Animagine XL 3.0

Instalación recomendada:

pip install diffusers --upgrade
pip install transformers accelerate safetensors

Ejemplo de uso con Diffusers:

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

# 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-3.0",
    vae=vae,
    torch_dtype=torch.float16,
    use_safetensors=True,
)
pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config)
pipe.to('cuda')

# Define prompts and generate image
prompt = "1girl, arima kana, oshi no ko, solo, upper body, v, smile, looking at viewer, outdoors, night"
negative_prompt = "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, blurry, artist name"

image = pipe(
    prompt,
    negative_prompt=negative_prompt,
    width=832,
    height=1216,
    guidance_scale=7,
    num_inference_steps=28
).images[0]

Guía específica de prompting:

• Plantilla recomendada: 1girl/1boy, nombre del personaje, serie de origen, resto de etiquetas en cualquier orden.
• Para mejorar resultados, suele funcionar añadir masterpiece, best quality al prompt positivo.
• Para reducir artefactos y contenido no deseado, usar un prompt negativo como: 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, blurry, artist name.
• Ajustes recomendados: CFG de 5-7, menos de 30 pasos y sampler Euler a.
• Etiquetas de año permiten orientar el estilo visual: newest, late, mid, early, oldest.
• Resoluciones soportadas: 1024x1024, 1152x896, 896x1152, 1216x832, 832x1216, 1344x768, 768x1344, 1536x640, 640x1536.