all 21 comments

sorted by: hot top controversial new old
[–] 37 points 1 year ago (7 children)

is this what they're using as a promotional graphic? these don't look like the people in the photo at all

  • source
  • hideshow 7 child comments
  • [–] 23 points 1 year ago (5 children)

    Yeah wtf lol "here are some cartoony somewhat similar photos of somewhat similar people in completely different poses" ???

  • source
  • parent
  • hideshow 5 child comments
  • [–] 22 points 1 year ago (4 children)

    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

  • source
  • parent
  • hideshow 4 child comments
  • [–] 9 points 1 year ago (3 children)

    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

  • source
  • parent
  • hideshow 3 child comments
  • [–] 6 points 1 year ago (2 children)

    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.)?

  • source
  • parent
  • hideshow 2 child comments
  • [–] 4 points 1 year ago

    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

  • source
  • parent
  • [–] 3 points 1 year ago

    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

  • source
  • parent
  • [–] 25 points 1 year ago (2 children)

    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

  • source
  • hideshow 2 child comments
  • [–] 19 points 1 year ago

    I hate this shit so much. When family members use it i want to punch them. Its rage inducing.

  • source
  • [–] 19 points 1 year ago

    What a shitload of fuck, this shit is full of more diarrhea than a gas station bathroom after Taco Bell BOGO-night.

  • source
  • [–] 16 points 1 year ago (1 child)

    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.

  • source
  • hideshow 1 child comment
  • [–] 12 points 1 year ago

    In the bottom right slop, that left eye is going on an adventure!

  • source
  • [–] 11 points 1 year ago* (last edited 1 year ago) (1 child)

    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.

  • source
  • hideshow 1 child comment
  • [–] 8 points 1 year ago

    Seems like a PM at Google looked at the godawful Apple Image Playground and thought "Oh wow we need that!"

    Why? WHY??!! 😭

  • source
  • these AI tech bros really are soulless. Which photo would you rather have hanging up on your wall? If I saw the left photo, I'd think it was a memory from the happiest time of someone's life. If I saw the bottom right photo, I'd assume the person was obsessed with a Pixar character. and this is their curated example.

  • source
  • [–] 5 points 1 year ago

    The big naivete I see from most of the comments is blaming pms and "tech bros"instead of realizing the same villain as always is in charge and that's business majors. Tech was awesome before the business guys came and ruined it all in the name of shareholder value. No tech employee can stop their senior vps from demanding they make this shit.

  • source