🚀 Style Enhancer XL LoRA

Style Enhancer XL LoRA 是一款先进的高分辨率 LoRA（低秩自适应）适配器，旨在增强 Animagine XL 2.0 的功能。该创新模型在微调与优化动漫风格图像方面表现出色，能够生成无与伦比的高质量和细节丰富的图像。它可以无缝集成到 Stable Diffusion XL 框架中，并且独特地支持 Danbooru 标签，以实现精准而富有创意的图像生成。

🚀 快速开始

安装依赖

确保安装最新的 diffusers 库以及其他必要的软件包：

pip install diffusers --upgrade
pip install transformers accelerate safetensors

运行示例代码

以下 Python 脚本展示了如何将 Style Enhancer XL LoRA 与 Animagine XL 2.0 结合使用。默认调度器是 EulerAncestralDiscreteScheduler，但为了清晰起见，可以显式定义。

import torch
from diffusers import (
    StableDiffusionXLPipeline, 
    EulerAncestralDiscreteScheduler,
    AutoencoderKL
)

# Initialize LoRA model and weights
lora_model_id = "Linaqruf/style-enhancer-xl-lora"
lora_filename = "style-enhancer-xl.safetensors"

# Load VAE component
vae = AutoencoderKL.from_pretrained(
    "madebyollin/sdxl-vae-fp16-fix", 
    torch_dtype=torch.float16
)

# Configure the pipeline
pipe = StableDiffusionXLPipeline.from_pretrained(
    "Linaqruf/animagine-xl-2.0", 
    vae=vae,
    torch_dtype=torch.float16, 
    use_safetensors=True, 
    variant="fp16"
)
pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config)
pipe.to('cuda')

# Load and fuse LoRA weights
pipe.load_lora_weights(lora_model_id, weight_name=lora_filename)
pipe.fuse_lora(lora_scale=0.6)

# Define prompts and generate image
prompt = "face focus, cute, masterpiece, best quality, 1girl, green hair, sweater, looking at viewer, upper body, beanie, outdoors, night, turtleneck"
negative_prompt = "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, blurry"

image = pipe(
    prompt, 
    negative_prompt=negative_prompt, 
    width=1024,
    height=1024,
    guidance_scale=12,
    num_inference_steps=50
).images[0]

# Unfuse LoRA before saving the image
pipe.unfuse_lora()
image.save("anime_girl.png")

✨ 主要特性

• 专为增强 Animagine XL 2.0 功能而设计，在微调与优化动漫风格图像方面表现卓越。
• 无缝集成到 Stable Diffusion XL 框架中。
• 独特支持 Danbooru 标签，实现精准且富有创意的图像生成。
• 可帮助用户重现 SD 1.5 的独特“复古”艺术风格。

📦 安装指南

确保安装最新的 diffusers 库以及其他必要的软件包：

pip install diffusers --upgrade
pip install transformers accelerate safetensors

💻 使用示例

基础用法

import torch
from diffusers import (
    StableDiffusionXLPipeline, 
    EulerAncestralDiscreteScheduler,
    AutoencoderKL
)

# Initialize LoRA model and weights
lora_model_id = "Linaqruf/style-enhancer-xl-lora"
lora_filename = "style-enhancer-xl.safetensors"

# Load VAE component
vae = AutoencoderKL.from_pretrained(
    "madebyollin/sdxl-vae-fp16-fix", 
    torch_dtype=torch.float16
)

# Configure the pipeline
pipe = StableDiffusionXLPipeline.from_pretrained(
    "Linaqruf/animagine-xl-2.0", 
    vae=vae,
    torch_dtype=torch.float16, 
    use_safetensors=True, 
    variant="fp16"
)
pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config)
pipe.to('cuda')

# Load and fuse LoRA weights
pipe.load_lora_weights(lora_model_id, weight_name=lora_filename)
pipe.fuse_lora(lora_scale=0.6)

# Define prompts and generate image
prompt = "face focus, cute, masterpiece, best quality, 1girl, green hair, sweater, looking at viewer, upper body, beanie, outdoors, night, turtleneck"
negative_prompt = "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, blurry"

image = pipe(
    prompt, 
    negative_prompt=negative_prompt, 
    width=1024,
    height=1024,
    guidance_scale=12,
    num_inference_steps=50
).images[0]

# Unfuse LoRA before saving the image
pipe.unfuse_lora()
image.save("anime_girl.png")

📚 详细文档

模型详情

📄 许可证

本项目采用 CreativeML Open RAIL++-M 许可证。