Comment on Adobe’s ‘Ethical’ Firefly AI Was Trained on Midjourney Images
bionicjoey@lemmy.ca 6 months agoThe process of training is itself a pipeline
Comment on Adobe’s ‘Ethical’ Firefly AI Was Trained on Midjourney Images
bionicjoey@lemmy.ca 6 months agoThe process of training is itself a pipeline
General_Effort@lemmy.world 6 months ago
Yes, but the model is the end of that pipeline. The image is not supposed to come out again. A model can “memorize” an image, but then you wouldn’t necessarily expect an amplification of artifacts. Image generators are not supposed to d lossy compression, though the tech could be used for that.
Grimy@lemmy.world 6 months ago
If the image has errors that are hard to spot by the human eye and the model gets trained on these images, does errors that came about naturally on real data get amplified.
Its not a model killer but it is something to watch out for.
General_Effort@lemmy.world 6 months ago
Yes, if you want realism. But that’s just one of the things that people look for. Personal preference.
SomeGuy69@lemmy.world 6 months ago
Invisible artifacts still cause result retardation, realistic or not. Like issue with fingers, shadows, eyes, colors etc.