Dataset of 190 HD images with various positions, clothes and haircuts to guarantee a flexible character, working with all Illustrious models.
Recommanded generation settings:
- strength : 0.6 - 0.8
- cfg : 0.2-0.3
- steps : 20-30
-> Image hirez fix with denoise strength 0.2 for clean results.
NSFW supported, enjoy.
Thank you for any feedbacks and support !
Description
Dataset : 190 HD images
Selected epoch : 10
Params :
{ "lr": 0.0005, "engine": "ai-toolkit", "epochs": 15, "ecosystem": "sdxl", "keepTokens": 1, "networkDim": 32, "numRepeats": 2, "resolution": 1024, "lrScheduler": "cosine", "minSnrGamma": 5, "noiseOffset": 0.1, "networkAlpha": 32, "optimizerType": "adafactor", "shuffleTokens": true, "textEncoderLr": 0.00005, "flipAugmentation": true, "trainTextEncoder": true }