
You can try any model you want, however I really suggest using Hassaku XL Checkpoint or AutismMix checkpoint
Note: When using Hassaku you might need to use an age slider though, I like the quality and the prompt adherence of the model, but it tends to age down the characters. (Or just use any other model of your preference)
LoRA settings:
-
Weight: 0.7 - 1.0
Base model settings:
-
Steps: <30
-
Width: 896px
-
Height: 1132px
-
Sampler: Euler a
-
VAE: None
-
CFG Scale: 3 - 5
-
Clip skip: 2
Upscaler settings:
-
Upscaler: Latent (Nearest-Exact)
-
Upscale by: 1.5x
-
Denoising strength: 0.55
描述:
I tried really hard to check for any differences since they're pretty much identical twins and I couldn't find any. Nonetheless I trained a trigger word for each of the twins with their respective dataset, for the hardcore fans out there who might notice them apart.
训练词语: aoi_hinata_pony,aoi_yuuta_pony,orange hair, green eyes,
名称: Aoi_YuutaHinata_Pony.safetensors
大小 (KB): 223114
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success