---
license: openrail
language:
- en
tags:
- stable-diffusion
- stable-diffusion-diffusers
- stable-diffusion-xl
- lora
- diffusers
base_model: stabilityai/stable-diffusion-xl-base-1.0
datasets:
- frank-chieng/chinese_architecture_siheyuan
library_name: diffusers
inference:
  parameter:
    negative_prompt: 
widget:
- text: >-
    siheyuan, chinese traditional architecture, perfectly shaded, morning lighting, medium closeup, mystical setting, during the day
  example_title: example1 siheyuan
- text: >-
    siheyuan, chinese modern architecture, perfectly shaded, night lighting, medium closeup, mystical setting, during the day
  example_title: example2 siheyuan
pipeline_tag: text-to-image
---
## Overview

**Architecture Lora Chinese Style** is a lora training model with sdxl1.0 base model, latent text-to-image diffusion model. The model has been fine-tuned using a learning rate of `1e-5` over 3000 total steps with a batch size of 4 on a curated dataset of superior-quality chinese building style images. This model is derived from Stable Diffusion XL 1.0.

- Use it with 🧨 [`diffusers`](https://huggingface.co/docs/diffusers/index)
- Use it with the [`ComfyUI`](https://github.com/comfyanonymous/ComfyUI) **(recommended)**
- 
### Model Description

<!-- Provide a longer summary of what this model is. -->

- **Developed by:** [FrankChieng](https://github.com/frankchieng)
- **Model type:** Diffusion-based text-to-image generative model
- **License:** [CreativeML Open RAIL++-M License](https://huggingface.co/stabilityai/stable-diffusion-2/blob/main/LICENSE-MODEL)
- **Finetuned from model [optional]:** [Stable Diffusion XL 1.0 base](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0)

<hr>

## How to Use:
- Download `Lora model` [here](https://huggingface.co/frank-chieng/maggieQ/resolve/main/sdxl_lora_maggie_Q.safetensors), the model is in `.safetensors` format.
- You need to use include siheyuan prompt in natural language, then you will get realistic result image
- You can use any generic negative prompt or use the following suggested negative prompt to guide the model towards high aesthetic generationse:
```
low quality, low resolution,watermark, mark, nsfw, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username
```
- And, the following should also be prepended to prompts to get high aesthetic results:
```
masterpiece, best quality
```
<hr>

## Google Colab

[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1-9rHS6JybOsznkKRo6BlADMArUr8ctve?usp=sharing)


## 🧨 Diffusers 

Make sure to upgrade diffusers to >= 0.18.2:
```
pip install diffusers --upgrade
```

In addition make sure to install `transformers`, `safetensors`, `accelerate` as well as the invisible watermark:
```
pip install invisible_watermark transformers accelerate safetensors
```

Running the pipeline (if you don't swap the scheduler it will run with the default **EulerDiscreteScheduler** in this example we are swapping it to **EulerAncestralDiscreteScheduler**:
```py
pip install -q --upgrade diffusers invisible_watermark transformers accelerate safetensors
pip install huggingface_hub
from huggingface_hub import notebook_login
notebook_login()
import torch
from torch import autocast
from diffusers import StableDiffusionXLPipeline, EulerAncestralDiscreteScheduler

base_model_id = "stabilityai/stable-diffusion-xl-base-1.0"
lora_model = "frank-chieng/sdxl_lora_architecture_siheyuan"

pipe = StableDiffusionXLPipeline.from_pretrained(
    base_model_id,
    torch_dtype=torch.float16,
    use_safetensors=True,
    )
pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config)
pipe.load_lora_weights(lora_model, weight_name="sdxl_lora_architecture_siheyuan.safetensors")
pipe.to('cuda')
prompt = "siheyuan, chinese modern architecture, perfectly shaded, night lighting, medium closeup, mystical setting, during the day"
negative_prompt = "watermark"
image = pipe(
    prompt, 
    negative_prompt=negative_prompt, 
    width=1024,
    height=1024,
    guidance_scale=7,
    target_size=(1024,1024),
    original_size=(4096,4096),
    num_inference_steps=28
    ).images[0]
image.save("chinese_siheyuan.png")
```
<hr>

## Limitation 
This model inherit Stable Diffusion XL 1.0 [limitation](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0#limitations)