Tokyo Street Fashion Style XL

This SDXL LoRA is inspired by the street fashion popular around Tokyo, particularly around Harajuku, Shinjuku, Shibuya and Ginza.

Trained on a synthetic dataset of 50 images I generated with AAM XL and touched up with some light inpainting to improve details and fix imperfections.

I recommend using the AAM XL checkpoint with it, see the suggested resources.

Around 1 weight, Trigger should be tokyo_street_fashion_xl

Other prominent tags in the training data that I reccomend: chic, goth, parted lips, long sleeves, makeup, multicolored hair, print shirt, shiny jacket, tinted eyewear

This LoRA took a bit longer to create, being a bit more careful about the images chosen and tagging. If you enjoyed it please consider leaving a like and a review!

How to use LoRA's in auto1111 (Guide courtesy of Lycon):

• Update webui (use git pull like here or redownload it)

• Copy the file to stable-diffusion-webui/models/lora

• Select your LoRA like in this video

• Make sure to change the weight (by default it's :1 which is usually too high)

描述:

训练词语: