[SD 1.5][LORA][LoRA] Nagayama Yunon style for Anything v4.5 lora-v1.0

0xSoul

• checkpoint: Anything v4.5 (DO NOT Forget VAE)

• no trigger words required

• recommond CFG Scale = 7.0

• recommond weight: 0.6

• recommond use hires.fix

Training params

$resolution = "768,1024"
$batch_size = 3
$max_train_epoches = 8
$save_every_n_epochs = 1
$network_dim = 128 
$network_alpha = 128 
$clip_skip = 2 
$lr = "1e-4"
$unet_lr = "1e-4"
$text_encoder_lr = "1e-5"
$lr_scheduler = "cosine_with_restarts" 
$lr_warmup_steps = 0 
$lr_restart_cycles = 1
$noise_offset = 0.05 
$keep_tokens = 3
$min_bucket_reso = 256
$max_bucket_reso = 1024
$use_lion = 1