Katarina Claes - [My Next Life as a Villainess - All Routes Lead to Doom!]
Update 3.0
Commision Work
New own Trainer
Better Dataset
LoRA Info Illustrious 3.0
Trigger: sysdeep_Katarina
Trigger need: Yes
Base Model: Illustrious-XL
Generate Info: Dont use Base Model as Generation use Custom Models
Image Source: Screencaps
Train with NSFW Images: NO
Samples: 1248x1824 + 1.2x HRF
Sample Model: animemix 8.0
For Stable Diffusion WebUi (Only v3)
Under Downloads you find a Zip file (Training Data)- With Cover Image + LoRA Info (Trigger Word backed in)
OLD INFOS:
Illustrious v2
NEW Trigger: sysdeep_catarina
Train Image Size: 1024x1024 , 1216x832, 832x1216
SD Version: Illustrious
Clip Skip: 1
Trained on: Illustrious-XL
Failed Filename sry ^^
v2 has the Filename Catarina Claes - [My Next Life as a Villainess - All Routes Lead to Doom!] - illustriousXL v1
Illustrious v1
Trigger: sysdeep_katarina
Train Image Size: 1024x1024 , 1216x832, 832x1216
SD Version: Illustrious
Clip Skip: 1
Trained on: Illustrious-XL
Infos SD1.5
Trigger: sysdeep_katarina
Train Image Size: 768x768, 768x512, 512x768
SD Version: 1.5
Clip Skip: 1
Sample Images LoRA Weight: 0.8
Trained on: AnythingElse V4
SDXL 1.0
Trigger: sysdeep_katarina
Train Image Size: 1024x1024 , 1216x832, 832x1216
SD Version: SDXL
Clip Skip: 1
Trained on: Animagine XL V3
Pony Diffusion [SDXL]
Trigger: sysdeep_katarina
Train Image Size: 1024x1024 , 1216x832, 832x1216
SD Version: Pony [SDXL]
Clip Skip: 2
Trained on: Pony Diffusion V6 XL
Description
FAQ
Comments (2)
Unexpectedly, this is also Katarina's anime style. Although with very saturated light. Works without trigger word and clip skip:2. Did you do anything special here? For example, "Elise de Clorance", is not stylized that way.
Yes i focus on my character lora the official artstyle. The Saturated lights is because of traindata, the anime is little saturated ^^".
I use my own lora trainer and so my outputs change from time to time when i update my data ^^