13 Replies
rope seems not really to be in develeopment any more, would face fusion be the safer bet?
Does anyone have any info about optimal dataset sizes ?
I'm trying to retain to make images look more realistic as if they were taken from a camera. How many images should it need for that ?
unfortunately that didnt work for me too well
Im trying to make a flux lora with varied yet consistent outputs like this with 20 images ( can use more)
I had the best but not optimal results with 1_ohwx Head and body + joy captioning
when I use only instance + class prompt + no captions its way under trained
not too sure what to try next
yep that guy more active
no such thing but i have shared 15 vs 256 😄
also style training dataset as well
i can give you private lecture or train for you. other than that doing more experiments :d
@Dr. Furkan Gözükara try this prompt with your LoRA 🥲 :
a OHWX MAN standing inside a small room. the walls are made of hundreds of faces staring at him. each face is displaying different strong emotions
it will be all my face 😄
flux bleeds currently
yes it will be very weird 🤣
ye out of ordinary prompts
is there a channel for pricing
I will message you now
is the Image that you have on massed compute a docker image ?
yep
@NicB makes it
man tutorial is 2 hours 49 minutes after editing