Original link: https://sololo.xyz/model/588-vg20-rebecca-SoloLoRA
VG20 Rebecca, a virtual woman.
Still continuing the same experiment as before. It hasn’t reached the result I really want yet, but the outcome is still pretty decent.
Want more of my models? Visit my website: sololo.xyz
Latest releases first, HUNDREDS of models FREE to download.
♥ Support me on Ko-fi: https://ko-fi.com/solo_lee
♥ Telegram channel: https://t.me/sololeeai
♥ Model orders: https://sololo.xyz/commission
Thanks so much for your support! ♥
Description
Original link: https://sololo.xyz/model?id=588
This LoRA is trained on Z Image Base, but it can also be used with ZIT. All sample images were generated using ZIT.
In terms of facial aesthetics, I personally prefer the Zv1. In terms of facial consistency and stability, Zv2 doesn’t feel much different from Zv1, but both are clearly better than F2K9v1.
Based on my limited experience so far, training a LoRA on Z Image Base for use with ZIT doesn’t seem like a good idea. Using Z Image Base for text-to-image also doesn’t seem like a good idea. In terms of both generation speed and image quality, ZIB doesn’t really have any advantages. ZIB’s real value may lie more in the derivative models built on top of it in the future—much like how SD 1.5 served as a foundation back in the day.
For upcoming ZIT LoRAs, I’ll likely go back to training directly on ZIT. The training methods and strategies still need some adjustment and optimization.
I’m hoping that better ZIB derived models will eventually come along and replace ZIT.
FAQ
Comments (4)
You seem to have experimented quite a bit. What would you currently recommend to train Character LoRAs on?
ZIB, ZIT or Flux.Klein 9B Base?
Haha, that’s exactly what I’m struggling with right now. None of the three have given me results I’m really happy with yet, so I’m still experimenting.
@solo_lee I mean I haven't trained a character for all of them so far, but from all the LoRAs on CivitAI, I can't see any model being stronger than ZIT for characters. ZIB left me a bit clueless 😅
@cluster1500 From my experience, ZIB feels better on the training side, but when it comes to actually generating images… ZIB is really not great 😅