this post was submitted on 01 Dec 2025
315 points (86.2% liked)
Memes
53334 readers
674 users here now
Rules:
- Be civil and nice.
- Try not to excessively repost, as a rule of thumb, wait at least 2 months to do it if you have to.
founded 6 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
Training models takes a stupid amount of energy. Using them after the fact uses very little.
I could generate something like this on my phone using any of the dozens of local models.
Feel free to share the device type and local AI model capable of producing an image like this. My guess is you won’t though because it’s not possible 😕
Try for yourself https://github.com/ShiftHackZ/Stable-Diffusion-Android
But that's (very clearly) beside the point, which is that you can run a variety of models locally on your PC or phone for miniscule energy. Once a model is trained the damage has already been done.
As always, it's the corporations using the resources and doing the damage, so pearl clutching about random individuals is less than useless.
Try Z-Image Turbo it's super new and runs on any computer with, like, a cpu and 24 GB ram. It can generate way better images than this too.