News for hackers. Stuff that matters.
Re:LoRA Adaptors for Precise Control in Diffusion Models by minimaxir on Wednesday December 13, 2023 @10:27PM (#38637424)
AI art and its modern tooling ecosystem is at a point now that it unironically takes more effort to generate an intentionally innovative AI image than it is to draw it from scratch.

Just look at ComfyUI: https://github.com/comfyanonymous/ComfyUI

Re:LoRA Adaptors for Precise Control in Diffusion Models by tracerbulletx on Wednesday December 13, 2023 @11:16PM (#38637712)
It unironically absolutely does not. Source: every visual artist that's spent the last 20 years slowly improving their work.
Re:LoRA Adaptors for Precise Control in Diffusion Models by bee_rider on Thursday December 14, 2023 @12:33AM (#38638168)
FWIW I don’t think they are defending AI by saying that it takes more effort than drawing to make an “intentionally innovative” image.
Re:LoRA Adaptors for Precise Control in Diffusion Models by Der_Einzige on Thursday December 14, 2023 @03:44AM (#38639210)
The person you’re responding to is a titan in their field. Check yourself before you try to check others.
Re:LoRA Adaptors for Precise Control in Diffusion Models by MrScruff on Thursday December 14, 2023 @04:42AM (#38639551)
How do you know the background/experience of the person you're responding to? And even if the person you're claiming has authority here were the worlds leading expert on generative AI, that wouldn't make them authorative on the difficulty of drawing an intentionally innovative image from scratch.

Regardless, the original comment was clearly not serious.

Re:LoRA Adaptors for Precise Control in Diffusion Models by minimaxir on Thursday December 14, 2023 @11:59AM (#38643671)
tbh I don't consider myself a titan in the field but I appreciate the complement :)

I don't get paid enough to be a titan.

Re:LoRA Adaptors for Precise Control in Diffusion Models by smith7018 on Wednesday December 13, 2023 @11:25PM (#38637769)
You genuinely can’t believe that, right? An “innovative AI image” is created all the time whereas it’s much harder to paint an “innovative painting” due to the skill required and the well-tread medium. That’s not even getting into the fact that you can set up and really learn ComfyUI in a week whereas painting is a life-long pursuit.
Re:LoRA Adaptors for Precise Control in Diffusion Models by minimaxir on Wednesday December 13, 2023 @11:56PM (#38637932)
It was not a completely serious comment and was not intended to be a slight against professional artists.
Re:LoRA Adaptors for Precise Control in Diffusion Models by spookie on Thursday December 14, 2023 @02:43AM (#38638837)
Honestly, that happened to me. Was making some UI elements for a game, and tried to generate some. After a while, I was so tired of getting results that weren't quite what I wanted that I just drew them.

It certainly has its place, but the "its taking people's jobs" argument kinda fell apart for me after that moment

Re:LoRA Adaptors for Precise Control in Diffusion Models by MrScruff on Thursday December 14, 2023 @04:29AM (#38639472)
If you find ComfyUI offputting you really wouldn't like the nodegraph based applications we use in VFX.
Re:LoRA Adaptors for Precise Control in Diffusion Models by minimaxir on Thursday December 14, 2023 @12:07PM (#38643811)
That is a correct inference.
Re:LoRA Adaptors for Precise Control in Diffusion Models by whywhywhywhy on Thursday December 14, 2023 @06:03AM (#38640071)
People honestly overcomplicate it, the variety you can get just out of base SDXL without even using loras or other models and comfy nodes is crazy once you get a feel of it but a lot of people make the mistake of not spending the time on it to figure out how to push it in the direction they want and instead think piling on a bunch of loras and an extra model is the key to getting something different.