Ready to leverage your Real-ESRGAN-Anime-finetuning model for breathtaking anime image upscaling based on Real-ESRGAN_x4Plus?

#17
by danhtran2mind - opened

Overview 🌟

Real-ESRGAN-Anime-finetuning, built upon Real-ESRGAN_x4Plus, is optimized for high-quality anime image upscaling, delivering superior clarity and consistency! πŸš€

Performance Comparison πŸ“Š

Model Name Mean↑ Std Deviation↓
RealESRGAN_x4plus 36.8437 3.4551
Real-ESRGAN-Anime-finetuning 36.8695 πŸ† 3.3193 πŸŽ‰

PSNR Results πŸ“ˆ

Input File Upscale Factor Real-ESRGAN-Anime-finetuning RealESRGAN_x4plus_anime_6B
_resized_div_2.png 2 27.65 dB 🌟 26.01 dB
_resized_div_4.png 4 24.46 dB 🌟 23.07 dB

Requirements πŸ”§

This model is based on Real-ESRGAN_x4Plus and requires its architecture for optimal performance. Ensure you have the necessary dependencies for Real-ESRGAN_x4Plus. πŸ› οΈ

Usage πŸ–ΌοΈ

1. Download Model πŸ“₯

Get the model from:

https://huggingface.co/danhtran2mind/Real-ESRGAN-Anime-finetuning/resolve/main/Real-ESRGAN-Anime-finetuning.pth

2. Install stablepy πŸ“¦

pip install stablepy

3. Run Inference πŸ’»

from PIL import Image
from stablepy import load_upscaler_model

scaler = load_upscaler_model(
    model="./Real-ESRGAN-Anime-finetuning.pth",
    tile=0, 
    tile_overlap=8,
    device="cuda",
    half=True
)

image = Image.open("<your_image_path>").convert("RGB")
upscaled = scaler.upscale(image, 4)
upscaled

Why This Model? 🀩

  • Based on Real-ESRGAN_x4Plus: Leverages a proven architecture for anime optimization. πŸ–ŒοΈ
  • Top Metrics: Higher quality and consistency. πŸ“‰
  • Easy Integration: Seamless use with stablepy. πŸ”—

Upscale your anime images with this enhanced model! 🌈✨

Sign up or log in to comment