For those using the Anima version, it can be a little tricky. I recommend a weight of 0.9 or lower. At full strength you can get some anatomy inconsistencies. I'm not 100% happy with how it came out but I feel I gave it the best shot I can give right now.
ZCIK is an artist I've been wanting to do for a super long time but I was worried their style wouldn't translate well into AI. Thankfully it seems I was wrong, I'm super happy with how this one came out. Sucks it's uploading in the middle of Civitai's ongoing notification issues. If you're reading this, thanks for checking it out anyway.
Regretfully there's no character tagging in the dataset as ZCIK's recurring characters don't appear often enough for that to be viable.
Description
Trained in 201 images:
{
"engine": "kohya",
"unetLR": 1,
"clipSkip": 2,
"loraType": "lora",
"keepTokens": 1,
"networkDim": 16,
"numRepeats": 3,
"resolution": 1024,
"lrScheduler": "cosine",
"minSnrGamma": 5,
"noiseOffset": 0.05,
"targetSteps": 3015,
"enableBucket": true,
"networkAlpha": 8,
"optimizerType": "Prodigy",
"textEncoderLR": 1,
"maxTrainEpochs": 20,
"shuffleCaption": true,
"trainBatchSize": 4,
"flipAugmentation": true,
"lrSchedulerNumCycles": 3
}