
IMP: This LORA is not to be used for 18+ or mature themes, this is a kawaii or cute theme based and should be used only for that purpose.
This is my fourth Lora! It is not the best but still can generate some good images.
TRIGGER: neema_fluffy, child, kid
IMP: For some reason this lora creates low contrast images, if you do not want that there are 2 ways to solve it:
-
increase cfg (not recommended as can effect the way model works)
-
write the trigger "high contrast" (recommended)
(no animal ears) - Add this to ensure close resemblance to char (optional)
Tested on all Illustrious models. I have not tested on any other.
Steps: 20-30 (use model recommendation /I trained on 24 steps)
Cfg: 7.0 (Use what is recommended by model)
Sampler: Euler_A
Scheduler: normal /simple /beta (may produce artifacts)
HIGH RES FIX: ((((highly recommended)))
Steps: 13
Denoise: 0.58
Upscale type: latent
Latent upscale: nearest_exact
Upscale by: 1.5
FOR UPSCALER: 4x RealESRGAN X PLUS
Daemon detailer (Optional, but recommended) {Can be ultra good at 0.55 denoise and 20 steps /I have seen it brings out a lot of detail and also fixes certain issue with some anatomy, do not go to 0.6 as it can change the image a lot, stick to 0.5-0.55}
Face and hand detailer (Optional)
HAPPY GENERATIONS!
描述:
训练词语:
名称: 1303724_training_data.zip
大小 (KB): 7172
类型: Training Data
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success
名称: Nefertima_Osfe_ネフェルティマオスフェ_Kawaii__Cute_Illustrious__Fluffy_Paradise__Anime_character.safetensors
大小 (KB): 223103
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success