131–140 of 504 posts
Earlier quoted context omitted.
Use it on fal.ai
Since API currently is not working (seems rate limits not set for Image Generation yet) I tried on fal. Definitely inferior to results I see on AI Studio and image generation time is 6s on AI Studio vs 30 seconds on Fal.AI
Quality or latency?
Earlier quoted context omitted.
In other words, this is the gpt 4 moment for image editing models. Gpt4 isn't "fundamentally different" from gpt3.5. It's just better. That's the exact point the parent commenter was trying to make.
did you see the generated pic demis posted on X? it looks like slop from 2 years ago. https://x.com/demishassabis/status/1960355658059891018
My test is going to https://unsplash.com/s/photos/random and pick two random images, send them both and "integrate the subject from the second image into the first image" as the prompt. I think Gemini 2.5 is doing far better than ChatGPT (admittedly ChatGPT was the trailblazer on this path). FluxKontext seems unable to do that at all. Not sure if I were using it wrong, but it always only considers one image at a time for me.
Edit: Honestly it might not be the 'gpt4 moment." It's better at combining multiple images, but now I don't think it's better at understanding elaborated text prompt than ChatGPT.
I don't get the hype. Tested it with the same prompts I used with Midjourney, and the results are worse than in Midjourney a year ago. What am I missing?
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.
Earlier quoted context omitted.
I guess it was something like [0] The Nigerian prince is now a deep fake Elon but the concept is the same. You need to send some money to get way more back. [0]: https://www.ncsc.admin.ch/ncsc/en/home/aktuell/im-fokus/2023...
hm, but isn't it wild thinking that elon is talking to you and asking you for 15k , like bro has the money of his lifetime, why would he ask you? It doesn't make that much sense idk
Granted I played Runescape and EvE as a kid, so any double-isk scams are immediate redflags.
Earlier quoted context omitted.
facebook isn't going to implement detection though. Many (if not most) of the viral pictures are AI-generated. and facebook is incentivized to let their users get fooled to generate endless scrolling
Along with those being fooled there are many comments saying this is fake, AI trash and etc. That portion of the commenters are teaching the ignorant and soon no one will believe what they see on the Internet as real.
Now is that so bad?
I could see this destroying a lot of jobs like photography, editing, marketing, etc.
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've been waiting for that, too. But I'm also not interesting in feeding my entire extended family's visual history into Google for it to monetize. It's wrong for me to violate their privacy that way, and also creepy to me.
Am I correct to worry that any pictures I send into this system will be used for "training?" Is my concern overblown, or should I keep waiting for AI on local hardware to get better?
Earlier quoted context omitted.
Wow I hate the ‘voice’ in that article - big if true though.
I suspect the "voice" is a language model with a bad system prompt. (Possibly the author's own words run through an LLM, to be charitable.)
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
Why is it called nano banana?