LoRA Model Training

Training of my face with the LoRA Model (Low-Rank Adaptation), which allows you to use low-rank adaptation technology to quickly fine-tune diffusion models.

Parameters:
<lora:openjourneyLora_v1:1>| ((tarot card with intricate detailed frame around the outside)) | side profile of cyberpunk head of man <lora:Damian Lora:1> with large moon in background| cyberpunk | styled in Art Nouveau | insanely detailed | embellishments | high definition | concept art | digital art | vibrant
Negative prompt: lowres| text| error| missing fingers| extra digit| fewer digits| cropped| (worst quality| low quality:1.4)| jpeg artifacts| signature| bad anatomy| extra legs| extra arms| extra fingers| poorly drawn hands| poorly drawn feet| disfigured| out of frame| tiling| bad art| deformed| mutated| blurry| fuzzy| misshaped| mutant| gross| disgusting| ugly| watermark| watermarks
Steps: 75, Sampler: Euler a, CFG scale: 3, Seed: 193115319, Size: 512×512, Model hash: e1441589a6, Model: v1-5-pruned, Version: v1.2.1

Share the Post: