<h3 id="original-link:-https:sololo.xyzmodel588-vg20-rebecca-sololora">Original link: <a target="_blank" rel="ugc" href="https://sololo.xyz/model/588-vg20-rebecca-SoloLoRA">https://sololo.xyz/model/588-vg20-rebecca-SoloLoRA</a></h3><h3 id="vg20-rebecca-a-virtual-woman.">VG20 Rebecca, a virtual woman.</h3>Still continuing the same experiment as before. It hasn’t reached the result I really want yet, but the outcome is still pretty decent.<h3 id="want-more-of-my-models-visit-my-website:-sololo.xyz">Want more of my models? Visit my website: <a target="_blank" rel="ugc" href="http://sololo.xyz">sololo.xyz</a></h3>Latest releases first, HUNDREDS of models FREE to download.♥ Support me on Ko-fi: <a target="_blank" rel="ugc" href="https://ko-fi.com/solo_lee">https://ko-fi.com/solo_lee</a>♥ Telegram channel: <a target="_blank" rel="ugc" href="https://t.me/sololeeai">https://t.me/sololeeai</a>♥ Model orders: <a target="_blank" rel="ugc" href="https://sololo.xyz/commission">https://sololo.xyz/commission</a><hr />Thanks so much for your support! ♥

VG20 Rebecca SoloLoRA

Original link: <a target="_blank" rel="ugc" href="https://sololo.xyz/model?id=586">https://sololo.xyz/model?id=586</a>Experimental, almost there, but still a long way to go.Both base 9B and 9B are supported.This is my first klein 9B LoRA. I tried training on 4B several times before but ended up putting it aside for now. From a LoRA training perspective, 9B works much better than 4B.What surprised me was that it turned out to be even harder to train than ZIT. I didn’t expect that, especially since one is a base model and the other is a turbo model.That actually makes me even more excited about Z Image. Hopefully it won’t be a letdown when it finally arrives.The main issues with this LoRA at the moment are:<ol><li>Some facial distortion.</li><li>The face likeness isn’t quite where I want it to be yet.</li><li>Facial consistency is still not very stable.</li></ol>Also, I’m still getting familiar with how klein behaves when generating images, and I haven't fully figured out what kind of prompts work best yet.My rough impression is that klein goes further than ZIT in terms of realism, but it seems to fall a bit short when it comes to aesthetics.That’s it for now. I’ll keep experimenting.

Files with SHA256: 8f238229b67f836aa1c3ee6c8603303094adf2c68edc418b6ceb679dbcd1486c