YourAnimeHaven
Practicing making LoRa
Works pretty well with aDetailers especially face.
v0.1 was used to generate training data for Beta v0.2 and I personally find v0.2 to work better but both are still difficult to prompt and require messing around with cfg and LoRa weights depending on what you're using it for.
Check descriptions on each version for notes.
Popularity
Info
Latest version (Beta v0.3): 1 File
About this version: Beta v0.3
Trained on images generated by Beta v0.2
Still struggling with pulling the eyes out of v0.1 data but working way better than last version
Works insanely well with a good seed and aDetailers
Don't need to prompt too heavily to obtain Fades jewelry, or hair, but the eyes still require to be told what color they are and sometimes the nail and lip color need to be prompted
Moving away from the default clothing here a bit cuz it was ruining the face on previous versions but is still there if you prompt it
Works best on close ups and medium distance shots
fade_(valorant) tag needs to be typed like fade_\(valorant\) in prompt but honestly works either way pretty well
Use lower CFG from my experience unless you know what you're doing
3 Versions
Go ahead and upload yours!
