详情
推薦
SDXL
v1.0
Easter Egg House [Illustrious & SDXL & SD1.5]

Easter Egg House [Illustrious & SDXL & SD1.5]

34
1
0
#statue
#建築物
#building
#復活節
#2024 年復活節
#二零二五年復活節

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

Happy Easter! 🐰 Hope you and your loved ones have a wonderful Easter weekend! ✝

Please checkout out all my Easter Loras --> https://civitai.com/user/CitronLegacy/models?tag=easter

查看译文

評分與評論

-- /5
0 個評分

尚未收到足夠的評分或評論

no-data
暫無數據
C
與模型對話
公告
2024-04-01
发布模型
2025-04-19
更新模型資訊
模型详情
類型
LORA
发布時間
2024-04-01
基础模型
SDXL 1.0
触发词
Easter Egg Home
復制
版本介绍

Trained on: 21 images

Steps: 280

Total Time: 40:07

--

[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 = 13

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 = "Easter_Egg_Home_SDXL"

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

log_prefix = "Easter_Egg_Home_SDXL"

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

许可范围
來源: civitai

1. 轉载模型僅供學習與交流分享,其版權及最終解释權归原作者。

2. 模型原作者如需認領模型,請通過官方渠道联系海藝AI工作人員進行認證。我們致力於保護每一位創作者的權益。 點擊去認領

創作许可范围
在線生圖
進行融合
允许下载
商業许可范围
生成圖片可出售或用於商業目的
允许模型轉售或融合后出售
QR Code
下載SeaArt App
在移動端继續你的AI創作之旅