I have tried Images 2.0 and I believe it does a way better job than the other image generation models. For example, I used NanoBanana and Images 2.0 to generate the same written article in Chinese as IMAGES, GPT does 100x better at rendering all the Chinese characters despite having minor mistakes.
ChatGPT Images 2.0
861–870 of 1001 posts
Re: ChatGPT Images 2.0
#862A great technical achievement, for sure, but this is kind of the moment where it enters uncanny valley to me. The promo reel on the website makes it feel like humans doing incredible things (background music intentionally evokes that emotion), but it's a slideshow of computer generatated images attempting to replicate the amazing things that humans do. It's just crazy to look at those images and have to consciously r…
Yep. Just like motion pictures. Why, it's just a facsimile! People were meant to see performances by real people. These motion pictures fool your eye and surely will unravel the very fabric of civilized society! No longer shall the thespian be well employed! And the minds of the children will lay in ruins from such filth!
I get your point, but it's not even really that. It's that an AI generated photo evokes the same feelings in me that human-made photographs do and I have to catch that and turn that off consciously.
Re: ChatGPT Images 2.0
#863I have tried Images 2.0 and I believe it does a way better job than the other image generation models. For example, I used NanoBanana and Images 2.0 to generate the same written article in Chinese as IMAGES, GPT does 100x better at rendering all the Chinese characters despite having minor mistakes.
I think they're using whatever approach they used for Suno with this model, with Suno, I could tell it things with little context, and it knew that I was asking for something modern with a dated term, and it updated my request to match today's reality. I was impressed.
Re: ChatGPT Images 2.0
#864Every cent you spend on this, remember: The people who made this possible are not even getting a millionth of a cent for every billion USD made with it (they are getting nothing). Same with code; that code you spent years pouring over, fixing, etc. is now how these companies make so much money and get so much investment. It's like open source, except you get shafted.
This is, in my opinion, attempting to say the right thing with entirely the wrong perspective: The people you say are getting "shafted" always got shafted. Their works are the inspiration for all artists and people who lay their eyes on it - maybe they got paid when they made the work, maybe they managed to sell it, but probably not. And still, other artists (and machines) will use remember and be inspired by it, som…
> The person (singular) that is actually getting "shafted" at each use is the artist you didn't hire to do the job of making your new work, because it is their skill that got replaced.
1% Yes, and 99% No.
Over 99% of uses would not have resulted in hiring someone to do the work had these models not existed as you yourself acknowledge.
Re: ChatGPT Images 2.0
#865Earlier quoted context omitted.
It's going to mess up accountability. Some politician will be recorded doing something & he'll have his people release a thousand photos/videos of him doing crimes. And they'll say, look, it's a smear campaign. This is just one stupid example, but people will have better schemes. Also global coordinated releases of fake content and hypertargeted possibly abusive content. Virtual kidnappings will take off, automated &…
Some politician will be recorded doing something & he'll have his people release a thousand photos/videos of him doing crimes. And they'll say, look, it's a smear campaign. And his enemies will do the same, hopefully resulting in less blind trust for everyone in the population, which can only be a good thing.
I would’ve paused image models for now until we’ve better educated our less-savvy neighbors.
Re: ChatGPT Images 2.0
#866Earlier quoted context omitted.
While I agree with you, hacker news audience is not in the middle of the bell curve. I get this sounds elitist - but tremendous percentage of population is happily and eagerly engaging with fake religious images, funny AI videos, horrible AI memes, etc. Trying to mention that this video of puppy is completely AI generated results in vicious defense and mansplaining of why this video is totally real (I love it when vi…
HN is absolutely not more critical of AI output than the norm. It's been true for various technologies that HN (and tech audiences in general) have a more nuanced view, but AI flips the script on that entirely. It's the tech world who are amazed by this, producing and being delighted by endless blogposts and 7-second concept trailers.
I think we are conflating usage vs consumption.
I think HN probably uses GenAI more than average population.
But I think HN consumes less GenAI content than average population.
Look at Facebook, Instagram, Youtube, TikTok, etc. All I see is my non-techie friends being amazed and mesmerized by - cute animals, creepy animals, political events, jokes, comedy, outrage, events, speeches - that never ever happened. As if we don't have actual real puppies that are cute, my acquintenances and family are oooing and awwwing at fake howling huskies, fake animals being jump-scared by fake surprises.
HN may be amazed by potential of AI output the improve the world more than average person. But hustlers are laughing their way to the bank as they actually use AI to make ridiculous, and I do mean ridiculous, amount of "content" for cheap, that is, absolutely is, being consumed at prodigious rate with no sign of stopping. This is not 7-second trailers and concepts for some future years - this is mega-years of actual content being liked, shared, engaged with and consumed, right now. This is what OP is hoping that tides will turn against, and this is what I see no sign of rejection in my non-techie/non-geeky circles :(
Re: ChatGPT Images 2.0
#867So during my Nano Banana Pro experiments I wrote a very fun prompt that tests the ability for these image generation models to follow heuristics, but still requires domain knowledge and/or use of the search tool: Create a 8x8 contiguous grid of the Pokémon whose National Pokédex numbers correspond to the first 64 prime numbers. Include a black border between the subimages. You MUST obey ALL the FOLLOWING rules for th…
How is it that a model can produce what must be near 1:1 images ripped straight out of Pokemon Fire Red (The first ones) for profit and not be infringing copyright. I know that's the game, but it seems CRAZY to me that they can do this.
Gemini uses google search to find references when making images, so it probably found the pokemon images online to do this.
> I know that's the game, but it seems CRAZY to me that they can do this.
Its not crazy that a search can find existing pokemon images. Maybe google should show which images it used as references to be more transparent here.
Re: ChatGPT Images 2.0
#868Earlier quoted context omitted.
That's also the wrong framing AI Labs are getting a tiny cut of the hundreds saved by not hiring an artist. So regular people save hundreds, the labs get a few dollars, and the artists get nothing. The artists are still losing, but it's regular people, especially the least able, who are winning. The coffee shop isn't cutting OAI a $300 check for doing their spring menu. They are pocketing $295 and paying OAI $5.
No. The coffee shop who isn’t paying an artist $300 is gonna get negative reviews and loose customers and money from their bad business decision[1]. I know I would think twice about ordering at a café which uses AI in their marketing, and I am not the only one. The coffee shop who cannot afford the $300 for an artist and homebrews their design in Microsoft Word is still doing just as before, the coffee shop which can…
Sure, just like every software company using AI is going to go under and every video game using AI will fail?
Re: ChatGPT Images 2.0
#869Earlier quoted context omitted.
Yep. Just like motion pictures. Why, it's just a facsimile! People were meant to see performances by real people. These motion pictures fool your eye and surely will unravel the very fabric of civilized society! No longer shall the thespian be well employed! And the minds of the children will lay in ruins from such filth!
I get your point, but it's not even really that. It's that an AI generated photo evokes the same feelings in me that human-made photographs do and I have to catch that and turn that off consciously.
It shouldn't bother you. Just enjoy stuff. It's ok to think computer art is pretty. It's not some kind of personal or societal moral failing.
Re: ChatGPT Images 2.0
#870A great technical achievement, for sure, but this is kind of the moment where it enters uncanny valley to me. The promo reel on the website makes it feel like humans doing incredible things (background music intentionally evokes that emotion), but it's a slideshow of computer generatated images attempting to replicate the amazing things that humans do. It's just crazy to look at those images and have to consciously r…
The wolf photo for the article was the most eerie example for me... if I am reading about the natural world, I want to see a real photo of the natural world.