and also left out Nano Banana Pro, which in my opinion is still better in many cases then NB2 ... even on the site arena.ai, it's still best at editing
Wow, that's a pretty massive decrease in latency, which should unlock some use cases, but the linked web page doesn't exactly make it straightforward to understand the differences between the models.
However, based off my personal experiences with general images models, Google in my opinion is the best for my workflows. Granted, I haven't tried far-east providers yet.
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 is that you cannot programmatically force aspect ratios with NB2L but you can with NB2.
That said, the price of $0.034/image is higher than expected since price is generally correlated with generation time, and it takes half the time to generate than a Nano Banana 1 image which costs $0.039/image. Google's assertion that you can directly replace NB1 pipelines with NB2L is fair.
Yesterday, Google announced that the Gemini app will allow free image generations (https://blog.google/innovation-and-ai/products/gemini-app/pe...) but did not specify which model would be used: I suspect it's the main motivation for Nano Banana 2 Lite.
Can it make diagrams that can be imported into .pptx or google slides as actual diagrams (SVG in PowerPoint I guess) i.e. you can move the components, there are real arrows, etc… or does it strictly produce raster images?
Fable is the first model I found that can actually produce such diagrams in slides, in .pptx format that exports cleanly and consistently to Google slides, and is also able to iterate on those diagrams with specific feedback like “center align the arrow with the blue pill on the left which should be vertically aligned inside the dashed database container and make the arrow terminate in the left edge vertical center of the light blue object storage container.”
I was surprised with how well grok imagine performed when reviewing fast image generation. It balances quality, speed and cost really well with under $0.02 per 1K image within a few seconds.
I'm way behind in imagegen - only using it occasionally for roleplaying tokens, goofing around, and random personal assets. To me, this is nuts. It's able to create images in like 2 seconds... before with chatgpt it would take 30s-1m for the same quality image. I don't get the negative comments here
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.
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 keep hoping the fucking barn doors people are putting in houses now are an AI illusion, but that's never the case. Barn doors. In the god damned house. Talk about a crime.
I sense a business opportunity: a web app that de-sloppifies real estate, airbnb, and vrbo photos! See what it really looks like, thanks to the power of AI!
Isnt this what people have been doing for years now with their phone filters? misrepresenting their physical appearance in order to sell the idea that they are something they're not
The speed is definitely impressive. I'm seeing under 5 seconds per image vs ~30 seconds for base NB2.
I built an app for my kids that generates illustrated stories for them with them as the characters. I wanted to prioritize likeness while still stylizing the illustrations. I tested a bunch of models but none seem to come close to maintaining likeness when stylized. I find the others generate generic looking characters.
I'm excited to incorporate this into the onboarding of my app since I want the users to experience the aha moment as soon as possible and waiting half a minute+ isn't ideal. I'll still be using the main NB2 for the actual illustrations as this lite version still has slight issues with nuance and consistency as others have pointed out.
Expensive and Google doesn't even have enough resources to decently deploy a model like that. Creating 10 images in parallel gives me RESOURCE_EXHAUSTED error, which is a painfully common error when using Google AI products.
I've been testing for the last 2 hours and compared to GPT Image 2. The pricing for 1K resolution it costs $0.0342, takes 8 seconds (not 3 sec). Compared to the GPT Image 2 api ($0.0414 for the same res, responding in 35-45 seconds) I am pleased with its quality and pricing. The texts come garbled, it adds them to every image generated without the prompt, but negative prompts do work well to remove those.
It tends to generate depressing-looking lighting, but if instructed, it overcomes it. Up close, faces also look pretty decent. I can still tell it is AI-generated, but to an untrained eye, it is nearly impossible to distinguish, especially for regular blog posts and ads.
That's nice but it's on google's broken AI studio thing. I can't use half the stuff on there because it requires a Google One account. Which I'm ineligible for because I'm on a workspace account. Can I switch? No, because Google One doesn't support own domains.
So I need to run (AND PAY!) two accounts to have both a nice email address and Banana? Starting to think the correct number of paid google accounts here is zero.
FYI: If you are willing to pay API rates AI studio supports using API keys. To do this on the slashed off key icon on the bottom left of the textbox and go through the process
no human wrote the prompts listed as example prompts here.
"In a breathtaking display of surreal transformation, a cinematic moment of pure action unfolds against a textured, golden-brown canvas. From the right, a woman is seen in elegant profile, her lips a startling slash of red. Her quiet composure is violently contradicted by the explosive event taking place: her dark hair is erupting, bursting forth into a chaotic flock of black birds. These creatures are captured mid-flight, a dynamic swarm launching from her mind and sweeping across the frame to the left. The motion is palpable; you can almost hear the frantic beating of a hundred wings as they break free. Some birds are still tangled, emerging from the dark mass of her hair, while others are already soaring into the open space. This is not a gentle release, but a powerful, almost violent, act of creation or liberation. The camera captures this impossible metamorphosis head-on, focusing on the sheer force of the birds' exodus. This highly sophisticated image is a kinetic masterpiece, portraying an internal storm made external, a thought process so intense it literally takes flight in a beautiful, dark, and unstoppable flurry of action."
really? anyone using for more than 10 or so tries these knows how to prompt them, and its not "The motion is palpable; you can almost hear the frantic beating of a hundred wings"
"surreal transformation, cinematic action. Textured golden-brown canvas. A woman in profile, red lips. Dark hair erupting into a flock of black birds mid-flight. Explosive metamorphosis" is pretty much all the actual meaning captured here
40 comments
[ 0.24 ms ] story [ 41.4 ms ] threadHowever, based off my personal experiences with general images models, Google in my opinion is the best for my workflows. Granted, I haven't tried far-east providers yet.
What does everyone else think?
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 is that you cannot programmatically force aspect ratios with NB2L but you can with NB2.
That said, the price of $0.034/image is higher than expected since price is generally correlated with generation time, and it takes half the time to generate than a Nano Banana 1 image which costs $0.039/image. Google's assertion that you can directly replace NB1 pipelines with NB2L is fair.
Yesterday, Google announced that the Gemini app will allow free image generations (https://blog.google/innovation-and-ai/products/gemini-app/pe...) but did not specify which model would be used: I suspect it's the main motivation for Nano Banana 2 Lite.
Fable is the first model I found that can actually produce such diagrams in slides, in .pptx format that exports cleanly and consistently to Google slides, and is also able to iterate on those diagrams with specific feedback like “center align the arrow with the blue pill on the left which should be vertically aligned inside the dashed database container and make the arrow terminate in the left edge vertical center of the light blue object storage container.”
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.
I built an app for my kids that generates illustrated stories for them with them as the characters. I wanted to prioritize likeness while still stylizing the illustrations. I tested a bunch of models but none seem to come close to maintaining likeness when stylized. I find the others generate generic looking characters.
I'm excited to incorporate this into the onboarding of my app since I want the users to experience the aha moment as soon as possible and waiting half a minute+ isn't ideal. I'll still be using the main NB2 for the actual illustrations as this lite version still has slight issues with nuance and consistency as others have pointed out.
I mean 3 cents compared to 6 cents doesnt seem like much in my mind-unless youre running a consumer saas
gemini.g lets you add a canvas or use image gen, but it isn't clear to me how you stick in the "space lift" prompt and out comes what is demo'd
Why would you prefer otherwise? Seems like tragedy of the commons to release flood of unmarked AI generation images, among many other risks.
It tends to generate depressing-looking lighting, but if instructed, it overcomes it. Up close, faces also look pretty decent. I can still tell it is AI-generated, but to an untrained eye, it is nearly impossible to distinguish, especially for regular blog posts and ads.
So I need to run (AND PAY!) two accounts to have both a nice email address and Banana? Starting to think the correct number of paid google accounts here is zero.
> Does this pill make me smater?
> No, but it can make you dumb faster!
"In a breathtaking display of surreal transformation, a cinematic moment of pure action unfolds against a textured, golden-brown canvas. From the right, a woman is seen in elegant profile, her lips a startling slash of red. Her quiet composure is violently contradicted by the explosive event taking place: her dark hair is erupting, bursting forth into a chaotic flock of black birds. These creatures are captured mid-flight, a dynamic swarm launching from her mind and sweeping across the frame to the left. The motion is palpable; you can almost hear the frantic beating of a hundred wings as they break free. Some birds are still tangled, emerging from the dark mass of her hair, while others are already soaring into the open space. This is not a gentle release, but a powerful, almost violent, act of creation or liberation. The camera captures this impossible metamorphosis head-on, focusing on the sheer force of the birds' exodus. This highly sophisticated image is a kinetic masterpiece, portraying an internal storm made external, a thought process so intense it literally takes flight in a beautiful, dark, and unstoppable flurry of action."
really? anyone using for more than 10 or so tries these knows how to prompt them, and its not "The motion is palpable; you can almost hear the frantic beating of a hundred wings"
"surreal transformation, cinematic action. Textured golden-brown canvas. A woman in profile, red lips. Dark hair erupting into a flock of black birds mid-flight. Explosive metamorphosis" is pretty much all the actual meaning captured here