Indeed!
Another thing that comes to mind as a corollary is that the AI seems to like being constrained in its outputs. So adding something like “in the style of Monet” to the end of the prompt will return much more coherent results.
Another thing that comes to mind as a corollary is that the AI seems to like being constrained in its outputs. So adding something like “in the style of Monet” to the end of the prompt will return much more coherent results.
[1]The Deep-Daze author's most popular T2I mashup: https://github.com/lucidrains/big-sleep
https://colab.research.google.com/drive/1NCceX2mbiKOSlAd_o7I...