I was trying to train my Au Ra in FF14, by providing screenshot from the game. Its can output the horn and scales right, but the 3D style is affecting the generation. Anyone have a idea of how to fix it?

These are some of the setting

pretrained_model_name_or_path = "./sd-models/latest.ckpt"

resolution = "640,640"

enable_bucket = true

min_bucket_reso = 256

max_bucket_reso = 1024

save_every_n_epochs = 1

max_train_epochs = 10

train_batch_size = 2

network_train_unet_only = false

network_train_text_encoder_only = false

learning_rate = 0.0001

unet_lr = 3.5e-5

text_encoder_lr = 3e-6

lr_scheduler = "cosine_with_restarts"

optimizer_type = "Lion"

lr_scheduler_num_cycles = 1

network_module = "networks.lora"

network_dim = 32

network_alpha = 32

shuffle_caption = true

weighted_captions = false

keep_tokens = 1

max_token_length = 255

seed = 1337

prior_loss_weight = 1

clip_skip = 2

gradient_checkpointing = false

mixed_precision = "fp16"

save_precision = "fp16"

xformers = true

lowram = false

cache_latents = true

cache_latents_to_disk = false

persistent_data_loader_workers = true