
Hello guys!
So, this is the 2.0 version of my original LoRa of Matthis Coleman, where I included images from 2021 to 2024 (200 imgs).
How to use it:
Clip skip: 2
Hi res upscaler: DAT_x2
Sampling Steps: 20-30
VAE: vae-ft-ema-560000-ema-pruned.ckpt
Prompt weight: 0.8 - 1
Prompting:
Character: Matthis Coleman, male focus, solo, blonde hair, beard, tople
Hairstyle: short hair, buzz cut, blonde hair, brown hair
Body parts: legs, armpit, arm behind back, blue eyes, from back, arms behind back, topless, nude, thighs
Accesories: necklace, rings, beanie, laurel crown (i recommend using v1.0)
Context: bathtub (i recommend using v1.0)
Negative prompt: (low res, worst res:2.0), bad anatomy, deformities, watermark
Additional prompt to complement with:
"detailed face, uhd, 8k, masterpiece"
描述:
More training images were used, now you can add different hairstyles (shaved, buzz and short hair) and you can give a beard to your character.
训练词语:
名称: Matthis_Coleman_V2.0.safetensors
大小 (KB): 36984
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success