It's still not perfect. may need to filter the image training model again.


Main tag : Suspension,
Secondary tag : arms behind back, bound, ???????,
: knee down, knee up, ???????????,
LoRA str : 0.8-1.1
Prompt str : 1.0
Denoising str : <0.35
Training Pony LoRA Powershell info :
resolution = 768
Batch size = 2
network_dim = 8
network alpha = 8
mix/save_precision = BF16
optimizer_type = Lion
optimizer_args = WD=0.001
GPU RTX 4060Ti 16GB
Torch 2.51+cu121 + Xformers + gradient_checkpointing
Vram used = 9.8GB
Speed = 1.46sec/it
It's still not perfect. may need to filter the image training model again.
1. I diritti dei modelli ripubblicati appartengono ai creatori originali.
2. I creatori originali che desiderano reclamare il proprio modello devono contattare il personale di SeaArt AI tramite canali ufficiali. Clicca per rivendicare
