Skip Navigation

InitialsDiceBearhttps://github.com/dicebear/dicebearhttps://creativecommons.org/publicdomain/zero/1.0/„Initials” (https://github.com/dicebear/dicebear) by „DiceBear”, licensed under „CC0 1.0” (https://creativecommons.org/publicdomain/zero/1.0/)RE
Posts
4
Comments
203
Joined
2 yr. ago

  • Pretty much

    Its on the same path as GAN but there is no adversarial network feedback - Nothing telling the generative ai it is generating bad data

    Seems like GAN without the benefits for training models (which is what they wanted it seems. To mess with the training data)

    I dont see how this becomes permanent since the models are already trained. Maybe if the technique becomes easy for artists to apply to their digital works and makes it into the training data for the next models