HI there,
You're obviously not understanding (or pretending not to understand) my earlier posts about the source of the current 2D ML models, so I'll leave it at that.
Very cool Pilou !
.
I did some research and found out that what I am looking for is
called "Algorithmic Paredolia" performed by digital neural net-
works. The first algorithm of this kind was created by Google and
is called "Deepdream"
.
I wonder if it is the same / modified or a new algorithm used
for the "remix" function of Midjourney which generates pretty
amazing results.
.
Now I am searching for such an offline open-source tool to
merge imagery and expect to find some sophisticated stuff
which is capable to "learn" what I expect it to do by iterative
processes.
I imagine a "Pareidola" software with a node based system where I can link
a pool of images, patterns and textures together and to be able to teach the
neural ntework based system in which way I wont those nodes applied to
my base image. And to be able to create quick iterations by changing the
respective parameters.
same with "a hoard of strange creatures from hell fighting over a very large pizza in front of a volcano spewing lava and black smoke streams of glowing hot lava Joe Fenton" https://www.joefentonart.com
What really made my jaw drop was this collection of Midjourney -
generated images which stand out from anything I have seen in
AI created imagery. As if Midjourney has an inbuilt art-director of
exquisite taste and a thorough inbuilt quality control - absolutely
awesome.
. https://www.midjourney.com/showcase/top/
cm.jpg
