Should be a more suitable fit for illustrious. It is bigger than the previous versions, both in terms of training dataset (200+ images) and the number of steps. Training parameters are listed below -

"engine": "kohya",

"unetLR": 1,

"clipSkip": 1,

"loraType": "lora",

"keepTokens": 0,

"networkDim": ??,

"numRepeats": 3,

"resolution": 1024,

"lrScheduler": "cosine",

"minSnrGamma": 5,

"noiseOffset": 0.1,

"targetSteps": 3045,

"enableBucket": true,

"networkAlpha": 32,

"optimizerType": "Prodigy",

"textEncoderLR": 1,

"maxTrainEpochs": 10,

"shuffleCaption": false,

"trainBatchSize": 2,

"flipAugmentation": false,

"lrSchedulerNumCycles": 3