README.md

---
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
- character
- hanfu
- long hair
- asian male

base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: ylxn
widget:
- text: 'ylxn, solo, hanfu, hat, 1boy, front view, face focus, arms crossed, portrait, long hair, brown hair, large pectorals,  '
  parameters:
    negative_prompt: deformed, distorted, disfigured, low quality, blurry
            
  output:
    url: >-
      51219951.jpeg
- text: 'ylxn, solo, hanfu, hat, 1boy, sitting, long hair, brown hair, inside a living room, large pectorals,  '
  parameters:
    negative_prompt: deformed, distorted, disfigured, low quality, blurry
            
  output:
    url: >-
      51218769.jpeg
- text: 'ylxn, solo, hanfu, hat, 1boy, full body, long hair, brown hair, standing in a living room, large pectorals,  '
  parameters:
    negative_prompt: deformed, distorted, disfigured, low quality, blurry
            
  output:
    url: >-
      51218768.jpeg
- text: 'ylxn, solo, hanfu, hat, 1boy, sitting, long hair, brown hair, inside a living room, large pectorals,  '
  parameters:
    negative_prompt: deformed, distorted, disfigured, low quality, blurry
            
  output:
    url: >-
      51218771.jpeg
- text: 'ylxn, solo, hanfu, hat, 1boy, full body, long hair, brown hair, standing in a living room, large pectorals,  '
  parameters:
    negative_prompt: deformed, distorted, disfigured, low quality, blurry
            
  output:
    url: >-
      51218770.jpeg

---

# Yu Lexuan (Blue hanfu version) SDXL 

<Gallery />





## Model description

<p>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.</p>

## 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](/YuLexuan30/yu-lexuan-blue-hanfu-version-sdxl/tree/main) them in the Files & versions tab.

## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)

```py
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](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)