Donate Coffee for Gtonero

Prompt ใช้ยังไงโปรดอ่านใน About This Version

Anima Weight Norm

• DiT - 1.0288

• Text-Encoder - 0.5250

Training LoRA Powershell info :

• resolution = 512 [Anima]

• Batch size = 2

• network_dim = 32

• network alpha = 32

• mix/save_precision = BF16

• optimizer_type = AdamW

• optimizer_args_other = foreach=True

• GPU RTX 4060Ti 16GB

• Torch 2.9.0+cu130 + SDPA+ gradient_checkpointing