this post was submitted on 08 May 2024
1126 points (98.7% liked)

Science Memes

15221 readers
1142 users here now

Welcome to c/science_memes @ Mander.xyz!

A place for majestic STEMLORD peacocking, as well as memes about the realities of working in a lab.



Rules

  1. Don't throw mud. Behave like an intellectual and remember the human.
  2. Keep it rooted (on topic).
  3. No spam.
  4. Infographics welcome, get schooled.

This is a science community. We use the Dawkins definition of meme.



Research Committee

Other Mander Communities

Science and Research

Biology and Life Sciences

Physical Sciences

Humanities and Social Sciences

Practical and Applied Sciences

Memes

Miscellaneous

founded 2 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
[โ€“] SomeAmateur@sh.itjust.works 94 points 1 year ago* (last edited 1 year ago) (5 children)

I had to run that through Bing AI real quick lol

[โ€“] brbposting@sh.itjust.works 60 points 1 year ago (1 children)

Ataliative ๐Ÿ˜ฎ

Adetvi Learning ๐Ÿ˜ฒ

Blowv the ciompetittio ๐Ÿคฏ

[โ€“] Venator@lemmy.nz 24 points 1 year ago* (last edited 1 year ago) (1 children)

BlocklBerach

Clould frist lustion

Agรญee

[โ€“] brbposting@sh.itjust.works 13 points 1 year ago (1 children)
[โ€“] Venator@lemmy.nz 5 points 1 year ago* (last edited 1 year ago)
[โ€“] CluckN@lemmy.world 36 points 1 year ago (4 children)

Iโ€™m surprised itโ€™s able to make readable text.

[โ€“] zalgotext@sh.itjust.works 22 points 1 year ago (1 children)
[โ€“] barsoap@lemm.ee 8 points 1 year ago

Image generation models are generally more than capable of doing that they're just not trained to do it.

That is, just doing a bit of hand-holding and showing SDXL appropriately tagged images and you get quite sensible results. Under normal circumstances it just simply doesn't get to associate any input tokens with the text in the pixels because people rarely if ever describe, verbatim, what's written in an image. "Hooters" is an exception, hard to find a model on Civitai that can't spell it.

[โ€“] ghen@sh.itjust.works 7 points 1 year ago

The worst part is that it now tries to add text to a whole lot of pictures

[โ€“] SomeAmateur@sh.itjust.works 4 points 1 year ago (1 children)

Yeah it's been improving over the past few months. It's hit or miss though

I like to post sometimes on the "guess the song" AI communities, but more often than not, the Bing image creator just plast the lyrics on the image making it useless for the game.

[โ€“] MonkeMischief@lemmy.today 23 points 1 year ago

Yeah these look exactly like things I'd see on billboards in Vegas when certain conventions are in town...

[โ€“] drolex@sopuli.xyz 11 points 1 year ago (1 children)

I will probably use these images in a corporate PowerPoint. I'm not asking for your permission, I'm warning you. Sorry, it's too good. (I will credit you as a CTO of some company ending in -SYS or - LEA if you want)

Lol go for it just send me a screenshot of the slide!

Ahh I miss the days when people who knew and used generative AI understood they are best for shits and giggles.