16枚の画像で学習。最も長い辺の約400ピクセルほど... JPEGが多数含まれる。
{
"engine": "kohya",
"unetLR": 0.0005,
"clipSkip": 1,
"loraType": "lora",
"keepTokens": 0,
"networkDim": 16,
"numRepeats": 30,
"resolution": 512,
"lrScheduler": "cosine_with_restarts",
"minSnrGamma": 8,
"noiseOffset": 0,
"targetSteps": 1067,
"enableBucket": true,
"networkAlpha": 16,
"optimizerType": "Adafactor",
"textEncoderLR": 0.0001,
"maxTrainEpochs": 20,
"shuffleCaption": true,
"trainBatchSize": 9,
"flipAugmentation": true,
"lrSchedulerNumCycles": 4
}