When my first thought was of an SBC, then a media AI cloud product was not high up on my guess list.
Nano Banana Pro
491–500 of 718 posts
Re: Nano Banana Pro
#492Something I find weird about AI image generation models is that even though they no longer produce weird "artifacts" that give away that the fact that it was AI generated, you can still recognize that it's AI due to stylistic choices. Not all examples they gave were like this. The example they gave of the word "Typography" would have fooled me as human-made. The infographics stood out though. I would have immediately…
The problem is how they are fine tuned with human feedbacks that are not opinionated, so they produce some "average taste" that is very recognizable. Early models didn't have this issue, it's a paradox... Lower quality / broken images but often more interesting. Krea & Black Forest did a blog post about that some time ago.
I wonder if we'll get to the point where we train different personalities into an image model that we can bring out in the prompt and these personalities have distinct art/picture styles they produce.
Re: Nano Banana Pro
#493The visual quality of photorealistic images generated in the Gemini app seems terrible.
Like really ugly. The 1K output resolution isn't great, but on top of that it looks like a heavily compressed JPEG even at 100% viewing size.
Does AI Studio have the same issue? There at least I can see 2K and 4K output options.
Re: Nano Banana Pro
#494Something I find weird about AI image generation models is that even though they no longer produce weird "artifacts" that give away that the fact that it was AI generated, you can still recognize that it's AI due to stylistic choices. Not all examples they gave were like this. The example they gave of the word "Typography" would have fooled me as human-made. The infographics stood out though. I would have immediately…
The problem is how they are fine tuned with human feedbacks that are not opinionated, so they produce some "average taste" that is very recognizable. Early models didn't have this issue, it's a paradox... Lower quality / broken images but often more interesting. Krea & Black Forest did a blog post about that some time ago.
Oh yeah, funny enough even though I’m a bit of an AI art hater I actually thought very early Midjourney looked good because of all had an impressionistic, dreamy quality.
Re: Nano Banana Pro
#495Earlier quoted context omitted.
This watermarking ceremony is useless. We will always have local models. Eventually the Chinese will release a Nano Banana equivalent as open source.
> We will always have local models. If watermarking becomes a legal mandate, it will inevitably include a prohibition on distributing (and using and maybe even possessing, but the distribution ban is the thing that will have the most impact, since it is the part that is most policable, and most people aren't going to be training their own models, except, of course, the most motivated bad actors) open models that do n…
I don't see how banning distribution would do anything: distributing pirated games, movies, software is banned in most countries and yet pirated content is trivial to find for anyone who cares.
As long as someone somewhere is publishing models that don't watermark output, there's basically nothing that can stop those models from being used.
Re: Nano Banana Pro
#496The visual quality of photorealistic images generated in the Gemini app seems terrible. Like really ugly. The 1K output resolution isn't great, but on top of that it looks like a heavily compressed JPEG even at 100% viewing size. Does AI Studio have the same issue? There at least I can see 2K and 4K output options.
I have a couple of 25MB PNG 4K images from AI Studio here:
https://drive.google.com/file/d/1QV3pcW1KfbTRQscavNh6ld9PyqG...
https://drive.google.com/file/d/18AzhM-BUZAfLGoHWl6MQW_UW9ju...
Re: Nano Banana Pro
#497Everyone who worked on this is a traitor to the human race. Why do we need to make it impossible to make a living as an artist? Who thinks an endless tsunami of garbage “content” churned out by machines dropping the bottom out of all artistic disciplines is a good idea?
> Everyone who worked on this is a traitor to the human race.
Have we felt this way for all other large scale advances in human history?
Re: Nano Banana Pro
#498Alright results are in! I've re-run all my editing based adherence related prompts through Nano Banana Pro. NB Pro managed to successfully pass SHRDLU, the M&M Van Halen test (as verified independently by Simon), and the Scorpio street test - all of which the original NB failed. Model results 1. Nano Banana Pro: 10 / 12 2. Seedream4: 9 / 12 3. Nano Banana: 7 / 12 4. Qwen Image Edit: 6 / 12 https://genai-showdown.spec…
I think Nano Banana Pro should have passed your giraffe test. It's not a great result but it is exactly what you asked for. It's no worse than Seedream's result imo.
Yeah it’s better than the weirdness of seedream for sure.
Re: Nano Banana Pro
#499Earlier quoted context omitted.
another interesting use case with synth https://chat.vlm.run/c/1c726fab-04ef-47cc-923d-cb3b005d6262 . made a puppet from a image of a model and made the puppet dance.
The feet are doing unusual movements. Reminds me of leaf node cumulative error in overcompressed hierarchical animation.
yeah the video models still do not understand physics the way humans do. We are getting there one step at a time. By the way, I am seeing a lot of people complain about google billing not working well. I was able to generate these for free without signing. Look at the results and try to come up with your own failure and working use cases.
Re: Nano Banana Pro
#500I...worked on the detailed Nano Banana prompt engineering analysis for months ( https://news.ycombinator.com/item?id=45917875 )...and...Google just...Google released a new version. Nano Banana Pro should work with my gemimg package ( https://github.com/minimaxir/gemimg ) without pushing a new version by passing: g = GemImg(model="gemini-3-pro-image-preview") I'll add the new output resolutions and other features ASAP…
>> - Put a strawberry in the left eye socket. >>- Put a blackberry in the right eye socket. >> All five of the edits are implemented correctly This is a GREAT example of the (not so) subtle mistakes AI will make in image generation, or code creation, or your future knee surgery. The model placed the specified items in the eye sockets based on the viewers left/right; when we talk relative in this scenario we usually (…
That was a big problem when I was toying around the original Nano Banana. I always prompted the perspective of the (imaginary) camera, and yet NB often interpreted that as that of the target, giving no way to select the opposite side. Since the selected side is generally closer to the camera, my usual workaround is to force the side far from the camera. And yet that was not perfect.