know how it handles '1920s nazi officer'? They stopped doing humans for a while but now I see they're back so I wonder how they're handling the criticism they got from that

Re: Gemini 2.5 Flash Image

#3

Post by dpoloncsak » Tue, Aug 26, 2025, 2:29 PM UTC

I've been looking for a whitepaper or something. So far I've found this...which is not a whitepaper but seems relevant

https://developers.googleblog.com/en/introducing-gemini-2-5-...

It seems like this is 'nano-banana' all along

Re: Gemini 2.5 Flash Image

#4

Post by lifthrasiir » Tue, Aug 26, 2025, 2:30 PM UTC

FYI, this is the famed nano-banana model which has been now renamed to gemini-2.5-flash-image-preview in LMArena.

Re: Gemini 2.5 Flash Image

#5

Post by simedw » Tue, Aug 26, 2025, 2:31 PM UTC

The model is only available in AI Studio when I set my VPN to the USA (I’m located in the UK).

Re: Gemini 2.5 Flash Image

#6

Post by napo » Tue, Aug 26, 2025, 2:31 PM UTC

qoez wrote: post #2

Anyone know how it handles '1920s nazi officer'? They stopped doing humans for a while but now I see they're back so I wonder how they're handling the criticism they got from that

it said: "I can create images about lots of things but not that. Can I try a different one for you?"

Re: Gemini 2.5 Flash Image

#7

Post by patates » Tue, Aug 26, 2025, 2:32 PM UTC

It seems that they still block access from Europe, or from Germany at least.

Re: Gemini 2.5 Flash Image

#8

Post by napo » Tue, Aug 26, 2025, 2:33 PM UTC

napo wrote: post #6

qoez wrote: post #2

Anyone know how it handles '1920s nazi officer'? They stopped doing humans for a while but now I see they're back so I wonder how they're handling the criticism they got from that

it said: "I can create images about lots of things but not that. Can I try a different one for you?"

when giving more context it replied:

""" Unfortunately, I can't generate images of people. My purpose is to be helpful and harmless, and creating realistic images of humans can be misused in ways that are harmful. This is a safety policy that helps prevent the generation of deepfakes, non-consensual imagery, and other problematic content.

If you'd like to try a different image prompt, I can help you create images of a wide range of other subjects, such as animals, landscapes, objects, or abstract concepts. """

Re: Gemini 2.5 Flash Image

#9

Post by lemonish97 » Tue, Aug 26, 2025, 2:36 PM UTC

dpoloncsak wrote: post #3

I've been looking for a whitepaper or something. So far I've found this...which is not a whitepaper but seems relevant https://developers.googleblog.com/en/introducing-gemini-2-5-... It seems like this is 'nano-banana' all along

Yes, they mention that the model is aka nano-banana in the blogpost

Re: Gemini 2.5 Flash Image

#10

Post by punkpeye » Tue, Aug 26, 2025, 2:37 PM UTC

patates wrote: post #7

It seems that they still block access from Europe, or from Germany at least.

Use one of the router services