Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Nano Banana 2 Lite

deepmind.google

Post reply on HN
Print view View original

11–20 of 214 posts

Re: Nano Banana 2 Lite

#11

Post by minimaxir »

algoth1 wrote: post #2

They didnt include chatgpt in the comparison chart. That tells a lot

That is fair to point out. For those who don't know, ChatGPT Image 2 has an absurd ELO of 1387; compared to the #2 model at 1273, it's over 100 points higher (https://arena.ai/leaderboard/text-to-image). The tradeoff is latency, and ChatGPT Image 2 at High is...slow (~2 minutes at 1024x1024). In both cases it would have skewed the charts here to uselessness.

I want to do a writeup on ChatGPT Image 2 but at this point I don't think people care about nuanced image generation anymore...even though ChatGPT Image 2 crushes all my existing tests.

Re: Nano Banana 2 Lite

#12

Post by monegator »

minimaxir wrote: post #5

I received early access to test this model. (through work — Google still does not like me personally lol) It works as advertised here, and it does behave like a distilled Nano Banana 2 with respect to certain elements such as good text rendering, which Nano Banana 1 does much worse with. It is definitely not at the level of the base Nano Banana 2 of course particularly with highly-nuanced prompts. My main criticism i…

but until this comes to edge gallery i won't care

Re: Nano Banana 2 Lite

#14

Post by ramesh31 »

It's only half the full model price, $30/m output: https://cloud.google.com/gemini-enterprise-agent-platform/ge...

Nano Banana is head and shoulders above the rest, but still too steep for personal use, and half off doesn't really mean much for enterprise if the results are worse. Hopefully this drives the rest to catch up at least.

Re: Nano Banana 2 Lite

#15

Post by vunderba »

minimaxir wrote: post #5

I received early access to test this model. (through work — Google still does not like me personally lol) It works as advertised here, and it does behave like a distilled Nano Banana 2 with respect to certain elements such as good text rendering, which Nano Banana 1 does much worse with. It is definitely not at the level of the base Nano Banana 2 of course particularly with highly-nuanced prompts. My main criticism i…

You can set aspect ratios with NB2 Lite programmatically through Vertex [1]. I updated the program I use to help create all the images for GenAI Showdown, set the model ID to `gemini-3.1-flash-lite-image`, and was able to use aspect ratios like 16:9, 4:3, and others.

[1] - https://cloud.google.com/developers/vertex-ai

Re: Nano Banana 2 Lite

#16

Post by shmolyneaux »

minimaxir wrote: post #11
algoth1 wrote: post #2

They didnt include chatgpt in the comparison chart. That tells a lot

That is fair to point out. For those who don't know, ChatGPT Image 2 has an absurd ELO of 1387; compared to the #2 model at 1273, it's over 100 points higher ( https://arena.ai/leaderboard/text-to-image ). The tradeoff is latency, and ChatGPT Image 2 at High is...slow (~2 minutes at 1024x1024). In both cases it would have skewed the charts here to uselessness. I want to do a writeup on ChatGPT Image 2 but at this poi…

I definitely appreciated your post about Nano Banana Pro. It's also a genuinely useful time-capsule for how these systems evolve and where they fall short. I've preferred the output of ChatGPT Image 2. I think a post would be very helpful for folks to see what they're missing.

Re: Nano Banana 2 Lite

#17

Post by torginus »

The first example of generating home interiors fills me with indescribable hatred. Recently real estate agents have taken to running every dilapidated unsellable apartment through these AI filters, and you have to scroll through a dozen of these Ikea-chic images of what the apartment presumably could look like, before you are allowed to see the horrors they are trying to peddle at insane prices.

Re: Nano Banana 2 Lite

#19

Post by psygn89 »

torginus wrote: post #17

The first example of generating home interiors fills me with indescribable hatred. Recently real estate agents have taken to running every dilapidated unsellable apartment through these AI filters, and you have to scroll through a dozen of these Ikea-chic images of what the apartment presumably could look like, before you are allowed to see the horrors they are trying to peddle at insane prices.

I think that should be illegal and misrepresenting. Lots of gray area with AI usage.

Re: Nano Banana 2 Lite

#20

Post by ianhawes »

mikert89 wrote: post #3

gemini is so far behind. starting to wonder if their strategy is launching the low cost alternative to image/text models. last release was 3.5 flash

Imagine saying Gemini is so far behind when Llama has unreleased max models from last year that are currently beat by quantized Qwen2.5 models.
Post reply on HN