DrawsTech

@drawstech.bsky.social

SFW Mostly | Contains 18+ | Anthro Artist striving to do better | Icon: @KingSuSN64 | Banner: @MastaFran | Don't use or steal my characters |34 M | FA: https://www.furaffinity.net/user/chasertech

Clarissa Bloodworth 🐻‍❄️( Tails Noir ) I loved this game! I feel sad for the raccoon 😭 Don't try to fool this woman, she always knows when you're lying, and she'll destroy you!

Bild

I got a lot to say. Models with clean data sets wouldn't produce work similar to someone else's unique work unless it's trained on it. There's a reason why there are tons of loras that are trained on an artist and not always embedded within local models. The work produced would be generic.

Sarantics@sarantics.bsky.social · 2y ago

When it comes to AI, a recurring concern is over "stolen art." This concern is bunk, and I'll explain why with two rebuttals: 1. If an AI trained on public domain work could accurately reproduce your art, would you feel less anxious? No, and for good reason. 🧵(1/8)