Parameter Settings Network Module LoRA Use Base Model Anima - preview-3 Trigger words - Image Processing Parameters Repeat 3 Epoch 10 Save Every N Epochs 1 Training Parameters Seed - Clip Skip - Text Encoder learning rate 0.000005 Unet/DiT learning rate 0.00002 LR Scheduler cosine Optimizer AdamW8bit Network Dim 64 Network Alpha 32 Gradient Accumulation Steps - Label Parameters Shuffle caption - Keep n tokens - Advanced Parameters Noise offset 0.01 Multires noise discount 0.1 Multires noise iterations 10 conv_dim - conv_alpha - Batch Size - Sample Image Settings Prompt witches hat, cleavage, hat, dress, 1girl, solo, white hair, long hair, staff, bare shoulders, simple background, hat ribbon, sfw, ribbons, original, black dress, off-shoulder, medium breasts, breasts, black_eyes Sampler euler