betterftr

reinstalled pip install --upgrade charset_normalizer and it seems resolved... Windows11

.jpg is the extension not the name. so u need image1.txt and image1.jpg :)

to guide music generation with input on top of text like "classical music" + humming.wav or some piano notes stuff like that

Update: did a fresh install on master branch with full default cascade settings, this time I even included training the prior (thought maybe the issue is with tenc only) but...

found the problem: changing safeguard warmup/coef doesnt break it, changing initial d or Bias correction does orange: prodigy's default settings loaded. blue: Bias correction turned on green: initial D changed...

update again: reinstalled windows, I have only a git, a python 3.10, an nvidia driver and OneTrainer. Results are still the same. Also did test kohya as well to see...