style enhancer xl lora
par Linaqruf
Open source · 4k downloads · 25 likes
1.8
(25 avis)ImageAPI & LocalÀ propos
Style Enhancer XL LoRA est un modèle LoRA avancé conçu pour sublimer les images de style anime avec une qualité et un niveau de détail exceptionnels. Il s’intègre parfaitement au framework Stable Diffusion XL et permet d’affiner les générations grâce à des tags Danbooru, offrant ainsi un contrôle précis sur les styles et les détails à appliquer. Que ce soit pour des portraits expressifs, des scènes détaillées ou des ambiances spécifiques, ce modèle excelle dans l’enrichissement visuel tout en conservant la cohérence artistique. Son atout majeur réside dans sa capacité à transformer des rendus standards en œuvres maîtrisées, idéales pour les artistes et créateurs cherchant à optimiser leurs visuels. Idéal pour les projets nécessitant une touche professionnelle ou des styles variés, il se distingue par sa flexibilité et son rendu haut de gamme.
Documentation
Style Enhancer XL LoRA
|
|
|
Overview
Style Enhancer XL LoRA is an advanced, high-resolution LoRA (Low-Rank Adaptation) adapter designed to enhance the capabilities of Animagine XL 2.0. This innovative model excels in fine-tuning and refining anime-style images, producing unparalleled quality and detail. It seamlessly integrates with the Stable Diffusion XL framework, and uniquely supports Danbooru tags for precise and creative image generation.
Example tags include face focus, cute, masterpiece, best quality, 1girl, green hair, sweater, looking at viewer, upper body, beanie, outdoors, night, turtleneck.
Model Details
- Developed by: Linaqruf
- Model type: LoRA adapter for Stable Diffusion XL
- Model Description: A compact yet powerful adapter designed to augment and enhance the output of large models like Animagine XL 2.0. This adapter not only improves the style and quality of anime-themed images but also allows users to recreate the distinct 'old-school' art style of SD 1.5. It's the perfect tool for generating high-fidelity, anime-inspired visual content.
- License: CreativeML Open RAIL++-M License
- Finetuned from model: Animagine XL 2.0
🧨 Diffusers Installation
Ensure the installation of the latest diffusers library, along with other essential packages:
Bash
pip install diffusers --upgrade
pip install transformers accelerate safetensors
The following Python script demonstrates how to utilize the Style Enhancer XL LoRA with Animagine XL 2.0. The default scheduler is EulerAncestralDiscreteScheduler, but it can be explicitly defined for clarity.
Py
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")
Liens & Ressources