README.md

---
license: other
license_name: bespoke-lora-trained-license
license_link: https://multimodal.art/civitai-licenses?allowNoCredit=True&allowCommercialUse=Rent&allowDerivatives=True&allowDifferentLicense=True
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
- style
- lego
- toy
- brickheadz
- minifigures

base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: LEGO MiniFig
widget:
- text: ' '
  output:
    url: >-
      6016204.jpeg
- text: '
LEGO MiniFig, A man in a vintage early-20th-century setting, possibly from a period film, stands prominently in the foreground. He wears a dark grey suit, a light blue shirt, a darker blue tie, and a classic fedora hat, conveying an aura of authority and composure. His face shows determination, with sharp features, short dark hair, and an intense gaze. The badge labeled ''K-6'' on his lapel suggests he might have an official or investigative role. The background is an open, dusty street typical of an old western town at dusk, with wooden buildings lining the side and a few people in period attire visible in the distance. The lighting is soft and golden, indicative of a setting sun, giving a cinematic quality to the scene.'
  output:
    url: >-
      6015806.jpeg
- text: '
LEGO Creator,  The Space Needle in seattle city view'
  output:
    url: >-
      6015809.jpeg
- text: '
LEGO MiniFig. 
A woman with platinum blonde hair exudes Barbie doll charm in a pink cowgirl outfit with a matching hat, her joyful stance enhancing the doll-like atmosphere around her'
  output:
    url: >-
      6015819.jpeg
- text: '
LEGO BrickHeadz, a red chinese dragon in a lunar new year'
  output:
    url: >-
      6015841.jpeg
- text: ' LEGO Creator,
Chinese traditional lion dance, on the street in the early morning'
  output:
    url: >-
      6015843.jpeg
- text: '
LEGO MiniFig. 
A man with curly hair and a whimsical expression wears a velvet top hat and red coat amidst a colorful, dreamlike backdrop'
  output:
    url: >-
      6015846.jpeg
- text: ' LEGO BrickHeadz,
In a field of golden wheat, a large doll with black short hair wears a yellow short-sleeve shirt topped with an orange suspender dress. White knee-high socks and black shoes adorn its feet, under a bare tree.'
  output:
    url: >-
      6015849.jpeg
- text: '
LEGO MiniFig. 
A man with platinum blonde hair and an athletic build wears a luxurious white fur coat over bare chest, accessorized with a headband and necklace, in a vibrant, stylized setting.'
  output:
    url: >-
      6015860.jpeg
- text: ' LEGO BrickHeadz,
In a field of golden wheat, a large doll with black short hair wears a yellow short-sleeve shirt topped with an orange suspender dress. White knee-high socks and black shoes adorn its feet, under a bare tree.'
  output:
    url: >-
      6016479.jpeg

