now you can create good memories with your family without meeting them
GPT Image 1.5
191–200 of 272 posts
Re: GPT Image 1.5
#192Earlier quoted context omitted.
This showdown benchmark was and still is great, but an enormous grain of salt should be added to any model that was released after the showdown benchmark itself. Maybe everyone has a different dose of skepticism. Personally I'm not even looking at results for models that were released after the benchmark, for all this tells us, they might as well be one-trick ponies that only do well in the benchmark. It might be too…
Yeah that’s a classic problem, and it's why good tests are such closely guarded secrets: to keep them from becoming training fodder for the next generation of models. Regarding the "model date" vs "benchmark date" - that's an interesting point... I'll definitely look into it! I don't have any captcha systems in place, but I wonder if it might be worth putting up at least a few nominal roadblocks (such as Anubis [1])…
The Blender previz reskin task [1] could be automated! New test cases could be randomly and procedurally generated (without AI).
Generate a novel previz scene programatically in Blender or some 3D engine, then task the image model with rendering it in a style (or to style transfer to a given image, eg. something novel and unseen from Midjourney). Another test would be to replace stand in mannequins with identities of characters in reference images and make sure the poses and set blocking match.
Throw in a 250 object asset pack and some skeletal meshes that can conform to novel poses, and you've got a fairly robust test framework.
Furthermore, anything that succeeds from the previz rendering task can then be fed into another company's model and given a normal editing task, making it doubly useful for two entirely separate benchmarks. That is, successful previz generations can be reused as image edit test cases - and you a priori know the subject matter without needing to label a bunch of images or run a VLM, so you can create a large set of unseen tests.
[1] https://imgur.com/gallery/previz-to-image-gpt-image-1-x8t1ij...
Re: GPT Image 1.5
#193Okay results are in for GenAI Showdown with the new gpt-image 1.5 model for the editing portions of the site! https://genai-showdown.specr.net/image-editing Conclusions - OpenAI has always had some of the strongest prompt understanding alongside the weakest image fidelity. This update goes some way towards addressing this weakness. - It's leagues better at making localized edits without altering the entire image's ae…
Stupid Cisco Umbrella is blocking you
Re: GPT Image 1.5
#194Earlier quoted context omitted.
my question to your anecdotal: who cares? not being fecicious, but who cares if someone reproduced your stuff and millions of people see your stuff? is the money that you want? is it the fame? because fame you will get, maybe not money... but couldn't there be another way?
People have values that go beyond wealth and fame. Some people care about things like personal agency, respect and deference, etc. If someone were on vacation and came home to learn that their neighbor had allowed some friends stay in the empty house, we would often expect some kind of outrage regardless of whether there had been specific damage or wear to the home. Culturally, people have deeply set ideas about what…
If I were a creative I would avoid seeing any work I am not legally allowed to get inspired by, why install furniture into my brain I can't sit on? I see this kind of IP protection as poisoned grounds, can't do anything on top of it.
Re: GPT Image 1.5
#195I get the tech implementation is amazing, I wonder if it takes away from genuineness of events, like the Astronaut photo, I get it's just a joke/funny too but it's like a photo of you in a supercar vs. actually buying one. Or fake AI companions vs. real people. Beauty filters/skinny filters vs. actually being healthy.
the next generation of humans growing up will not even care whether media is real or not any more. The saturation of AI content and FUD around real content is going to blur the lines to the extent that there's no point even caring about it. And it's an intractable problem. hopefully this leads to greater importance of seeing things with your own wetware.
The other issue is the need to show off... if I had a supercar why do I have to post it on Instagram that kind of thing.
Re: GPT Image 1.5
#196Was it ever explained or understood why ChatGPT Images always has (had?) that yellow cast?
My pet theory is that OpenAI screwed up the image normalization calculation and was stuck with the mistake since that's something that can't be worked around. At the least, it's not present in these new images.
wdym it cant be worked around when there exist literal yellow tint corrector models/tools haha
Re: GPT Image 1.5
#197Okay results are in for GenAI Showdown with the new gpt-image 1.5 model for the editing portions of the site! https://genai-showdown.specr.net/image-editing Conclusions - OpenAI has always had some of the strongest prompt understanding alongside the weakest image fidelity. This update goes some way towards addressing this weakness. - It's leagues better at making localized edits without altering the entire image's ae…
It failed my benchmark of a photo of a person touching their elbows together.
Re: GPT Image 1.5
#198AI-generated images would remove all the trust and admire for human talent in art, similar to how text-generation would remove trust and admire for human talent in writing. Same case for coding. So, let's simulate that future. Since no one trusts your talent in coding, art or writing, you wouldn't care to do any of these. But the economy is built on the products and services which get their value based how much of hu…
all I can hope for is that a new industry or reliable ecosystem of vetters of real human talent will emerge. Are you really as good a writer as you claim to be? Show us the badge. That or AI firms have to be forced to 'watermark' all their creative outputs, and anyone misleading the public/audience should be punishable by law.
Both are just mid-summer dreams. There is no global law to enforce watermark. There are no badges that can't be forged.
Re: GPT Image 1.5
#199Re: GPT Image 1.5
#200Sam Altman Christmas decoration isn't real, he can't hurt me...