145
Hell world
(hexbear.net)
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
this post was submitted on 16 Jun 2024
145 points (100.0% liked)
chapotraphouse
13287 readers
1240 users here now
Banned? DM Wmill to appeal.
No anti-nautilism posts. See: Eco-fascism Primer
Vaush posts go in the_dunk_tank
Dunk posts in general go in the_dunk_tank, not here
Don't post low-hanging fruit here after it gets removed from the_dunk_tank
founded 3 years ago
MODERATORS
no, see, here's the thing... how does every single one of these look WORSE than the slop Dall-E spits out??? why don't they just have the ai make the thumbnails instead of this???
it looks worse in the sense that it's an obvious photoshop where the subject was badly composited into the scene. AI might not have that same issue but would look worse in so many other ways like generating weird blobby nonsense
AI also probably won't do a good job at making someone's exact face unless you train a model on lots pictures of the person which takes time, effort and knowledge of how AI works. it would actually be a lot more difficult to get a passable AI result than just slapping a picture of your stupid face on a background image
There's IPadapter for SD models which only requires a single photo at runtime, though I don't know exactly how strong its adherence is. There's also training a LORA which would only require a few images and take maybe a day at the most, which would be an easy investment of time and resources for someone who wants to churn out tons of images with that one face on them. And of course there's the simplest method of all: just crudely pasting the desired face into the image and then sending it for a low denoise img2img pass to make the inscrutable machine integrate it into the image better.
That level of extremely basic and rudimentary technical knowledge is probably beyond the influencers themselves, but certainly not beyond whatever flunky they pay to maintain their brand like that, at which point it's probably self-preservation and not wanting to create an automated process that can replace themselves that stops them from using that approach.