Trained on Illustrious-XL(v0.1).
c-trigger/theredgoon:
http://www.furaffinity.net/user/c-trigger/
https://bsky.app/profile/theredgoon.bsky.social
https://meow.social/@TheTriggs
https://itaku.ee/profile/hotdoggoz
Prompt :
masterpiece, best quality, amazing quality, ctr1g93r, Negative Prompt :
bad quality, worst quality, worst detail, sketch, censor, optional negative prompt :
monochrome, greyscale, signature, url, artist name, username, watermark, text, English text,Description
{
"engine": "kohya",
"unetLR": 1,
"clipSkip": 2,
"loraType": "lora",
"keepTokens": 1,
"networkDim": 16,
"numRepeats": 5,
"resolution": 1984,
"lrScheduler": "cosine",
"minSnrGamma": 5,
"noiseOffset": 0.1,
"targetSteps": 3882,
"enableBucket": true,
"networkAlpha": 8,
"optimizerType": "Prodigy",
"textEncoderLR": 1,
"maxTrainEpochs": 23,
"shuffleCaption": true,
"trainBatchSize": 4,
"flipAugmentation": false,
"lrSchedulerNumCycles": 3
}
Comments (3)
Nice! What configurations you used on this lora? My version is a little strange and I want to make better style loras!
Thanks! All the configurable parameters I used are listed in the “About this version” section on the model page.
You’re also very welcome to check out a document I wrote here: [link] — it goes into more detail about how I make style LoRAs. Hope it helps!
@sxus_Sw Thanks for sharing!