zlacker

>>bewal4+(OP)
Ah, this is where this comes from. There has been rumours flying around in Stable Diffusion / Flux circles that you would get much more realistic pictures when you include a photo id like IMG_0416.

>>jsemra+44
I don’t think it comes from these Youtube videos – Flickr and other photo upload services are a more likely source of training images with default file names.

>>Sharli+Vd
Maybe its a combination of both.

>>jsemra+BJ
It seems exceedingly unlikely to me that frames from random YouTube videos would have been used to train image generation models. First off, they're difficult to extract and second, the quality of individual video frames is very low, especially if we're talking about 15 year old phone videos at what, 480p at the very best!