Follow me on X/Twitter for exclusive content: https://x.com/Citron_Legacy 😁
Please checkout all my Style Loras: https://civarchive.com/collections/10766871
Description
m1nC1tr0n,
FAQ
Comments (4)
What's your experiences training minimax? was it with videos or images? I wanna train one on zenless zone zero one day
A Zenless Zone Zero lora would be peak!
I'm training only on images so far. I'm using the same datasets from my Illustrious loras but I'm using captions instead of tags.
So far its a nice experience and it just works (other than the audio because I only have images).
I made 2 loras that might have failed but 8 successes out of 10 different ideas is pretty good.
I'm using 100-200 images
However smaller datasets seem fine
34 images - https://civitai.red/models/2943813/minimalistic-style-minimax-h3
26 images - https://civitai.red/models/2405530/civchan-yandere-buzz-queen-anima-and-h3
39 images - https://civitai.red/models/2943858/perona-ghost-princess-or-one-piece-minimax-h3
I'm using only the defaults on the CivitAI trainer. I usually use a different tool for captioning but I used the CivitAI caption-er for https://civitai.red/models/2405530/civchan-yandere-buzz-queen-anima-and-h3
I'm still learning and a have a few ideas on how to caption the datasets better but it works right now.
@CitronLegacy Thank you, I would like to train on videos, because that's kinda the point when it comes to those animations. But every lora on here is a porn one 😂, style loras are rare
@sovietlat use fizgig if you have the hardware. Makes training super easy and fast to get started with, the real magic happens with settings tuning and dataset curation.