361–370 of 504 posts
Earlier quoted context omitted.
The hype is about image editing, not pure text-to-image. Upload an input image, say what you want changed, get the output. That's the idea. Much better preservation of characters and objects.
Can it edit the photo at the original resolution? Most of my photos these days are 48MP and I don't want to lose a ton of resolution just to edit them.
This is the gpt 4 moment for image editing models. Nano banana aka gemini 2.5 flash is insanely good. It made a 171 elo point jump in lmarena! Just search nano banana on Twitter to see the crazy results. An example. https://x.com/D_studioproject/status/1958019251178267111
I've been testing it for several weeks. It can produce results that are truly epic, but it's still a case of rerolling the prompt a dozen times to get an image you can use. It's not God. It's definitely an enormous step though, and totally SOTA.
All images created or edited with Gemini 2.5 Flash Image will include an invisible SynthID digital watermark, so they can be identified as AI-generated or edited. Obviously I understand what is the purpose and the good intention, but I think sad to see that we are not not anymore responsible adults but big corps deciding for us what we can and what we cannot do. Snitching on your back.
Deepfakes have the potential to totally destroy the average person’s already tenuous connection with reality outside of their immediate vicinity.
Some will be fooled by an endless stream of fakes and others will never believe anything again.
Politicians will dismiss footage of them doing or saying something bad as fake. And many times, they’ll be telling the truth.
We are already living in a post-fact world to some extent, but buckle up, because it’s about to get a lot worse.
Earlier quoted context omitted.
Alarming hands on the third one: it can't decide which way they're facing. But Gemini didn't introduce that, it's there in the base image.
Yes, the base image's hands are creepy.
There is one thing Gemini 2.5 Flash Image can do that no other edit model can do: incorporate multiple images simultaneously without shenanigans due to its multimodality, e.g. for Flux Kontext, if you want to "put the person in the first image into the second image", you have to concatenate them pre-VAE which can be unwieldly, but this model doesn't have that issue. You can even incorporate more than two images, but…
I send him one photo a day and he's been loving it. Just a fun little thing to put a smile on his face (and mine).
its only a matter of time before this can be used to generate coherence with nudity on consumer hardware.
Earlier quoted context omitted.
It was very convincing. We thought it was a YouTube stream of the Starship launch. It paused with 40 seconds remaining, and "Musk" came on offering to reward those who support innovation and technology (BTC, in this case). All info here: https://docs.google.com/document/d/1lRbApgKT4U95zN0AYsPQqsLR...
Kind of missing their point there. Giving Elon Musk $15k in crypto based on some vague too-good-to-be-true "trust me bro" pitch is embarrassing even if the video turned out to be real.
I digitised our family photos but a lot of them were damaged (shifted colours, spills, fingerprints on film, spots) that are difficult to correct for so many images. I've been waiting for image gen to catch up enough to be able to repair them all in bulk without changing details, especially faces. This looks very good at restoring images without altering details or adding them where they are missing, so it might fina…
I don't really understand the point of this usecase. Like, can't you also imagine what the photos might look like without the damage? Same with AI upscaling in phone cameras... if I want a hypothetical idea of what something in the distance might look like, I can just... imagine it? I think we will eventually have AI based tools that are just doing what a skilled human user would do in Photoshop, via tool-use. This w…
All images created or edited with Gemini 2.5 Flash Image will include an invisible SynthID digital watermark, so they can be identified as AI-generated or edited. Obviously I understand what is the purpose and the good intention, but I think sad to see that we are not not anymore responsible adults but big corps deciding for us what we can and what we cannot do. Snitching on your back.