詳細
おすすめ
SDXL
v1.0
Hobbit Hole (Shire in Eriador, Middle Earth) (Lord of the Rings)

Hobbit Hole (Shire in Eriador, Middle Earth) (Lord of the Rings)

105
4
0
#house
#建物
#ロード・オブ・ザ・リング
#建物
#The Lord of the Rings

Help fuel my passion! Even $1 makes a difference. https://ko-fi.com/citronlegacy

Are there any cool buildings or structures from games you want to see?

I'm building my Building Lora skills so I'd appreciate ideas of cool video game structures!


"In a hole in the ground, there lived a Hobbit. Not a nasty, dirty, wet hole... it was a hobbit-hole, and that means comfort."

I love this music. It feels like hope and comfort.


Trained on: 33 images

Training Model: Animefull-final-pruned-fp16

flip_aug: False

Num of Repeats: 10

Unit is Epochs or Steps: Epochs

Number of Epochs or Steps: 10

Training Batch Size: 2

Total Steps: 1650

Resolution: 512

Network Dim: Dim 32 and Alpha 16

Lora Creation Process took: 00:18:27

翻訳を表示

評価とレビュー

-- /5
0 件の評価

まだ十分な評価やレビューが集まっていません

no-data
データなし
C
モデルと会話する
お知らせ
2024-03-27
モデルを公開
2024-04-14
モデル情報を更新
モデル詳細
タイプ
LORA
投稿日時
2024-04-14
基本モデル
SDXL 1.0
トリガーワード
Hobbit Hole,
flower, tree,
コピー
バージョン紹介

Trained on: 33 images

Steps: 330

Total Time: 49:19

--

[network_arguments]

unet_lr = 0.75

text_encoder_lr = 0.75

network_dim = 32

network_alpha = 32

network_module = "networks.lora"

network_train_unet_only = false

[optimizer_arguments]

learning_rate = 0.75

lr_scheduler = "cosine_with_restarts"

lr_scheduler_num_cycles = 3

lr_warmup_steps = 16

optimizer_type = "Prodigy"

optimizer_args = [ "weight_decay=0.1", "betas=[0.9,0.99]",]

[training_arguments]

pretrained_model_name_or_path = "stabilityai/stable-diffusion-xl-base-1.0"

vae = "stabilityai/sdxl-vae"

max_train_epochs = 10

train_batch_size = 4

seed = 42

max_token_length = 225

xformers = false

sdpa = true

min_snr_gamma = 8.0

lowram = true

no_half_vae = true

gradient_checkpointing = true

gradient_accumulation_steps = 1

max_data_loader_n_workers = 8

persistent_data_loader_workers = true

mixed_precision = "fp16"

full_bf16 = false

cache_latents = true

cache_latents_to_disk = true

cache_text_encoder_outputs = false

min_timestep = 0

max_timestep = 1000

prior_loss_weight = 1.0

[saving_arguments]

save_precision = "fp16"

save_model_as = "safetensors"

save_every_n_epochs = 1

save_last_n_epochs = 10

output_name = "Hobbit_Hole_SDXL"

output_dir = "/content/drive/MyDrive/lora_training/output/Hobbit_Hole_SDXL"

log_prefix = "Hobbit_Hole_SDXL"

logging_dir = "/content/drive/MyDrive/lora_training/log"

許可範囲
モデルソース: civitai

1.転載モデルは学習・共有目的のみで使用し、著作権は原作者に帰属します

2.モデルの認証は公式チャンネルでご連絡ください。クリエイターの権利保護に努めています クリックして認証

創作許可範囲
オンライン画像生成
統合
ダウンロード
商用利用の許可範囲
生成された画像は販売または商業目的での使用
モデルの転売やモデル統合後の販売
QR Code
SeaArt Appをダウンロード
モバイルでAI創作の旅を続けよう