New version i have started training, Once again, I implemented some new stuff to the training dataset, there has been any new image added, but I went back to training a large dataset, 490 image, which is probably bad idea, much of training is still voodoo, so I dont know maybe picking 100 image and doing 100 Epoch would be better. anyway.
Its still training there is things I like and things I dont, cant tell if its better or not
29/75 epoch trained so far, I will give 3 example of good I guess
again its barely half way through training but pov stuff with detailed tagging it does well so far. I dont think the artstyle is quite there yet, that really due to the steps and epoch stuff, at some point its not trained enough and after some point it will get fried.
now for bad. Jess. what happened, I am devastated lol.
yea I dont know, the tag was just Jess, so yea less detailed tagging the worse it is for now.
But everything is not lost