---

# LeLo - LEGO LoRA for XL & SD1.5 

<Gallery />





## Model description

<p><strong>LeLo</strong> stands for <strong>LEGO LoRA</strong>. It is a LoRA trained with over 900 images from the LEGO MiniFigures, BrickHeadz, and Creator themes. It provides a simulation of the LEGO design style.</p><p></p><p><strong><em>Update:</em></strong></p><p>The <strong><u>V2.1_SDXL1.0</u></strong> version expands the training image dataset to 893 high-resolution images, further enhancing the model's drawing quality. Starting from this version, I will no longer provide updates for the corresponding SD1.5 version.</p><p>This version is released to celebrate the Lunar Year of the Dragon. Wishing everyone a happy holiday and prosperous fortune!</p><p></p><p><strong><em>Usage:</em></strong></p><p><span style="color:rgb(253, 126, 20)">Trigger words:</span></p><ul><li><p><strong><u>LEGO MiniFig, {prompt}</u></strong>: MiniFigures theme, suitable for human figures and anthropomorphic animal images.</p></li><li><p><strong><u>LEGO BrickHeadz, {prompt}</u></strong>: BrickHeadz theme, suitable for human figures and anthropomorphic animal images.</p></li><li><p><strong><u>LEGO Creator, {prompt}</u></strong>: Creator theme, widely applicable to objects, animals, plants, buildings, etc.</p></li></ul><p><span style="color:rgb(253, 126, 20)">LoRA Weight: </span>Between 0.6-1.0, recommended to use <strong><u>0.8</u></strong>.</p><p><span style="color:rgb(253, 126, 20)">Denoising: </span>Recommended to use <strong><u>0.3</u></strong>.</p><p><span style="color:rgb(253, 126, 20)">Base model: </span>The <strong><u>V2.1_SDXL1.0</u></strong> version should be paired with the SDXL 1.0 series base models. For the SD 1.5 versions, it is recommended to use it in conjunction with the <strong><u>Realistic Vision</u></strong> series base models, but you can also try pairing it with other base models to explore different styles.</p><p></p><p>If you are interested in my other works, please visit my personal website at <a target="_blank" rel="ugc" href="https://ai.chao.cool">https://ai.chao.cool</a>. There, I have listed my main achievements in Stable Diffusion LoRA and GPTs of ChatGPT.</p><hr /><p><strong>LeLo</strong> 为 <strong>LEGO LoRA</strong> 简称。此 LoRA 模型使用了 900 多张 LEGO MiniFigures 系列，BrickHeadz 系列，和 Creator 系列产品图片训练而成，提供对乐高设计风格的模拟。</p><p></p><p><strong><em>更新说明：</em></strong></p><p><strong><u>V2.1_SDXL1.0</u></strong> 版扩充训练图像数据集至893张高分辨图片，进一步提升模型绘图质量。从这个版本开始，我将不再提供对应的 SD1.5 版本更新。</p><p>此版本为庆祝农历龙年新年而发布，祝大家节日快乐，恭喜发财！</p><p></p><p><strong><em>使用方法：</em></strong></p><p><span style="color:rgb(253, 126, 20)">触发词(Trigger words)：</span></p><ul><li><p><strong><u>LEGO MiniFig, {prompt}</u></strong>：人仔风格，适用于人物形象和拟人的动物形象。</p></li><li><p><strong><u>LEGO BrickHeadz, {prompt}</u></strong>：方头仔风格，适用于人物形象和拟人的动物形象。</p></li><li><p><strong><u>LEGO Creator, {prompt}</u></strong>： 乐高创意系列风格，广泛适用于物品、动物、植物、建筑等。</p></li></ul><p><span style="color:rgb(253, 126, 20)">LoRA 权重(weight)：</span>0.6-1.0 之间，推荐使用 <strong><u>0.8</u></strong></p><p><span style="color:rgb(253, 126, 20)">放大重绘幅度(Denoising)：</span>推荐使用 <strong><u>0.3</u></strong></p><p><span style="color:rgb(253, 126, 20)">基础模型：</span><strong><u>V2.1_SDXL1.0</u></strong> 版请配合 SDXL 1.0 系列基础模型。SD 1.5 版本推荐与 <strong><u>Realistic Vision</u></strong> 系列基础模型配合使用，也可尝试与其他基础模型配合使用以探索不同的风格。</p><p></p><p>如果你的我其他作品感兴趣，请移步我的个人网站（<a target="_blank" rel="ugc" href="https://ai.chao.cool/zh-cn/">https://ai.chao.cool/zh-cn/</a>）。在那里列出了我在 Stable Diffusion LoRA 以及 ChatGPT 定制化 GPTs 方面的主要工作成果。</p>

## Trigger words
You should use `LEGO MiniFig`, `LEGO Creator`, `LEGO BrickHeadz` to trigger the image generation.
    

## Download model

Weights for this model are available in Safetensors format.

[Download](/lordjia/lelo-lego-lora-for-xl-sd1-5/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

pipeline = AutoPipelineForText2Image.from_pretrained('stabilityai/stable-diffusion-xl-base-1.0', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('lordjia/lelo-lego-lora-for-xl-sd1-5', weight_name='Lego_XL_v2.1.safetensors')
image = pipeline(' LEGO BrickHeadz,
In a field of golden wheat, a large doll with black short hair wears a yellow short-sleeve shirt topped with an orange suspender dress. White knee-high socks and black shoes adorn its feet, under a bare tree.').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)