Style Enhancer XL LoRA

Asegúrese de instalar la biblioteca de diffusers más reciente, junto con otros paquetes esenciales:sh pip install diffusers --upgrade pip install transformers accelerate safetensors El siguiente script de Python muestra cómo utilizar Style Enhancer XL LoRA con Animagine XL 2.0. El scheduler predeterminado es EulerAncestralDiscreteScheduler, pero se puede definir explícitamente para mayor claridad.

import torch
from diffusers import (
StableDiffusionXLPipeline, 
EulerAncestralDiscreteScheduler,
AutoencoderKL
)
# Inicializar modelo LoRA y pesos
lora_model_id = "Linaqruf/style-enhancer-xl-lora"
lora_filename = "style-enhancer-xl.safetensors"
# Cargar componente VAE
vae = AutoencoderKL.from_pretrained(
"madebyollin/sdxl-vae-fp16-fix", 
torch_dtype=torch.float16
)
# Configurar el 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')
# Cargar y fusionar pesos LoRA
pipe.load_lora_weights(lora_model_id, weight_name=lora_filename)
pipe.fuse_lora(lora_scale=0.6)
# Definir prompts y generar imagen
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]
# Desfusionar LoRA antes de guardar la imagen
pipe.unfuse_lora()
image.save("anime_girl.png")```