YuLexuan30/yu-lexuan-blue-hanfu-version-sdxl

Yu Lexuan (Blue hanfu version) SDXL

Prompt

ylxn, solo, hanfu, hat, 1boy, front view, face focus, arms crossed, portrait, long hair, brown hair, large pectorals,

Negative Prompt

deformed, distorted, disfigured, low quality, blurry

Prompt

ylxn, solo, hanfu, hat, 1boy, sitting, long hair, brown hair, inside a living room, large pectorals,

Negative Prompt

deformed, distorted, disfigured, low quality, blurry

Prompt

ylxn, solo, hanfu, hat, 1boy, full body, long hair, brown hair, standing in a living room, large pectorals,

Negative Prompt

deformed, distorted, disfigured, low quality, blurry

Prompt

ylxn, solo, hanfu, hat, 1boy, sitting, long hair, brown hair, inside a living room, large pectorals,

Negative Prompt

deformed, distorted, disfigured, low quality, blurry

Prompt

ylxn, solo, hanfu, hat, 1boy, full body, long hair, brown hair, standing in a living room, large pectorals,

Negative Prompt

deformed, distorted, disfigured, low quality, blurry

Model description

This is the SDXL version of my previous SD 1.5 model, with an improved dataset and better tagging. The old version has been removed.

Trigger words

You should use ylxn, hanfu, hat 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/yu-lexuan-blue-hanfu-version-sdxl', weight_name='YulexuansdxlV6civit.safetensors')
image = pipeline('ylxn, solo, hanfu, hat, 1boy, full body, long hair, brown hair, standing in a living room, large pectorals,  ').images[0]

For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers