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

Nano Banana Pro

blog.google

Post reply on HN
Print view View original

531–540 of 718 posts

Re: Nano Banana Pro

#531

Post by mh- »

vunderba wrote: post #486
SamBam wrote: post #468

Earlier quoted context omitted.

Is there a model on Fal.ai that would make it easy to sharpen blurry video footage? I have found some websites, but apparently they are mostly scammy.

Unfortunately, this is a fairly difficult task. In my experience, even SOTA models like Nano Banana usually make little to no meaningful improvement to the image when given this kind of request. You might be better off using a dedicated upscaler instead, since many of them naturally produce sharper images when adding details back in - especially some of the GAN-based ones. If you’re looking for a more hands-off appro…

Seconding the Topaz recommendation. Although be aware that is the Image upscaler model, and the parent commenter asked about video.

Here's the Fal-hosted video endpoint: https://fal.ai/models/fal-ai/topaz/upscale/video

They also offer (multiple; confusing product lineup!) interactive apps for upscaling video on their own website - Topaz Video and Astra. And maybe more, who knows.

I have access to the interactive apps, and there are a lot of knobs that aren't exposed in the Fal API.

edit: lol I found a third offering on the Topaz site for this, "Video upscale" within the Express app. I have no idea which is the best, despite apparently having a subscription to all of them.

Re: Nano Banana Pro

#532

Post by mh- »

brk wrote: post #476
SamBam wrote: post #468

Earlier quoted context omitted.

Is there a model on Fal.ai that would make it easy to sharpen blurry video footage? I have found some websites, but apparently they are mostly scammy.

FYI that is an extremely challenging thing to do right. Especially if you care about accuracy and evidentiary detail. Not sure this is something that the current crop of AI tools are really tuned to do properly.

This is a good point. Some of the tools have a "creative mode" or "creativity" knob that hopefully drives this point home. But the simpler ones don't, and even with that setting dialed back it still has the same fundamental limitations/risks.

Re: Nano Banana Pro

#533

Post by tziki »

tylervigen wrote: post #511
vunderba wrote: post #396

Alright 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’s answer to the giraffe edit is far superior to the Seedream response, but you passed Seedream and failed NB pro. Maybe that one is just not a good test?

I agree, it seems like Seedream has the neck at same length as Nano Banana but also made the giraffe crouch down, making a major modification to the overall picture.

Re: Nano Banana Pro

#534

Post by esrauch »

withinboredom wrote: post #283
Jabrov wrote: post #275

Earlier quoted context omitted.

I don't know if that's so much a mistake as it is ambiguity though? To me, using the viewer's perspective in this case seems totally reasonable. Does it still use the viewer's perspective if the prompt specifies "Put a strawberry in the _patient's left eye_"? If it does, then you're onto something. Otherwise I completely disagree with this.

“The right socket” can only be implied one way when talking about a body just like you only have one right hand despite the fact that it is on my left when looking at you.

"Right hand" is practically a bigram that has more meaning, since handedness is such a common topic.

Also context matters, if you're talking to someone you would say "right shoulder" for _their_ right since you know it's an observer with different vantage point. Talking about a scene in a photo "the right shoulder" to me would more often mean right portion of the photo even if it was the person's left shoulder.

Re: Nano Banana Pro

#535

Post by rustystump »

ceroxylon wrote: post #306

Google has been stomping around like Godzilla this week, and this is the first time I decided to link my card to their AI studio. I had seen people saying that they gave up and went to another platform because it was "impossible to pay". I thought this was strange, but after trying to get a working API key for the past half hour, I see what they mean. Everything is set up, I see a message that says "You're using Paid…

How long till ai studio is in the graveyard i wonder? For real google has some of the most amazing tech but jfc do they suck at making a product.

The only way i use google is via an api key which billing for is arcane to be charitable. How can billions not crack the problem of quickly accepting cash from customers? Surely their ads platform does this?

Re: Nano Banana Pro

#536

Post by rester324 »

cheema33 wrote: post #497
egypturnash wrote: post #285

Everyone 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?

That's a question too generic. But yes, I guess? And people get Nobel prizes to point out that said advances have been causing the downfall of empires and nations.

Re: Nano Banana Pro

#537

Post by k12sosse »

SamBam wrote: post #468
vunderba wrote: post #327

Earlier quoted context omitted.

If it's just the API you're interested in, Fal.ai has put Nano-Banana-Pro up for both generative and editing. A great deal less annoying to sign up for them since they're a pretty generalized provider of lots of AI related models. https://fal.ai/models/fal-ai/nano-banana-pro

Is there a model on Fal.ai that would make it easy to sharpen blurry video footage? I have found some websites, but apparently they are mostly scammy.

I'm dimestore cheap, I'd be exploding to frames and sharpening and reassembling with a ffmpeg>irfanview process Lol. It would be awfully expensive to do it with an AI model and the results would be expensive. Would a photo/video editing suite do it? Google photos with a pro script, or Adobe premiere elements, or would you be able to do it in yourself in DaVinci resolve? Or are you talking hundreds of hours of video?

Re: Nano Banana Pro

#538

Post by ukuina »

logankilpatrick wrote: post #419
ceroxylon wrote: post #306

Google has been stomping around like Godzilla this week, and this is the first time I decided to link my card to their AI studio. I had seen people saying that they gave up and went to another platform because it was "impossible to pay". I thought this was strange, but after trying to get a working API key for the past half hour, I see what they mean. Everything is set up, I see a message that says "You're using Paid…

First off, apologies for the bad first impression, the team is pushing super hard to make sure it is easy to access these models. - On permission issue, not sure I follow the flow that got you there, pls email me more details if you are able too and happy to debug: Lkilpatrick@google.com - On overall friction for billing: we are working on a new billing experience built right into AI Studio that will make it super ea…

Congrats on the move to Google!

Please allow me to rant to someone who can actually do something about this.

Vertex AI has been a nightmare to simply sign up, link a credit card, and start using Claude Sonnet (now available on Vertex AI).

The sheer number of steps required for this (failed) user journey is dizzying:

* AI Studio, get API key

* AI Studio, link payment method: Auto-creates GCP property, which is nice

* Punts to GCP to actually create the payment method and link to GCP property

* Try to use API key in Claude Code; need to find model name

* Look around to find actual model name, discover it is only deployed on some regions, thankfully, the property was created on the correct region

* Specify the new endpoint and API key, Claude Code throws API permissions errors

* Search around Vertex and find two different places where the model must be provisioned for the account

* Need to fill out a form to get approval to use Claude models on GCP

* Try Claude Code again, fails with API quota errors

* Check Vertex to find out the default quota for Sonnet 4.5 is 0 TPM (why is this a reasonable default?)

* Apply for quota increase to 10k tokens/minute (seemingly requires manual review)

* Get rejection email with no reasoning

* Apply for quota increase to 1 token/minute

* Get rejection email with no reasoning

* Give up

Then I went to Anthropic's own site, here's what that user journey looks like:

* console.anthropic.com, get API key

* Link credit card

* Launch Claude Code, specify API key

* Success

I don't think this is even a preferential thing with Claude Code, since the API key is working happily in OpenCode as well.

Re: Nano Banana Pro

#539

Post by t-writescode »

egypturnash wrote: post #285

Everyone 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?

I want to piggyback off what you’ve said, but for *additional* problems with this:

To me, this is terrifying. Major use-cases presented on this page:

  * photo editing / post-processing
  * branding
  * infographics
Photo editing and post-processing seems like the “least harmful” version of this. Doing moderate color-space tweaks or image extensions based on the images themselves seems like a “relatively not-evil” activity and will likely make a lot of artwork a bit nicer. The same technology will probably also be able to be used to upscale photos taken on Pixel cameras, which might be nice. MOSTLY. It’ll also call into question any super-duper-upscaled visuals when used as evidence for court and the “accuracy of photos as facts” - see the fake stuff Samsung did with the moon; but far, far more ubiquitous.

However, Branding and Infographics are where I have concerns.

Branding - it’s AI art, so it can’t be copyrighted, or are we just going to forget that?

—

Infographics, though. We know that AI frequently hallucinates - and even hallucinates citations themselves, so … how can we generated infographics if they’re magicking into existence the stats used in the infographics themselves?!

Re: Nano Banana Pro

#540

Post by robots0only »

AmbroseBierce wrote: post #509

2D animators can still feel safe about their job, I asked it to generate a sprite sheet animation by giving it the final frame of the animation (as a PNG file) and asking in detail what I wanted in the spritesheet, it just gave me mediocre results, I asked for 8 frames and it just repeated a bunch of poses just to reach that number instead of doing what a human would have done with the same request, meaning the in-be…

the problem here is that text as the communication interface is not good for this. the model should be reasoning in the pose space (and generally in more geometric spaces), then interpolation and drawing is pretty easy. I think this will happen in some time.
Post reply on HN