"We did it, Patrick! We made a technological breakthrough!"
A place for all those who loathe AI to discuss things, post articles, and ridicule the AI hype. Proud supporter of working people. And proud booer of SXSW 2024.
Wow, this is a great showcase...
of AI slop! The original picture is actually awesome. It captures a genuine happy moment the couple had in between dancing and partying.
And then there's the AI slop that removes almost all of the context. Good. Let the people see the slop.
Also: immich
I don't use Immich (yet), but I was sold on it when I saw their cursed knowledge page. Delightfully human
What a shitload of fuck, this shit is full of more diarrhea than a gas station bathroom after Taco Bell BOGO-night.
I hate this shit so much. When family members use it i want to punch them. Its rage inducing.
is this what they're using as a promotional graphic? these don't look like the people in the photo at all
Yeah wtf lol "here are some cartoony somewhat similar photos of somewhat similar people in completely different poses" ???
the worst part is that we have been able to do this long before LLMs, and achieve much better results. There exist filters that will cartoonify your image! deterministic filters - they always spit out the same image given the same input.
the problem with LLMs is that they go through this completely unnecessary level of indirection - they describe the image in text and then generate an image based on this text - essentially behaving like an extremely lossy compressor-decompressor pipe
Hmm, I'm not an expert on image AI, but I think your idea of how this works is basically close enough but not exactly right. The image is encoded into tokens (vectors) by an encoder model, and then those tokens are decoded into a new image. The intermediary tokens aren't really text descriptions of the image but maybe this distinction is kind of pointless? The lossyness is the same either way
so you're saying that of I decoded these intermediate tokens I wouldn't get coherent sentences, but rather something completely random that is just a covenient representation of the image, or perhaps some words that relate to the image (sth like "woman" "man" "marriage" "blonde" "dress" etc.)?
Somewhat. I am not familiar with this exact type of algorithm, but the global name is “Encoder-Decoder” algorithm. Broadly speaking you have an input (the original image) and you want to create an output (obviously). You want the input and the output to be “very similar” according to some definition, but you imagine that the AI algorithm has two parts, the encoder part that extracts as much meaningful information as possible from the input and a decoder, that takes that information and generates something new out if it. This information is practically stored as a list of numbers, and we do not impose any prior meaning to them (we do not say that the first number for example is the number of people in the image) but the algorithm learns to make the best out of the encoding.
Two different machines that run the same algorithm trained independently might have completely different middle information. The only thing that matters is that the “encoder” and the “decoder” parts both know what’s going on. (Basically, yes, it’s random but the computer knows how to interpret it - where “know” is used very loosely here)
Sorry for the rant! I hope you found it interesting
I believe so, and some may not really translate well into text at all, and instead represent some kind of specific or abstract visual feature. There would be an entire other neural network or part of a neural network specifically for decoding the tokens into text
this is what popped up when I opened the photos app, so yes, it is. they don't resemble the real people at all
But is this one of your pics? If not, that would mean they've chosen it to show the best the software can do. Lame.
Weird how Google decided that the man in the original is laughing too much, and toned it down in all 4 versions.
her smiles are a lot weaker too, it's so fucking soulless
Her eyes look enormous compared to his in the slop images, while it’s obvious it’s just a head tilt and slightly closed eyes in the original.
That said, I am still glad that some AI slop fails in this regard. But I guess most are beyond and better by now or next week, unfortunately.
And these were the best they chose for the marketing
If they just spend a few hundred billion dollars more, their machine will finally will end the tyranny of the kiosk people at the mall.
The gimmicky ads around AI are the most pathetic part. If it was a good product, you wouldn't need to tell us to gaslight our elders with AI generated images of their childhood.
It's like nobody knows that the fuck it's good for.
I'll keep saying it. Solution looking for a problem.
In the bottom right slop, that left eye is going on an adventure!
Seems like a PM at Google looked at the godawful Apple Image Playground and thought "Oh wow we need that!"
Why? WHY??!! 😭