Anime Detailer Xl Lora

🚀 Anime Detailer XL LoRA

Anime Detailer XL LoRA是一款先进的LoRA适配器，可与Animagine XL 2.0配合使用。它专注于概念调制，能让用户调整生成的动漫风格图像的细节程度，通过操作概念滑块，用户可以创建从高度细节到更抽象表现的图像。

🚀 快速开始

安装依赖

确保安装最新的 diffusers 库以及其他必要的包：

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LoRA与Animagine XL 2.0结合使用。默认调度器为 EulerAncestralDiscreteScheduler，为清晰起见，也可显式定义。

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

# Initialize LoRA model and weights
lora_model_id = "Linaqruf/anime-detailer-xl-lora"
lora_filename = "anime-detailer-xl.safetensors"
lora_scale_slider = 2 # -2 for less detailed result

# 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=lora_scale_slider)

# 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

Anime Detailer XL LoRA是一款前沿的LoRA适配器，专为与Animagine XL 2.0协同工作而设计。该独特模型专注于概念调制，使用户能够调整生成的动漫风格图像的细节程度。通过操作概念滑块，用户可以创建从高度详细到更抽象表现的图像。

📦 安装指南

确保安装最新的 diffusers 库以及其他必要的包：

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/anime-detailer-xl-lora"
lora_filename = "anime-detailer-xl.safetensors"
lora_scale_slider = 2 # -2 for less detailed result

# 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=lora_scale_slider)

# 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

🔧 技术细节

Anime Detailer XL LoRA作为一个LoRA适配器，与Animagine XL 2.0结合使用，通过概念调制来控制生成的动漫图像的细节程度。它利用了 diffusers 库中的 StableDiffusionXLPipeline 进行图像生成，同时使用 EulerAncestralDiscreteScheduler 作为调度器。在代码实现中，首先加载VAE组件，然后配置管道，接着加载并融合LoRA权重，最后根据定义的提示生成图像。在保存图像之前，需要解除LoRA的融合。

📄 许可证

本项目采用 CreativeML Open RAIL++-M License 许可证。

致谢

我们的项目受益于以下重要工作：

• Erasing Concepts from Diffusion Models 作者：Rohit Gandikota等人
• LECO 作者：p1atdev
• AI Toolkit 作者：Ostris