license: other
license_name: bespoke-lora-trained-license
license_link: >-
https://multimodal.art/civitai-licenses?allowNoCredit=True&allowCommercialUse=Image&allowDerivatives=True&allowDifferentLicense=True
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
- migrated
- celebrity
- chinese boy
- yu lexuan
- 雨乐暄
- dorama
- bi wenjun
- 漂亮书生
- in a class of her own
- sdxl 1,0
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: yulexuan
widget:
- text: >-
yulexuan, fashion magazine cover with bold text saying "YU LEXUAN",
cinematic photo, sexy pose, face focus, upper body shot, young muscular
asian male with long hair and big pectorals, inside a studio, wearing
blue hanfu made of cotton, best quality, wide hips, small coronet made of
fabric on his head, 35mm photograph, film, bokeh, professional, 4k, highly
detailed,
parameters:
negative_prompt: >-
black background, drawing, painting, crayon, bad anatomy, sketch,
graphite, impressionist, noisy, blurry, soft, deformed, ugly
output:
url: 13596565.jpeg
- text: >-
disaster, ground level shot, muscular yulexuan with long hair and wide
hips wearing muddy dirty hanfu small coronet made of fabric on his head,
sad face, inside a heavily damaged Chinese temple room with broken doors
and broken windows whose furniture is covered by mud, cinematic, perfect
hands,
parameters:
negative_prompt: >-
bad quality, bad anatomy, worst quality, low quality, low resolutions,
extra fingers, blur, blurry, wrong proportions, watermark, image
artifacts, lowres, jpeg artifacts, deformed, noisy image
output:
url: 13596613.jpeg
- text: >-
adult magazine cover with bold text saying "YU LEXUAN", playboy,
yulexuan, cinematic photo, sexy pose, face focus, upper body shot, young
muscular asian male with long hair and big pectorals, inside a studio,
wearing blue hanfu made of cotton, best quality, wide hips, small
coronet made of fabric on his head, 35mm photograph, film, bokeh,
professional, 4k, highly detailed,
parameters:
negative_prompt: >-
black background, drawing, painting, crayon, bad anatomy, sketch,
graphite, impressionist, noisy, blurry, soft, deformed, ugly
output:
url: 13596659.jpeg
- text: >-
view from the ground up, ground level shot, ground camera angle,
wide-angle, yulexuan asian male with long hair wearing soiled blue hanfu
and a small coronet made of fabric looking at the sun, best quality, very
detailed, hd ,
parameters:
negative_prompt: >-
bad quality, bad anatomy, worst quality, low quality, low resolutions,
extra fingers, blur, blurry, wrong proportions, watermark, image
artifacts, lowres, jpeg artifacts, deformed, noisy image
output:
url: 13596707.jpeg
SDXL - "In a class of her Own" - Yu Lexuan / 漂亮书生 《雨乐暄》
- Prompt
- yulexuan, fashion magazine cover with bold text saying "YU LEXUAN", cinematic photo, sexy pose, face focus, upper body shot, young muscular asian male with long hair and big pectorals, inside a studio, wearing blue hanfu made of cotton, best quality, wide hips, small coronet made of fabric on his head, 35mm photograph, film, bokeh, professional, 4k, highly detailed,
- Negative Prompt
- black background, drawing, painting, crayon, bad anatomy, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly
- Prompt
- disaster, ground level shot, muscular yulexuan with long hair and wide hips wearing muddy dirty hanfu small coronet made of fabric on his head, sad face, inside a heavily damaged Chinese temple room with broken doors and broken windows whose furniture is covered by mud, cinematic, perfect hands,
- Negative Prompt
- bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, wrong proportions, watermark, image artifacts, lowres, jpeg artifacts, deformed, noisy image
- Prompt
- adult magazine cover with bold text saying "YU LEXUAN", playboy, yulexuan, cinematic photo, sexy pose, face focus, upper body shot, young muscular asian male with long hair and big pectorals, inside a studio, wearing blue hanfu made of cotton, best quality, wide hips, small coronet made of fabric on his head, 35mm photograph, film, bokeh, professional, 4k, highly detailed,
- Negative Prompt
- black background, drawing, painting, crayon, bad anatomy, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly
- Prompt
- view from the ground up, ground level shot, ground camera angle, wide-angle, yulexuan asian male with long hair wearing soiled blue hanfu and a small coronet made of fabric looking at the sun, best quality, very detailed, hd ,
- Negative Prompt
- bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, wrong proportions, watermark, image artifacts, lowres, jpeg artifacts, deformed, noisy image
Model description
In a Class of Her Own is a 2020 Chinese television series starring Ju Jingyi, Song Weilong, Bi Wenjun and Wang Ruichang. The series premiered on iQiyi with multi-languages subtitles globally on July 23, 2020.
Also check the SD1.5 model (768x768)
This highly experimental model was trained in a small dataset of only 11 high-quality images. A new version with at least 60 images is being refined. The v1.5 model offers more flexibility.
Usage tips:
♦The activation tag is just "yulexuan', if you can't get a good likeness of him, "asian male", "wearing a small coronet made of fabric" and "wearing blue hanfu" also work.
♦Set clip skip to 1.
♦Include "transparent background" and "black background" in the negative prompt. An error while cleaning the PNGs passed these attributes to the AI and it will show up if lora strength is above 0,7.
♦Resolution of 1024 x 1024, 1024 x 768 or near is also fine as these were the resolutions used for training.
♦LoRa strength can be anywhere from 0.3 to 1. Best results seem to be at 0.6 to 0.8 depending on model.
♦It works best on vanilla SDXL and Realistic Vision XL. Good results on OpenDall-e as well.
♦Use ADetailer instead of face restoration.
♦It has been trained using the base SDXL 1.0 model, so it should be compatible with all checkpoints. This is a photorealistic model, and won't work on Pony.
This model is not filtered and may produce NSFW.
Description
This is the SDXL LoRa version of my first checkpoint ever trained, Yu Lexuan:
This Lora has been optimized to reproduce his most recognizable clothing, a nice blue hanfu. It does a much better job than the checkpoint.
This SDXL version uses a reduced dataset with just 11 high-quality images scrapped from Weibo. I have close to 100 images with varied quality.
Trigger words
You should use yulexuan to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
Use it with the 🧨 diffusers library
from diffusers import AutoPipelineForText2Image
import torch
device = "cuda" if torch.cuda.is_available() else "cpu"
pipeline = AutoPipelineForText2Image.from_pretrained('stabilityai/stable-diffusion-xl-base-1.0', torch_dtype=torch.float16).to(device)
pipeline.load_lora_weights('YuLexuan30/sdxl-in-a-class-of-her-own-yu-lexuan-piao-liang-shu-sheng-yu-le-xuan', weight_name='YuLexuanSDXL3.safetensors')
image = pipeline('view from the ground up, ground level shot, ground camera angle, wide-angle, yulexuan asian male with long hair wearing soiled blue hanfu and a small coronet made of fabric looking at the sun, best quality, very detailed, hd , ').images[0]
For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers