タイプ
LoCon
投稿日時
2024-09-01
基本モデル
Flux.1 D
トリガーワード
ukiyo-e art
コピー
バージョン紹介
Training settings
Training epochs: 0
Training steps: 2000
Learning rate: 8e-05
Effective batch size: 2
Micro-batch size: 2
Gradient accumulation steps: 1
Number of GPUs: 1
Prediction type: flow-matching
Rescaled betas zero SNR: False
Optimizer: optimi-lion
Precision: Pure BF16
Quantised: Yes: int8-quanto
Xformers: Not used
LyCORIS Config:
{
"algo": "lokr",
"multiplier": 1.0,
"linear_dim": 10000,
"linear_alpha": 1,
"factor": 16,
"apply_preset": {
"target_module": [
"Attention",
"FeedForward"
],
"module_algo_map": {
"Attention": {
"factor": 16
},
"FeedForward": {
"factor": 8
}
}
}
}
Datasets
met-scrape-512
Repeats: 1
Total number of images: 1198
Total number of aspect buckets: 4
Resolution: 0.262144 megapixels
Cropped: False
Crop style: None
Crop aspect: None
