Like most image generators, it didn’t pass the piano keyboard test. (Black keys are wrong.) https://aistudio.google.com/app/prompts?state=%7B%22ids%22:%...
What is the piano keyboard test? Your link requires granting AI Studio access to Google Drive, which I do not want to do.
Gemini 2.5 Flash Image
201–210 of 504 posts
Re: Gemini 2.5 Flash Image
#202I 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?
Hmm, I think the hype is mainly for image editing, not generating. Although note I haven't used it! How are you testing it?
Re: Gemini 2.5 Flash Image
#203This 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.
Re: Gemini 2.5 Flash Image
#204Earlier quoted context omitted.
AI is supposed to set us all free. Yet, so far all the tech companies have done is eliminate the jobs of the lowest-paid people (artists, writers, photographers, designers) and transfer that money to billionaires. Yay.
[Plows] are supposed to set us all free. Yet, so far all the tech companies have done is eliminate the jobs of the lowest-paid people ([field hands]) and transfer that money to landowners. Yay.
Re: Gemini 2.5 Flash Image
#205Re: Gemini 2.5 Flash Image
#206What is the max input and output resolution of images? This is why I'm sticking mostly to Adobe Photoshop's AI editing because there are no restrictions in that regard.
Re: Gemini 2.5 Flash Image
#207Earlier quoted context omitted.
Programming and everything else will eventually fall to automation, too. It's just a matter of time. Engineering probably takes a while (5 years? 10 years?) because errors multiply and technical debt stacks up. In images, that's not so much of a big deal. You can re-roll. The context and consequences are small. In programs, bad code leads to an unmaintainable mess and you're stuck with it. But eventually this will ca…
Both of you are wrong and this is not good discussion level for HN
If you think that these tools don't automate most existing graphics design work, you're gravely mistaken.
The question is whether this increases the amount of work to be done because more people suddenly need these skills. I'm of the opinion that this does in fact increase demand. Suddenly your mom and pop plumbing business will want Hollywood level VFX for their ads, and that's just the start.
Re: Gemini 2.5 Flash Image
#208Re: Gemini 2.5 Flash Image
#209Very impressive. I have to say while I'm deeply impressed by these text to image models, there's a part of me that's also wary of their impact. Just look at the comments beneath the average Facebook post.
Facebook comments are obviously botted too