v3.0 :
Trained on Juggernaut X with 199 photos of Brazilian model Cindy Mello. Works best for Juggernaut X. Tested on Juggernaut X, Juggernaut v7, RealismEngine 2, RealVisXL3, AlbedoBaseV2! Use with keyword : "cixmllo" . Use around strength 1.0. CFG 5.0-7.0. Clipskip 1. Can be used for example as follows:
Positive : {Artstyle}, {Character and scene description}, cixmllo, <lora:cimello_juggerX_xl_1_wocap_merger_71_100_03_07-cixmllo:1.0>
Negative : ugly, deformed, airbrushed, photoshop, rendered, (multiple people), child
v1.0 and v1.1
Lora of Brazilian model Cindy Mello trained on 38 images of her with SDXL 1.0 base. The recommended strength for this version is in ComfyUi is 0.9-1.1.
Description
FAQ
Comments (2)
The likeness here is excellent - amazing training!
Thanks! I have two different levels of training v1.1 is trained much less and should be better at following the prompt, while v.1.0 is better at likeness.