Super cheap generation but expensive image upload, do I read that right? https://openrouter.ai/google/gemini-2.5-flash-image-preview
That’s like .12 cents per image uploaded
Gemini 2.5 Flash Image
171–180 of 504 posts
Re: Gemini 2.5 Flash Image
#172Re: Gemini 2.5 Flash Image
#173This is technically impressive though I really wish they'd choose other professions to automate than graphic design.
It’s what data is available, they’re not targeting graphic design
Re: Gemini 2.5 Flash Image
#174Are men not attractive? Or perhaps for Google, this blog is a targeted content? But who is it targeting? I would like to see the reasoning behind using all women images (at the least the top/first ones) to show off the model capabilities. I have noticed this trend in the image manipulation business a lot.
Re: Gemini 2.5 Flash Image
#175This 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
#176Are men not attractive? Or perhaps for Google, this blog is a targeted content? But who is it targeting? I would like to see the reasoning behind using all women images (at the least the top/first ones) to show off the model capabilities. I have noticed this trend in the image manipulation business a lot.
The average man finds the average woman more attractive than the average woman finds the average man. Replace attractive with (eye-catching/attention-grabbing/motivating/retention-boosting).
Re: Gemini 2.5 Flash Image
#177Like 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:%...
Re: Gemini 2.5 Flash Image
#178Earlier quoted context omitted.
Do you happen to know some software to repair/improve video files? I'm in the process of digitalizing a couple of Video 2000 and VHS casettes of childhood memories of my mom who start suffering from dementia. I have a pretty streamlined setup for digitalizing the videos but I'd like to improve the quality a bit.
I've used products from topazlabs.com for the same problem and have generally been happy with them.
Topaz is probably the SOTA in video restoration, but it can definitely fuck shit up. Use carefully and sparingly and check all the output for weird AI glitches.
Re: Gemini 2.5 Flash Image
#179FYI, this is the famed nano-banana model which has been now renamed to gemini-2.5-flash-image-preview in LMArena.
I mean they are going to have to rename their AI because gemini.com is going to IPO soon.
"Banana" would be a nice name for their AI, and they could freely claim it's bananas.
Re: Gemini 2.5 Flash Image
#180I 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?
Midjourney hasn't been SOTA for over a year. Even the latest release of version 7 scores extremely low on prompt adherence only managing to get 2 out of 12 prompts correct. Even Flux Dev running locally consistently out performs it.
Here's a comparison of Flux Dev, MJ, Imagen, and Flash 2.5.
https://genai-showdown.specr.net/?models=FLUX_1D%2CMIDJOURNE...
That being said, if image fidelity is absolutely paramount and/or your prompts are relatively simple - Midjourney can still be fun to experiment with particularly if you crank up the weirdness / chaos parameters.