Experimenting with the SD 2.1 model with an additional CLIP guidance integration. The hallucinated watermark issue is a big problem with this. Really needs some kind of watermark suppression, maybe associated with the additional CLIP modulation? Latent Majesty Diffusion way back in the dark ages of the summer of 22 used a modified CLIP aesthetic model that was specifically trained for watermark suppression and was very good at not generating them.
No comments:
Post a Comment