Trained with 217 Images.
Try rendering with 712x1024 resolutions to spot likeness on full body.
512x712 or so for portraits.
Note that version 2.0 its a LORA Standard Format and Version 1.0 its LyCORIS/LoCon.
I would like to encourage to use ADetailer [ https://github.com/Bing-su/adetailer.git ] if you want to get very good results on likeness mostly for your renders far from the common portrait zoom, like full body faces or so.
I know that I'm trying to do my best to give the best quality using good quality datasets, but even with the most perfect training some results are not what I want on full body faces, and the only get good results its using ADetailer.
Thanks!
https://www.patreon.com/smoonfucker
Daily updated list of models: https://www.patreon.com/posts/list-of-models-89239085
Please, you can also support me at:
Thanks :_)
Use of this model it's up to the responsibility of each user on posting any content, please avoid to post any NSFW content of the model to avoid model removal, users compliance or CIVITAI restrictions. Thanks!