Aller au contenu
ModelPrésentéExterne
Télécharger

Sprite Dx Anti Corruption v1

Pixel art restoration model that performs both quantization (denoising/sharpening) and optional background matting.

TypeOtherVersionRevision b195cbfBClasse

Source du modèle

Type
Other
Taille du fichier
50,8 MB
Version
vRevision b195cbf
Mis à jour
20 oct. 2026
Téléchargements
17
Source
Hugging Face

Description de la source

SpriteDX Anti-Corruption Model v1.1.3

Pixel art restoration model that performs both quantization (denoising/sharpening) and optional background matting.

Model Description

  • Architecture: U-Net with residual connections
  • Input: 128x128 RGBA (4 channels)
  • Output: 128x128 RGBA (4 channels)
  • Training: Mixed dataset strategy with 50/50 split between:
    • Background matting task (composited images)
    • Quantization task (transparent images)

Capabilities

  1. Pixel Art Quantization: Removes blur, noise, and interpolation artifacts
  2. Background Matting: Extracts transparency from composited images
  3. Unified Processing: Handles both tasks in a single forward pass

Usage

import torch
from PIL import Image
import numpy as np

# Load model (you'll need the model architecture from train_v1.1.3.py)
from train_v1_1_1 import AntiCorruptionUNet

model = AntiCorruptionUNet()
checkpoint = torch.load("model.safetensors")
model.load_state_dict(checkpoint)
model.eval()

# Process image
image = Image.open("input.png").convert("RGBA")
image_tensor = torch.from_numpy(
    np.array(image, dtype=np.float32).transpose(2, 0, 1) / 255.0
).unsqueeze(0)

with torch.no_grad():
    output = model(image_tensor)
    output = model.post_process(output)

# Convert back to PIL
output_np = output[0].permute(1, 2, 0).numpy()
output_np = np.clip(output_np * 255, 0, 255).astype(np.uint8)
output_image = Image.fromarray(output_np, mode='RGBA')

Training Details

  • Corruption pipeline: nearest neighbor upscaling → noise → blur → translation → bicubic downscaling
  • Loss: Weighted RGB + Alpha loss with contrast and whiteness weighting
  • Data augmentation: Color shifts, flips, grayscale conversion

Limitations

  • Input must be 128x128 pixels
  • Best results on pixel art and sprites
  • May struggle with very complex transparency patterns

License

MIT

Sources

1 source
Hugging FacePrincipalVersion b195cbf860da17e0fbdf29649b07e862fcfafa3a
huggingface.co/sprited/sprite-dx-anti-corruption-v1/tree/b195cbf860da17e0fbdf29649b07e862fcfafa3a

Vérifié 20 oct.

Artefacts du modèle

1 artefact

model.safetensors

safetensors · 50,8 MB · SHA-256 f46cfe7025d6…aebb · Hugging Face

Download file

Extraits de sources

3 extraits

--- license: mit tags: - image-to-image - pixel-art - sprite - background-removal - quantization --- # SpriteDX Anti-Corruption Model v1.1.3 Pixel art restoration model that performs both quantization (denoising/sharpening) and optional background matting. ## Model Description - **Architecture**: U-Net with residual connections - **Input**: 128x128 RGBA (4 channels) - **Output**: 128x128 RGBA (4 channels) - **Training**: Mixed dataset strategy with 50/50 split between: - Background matting task (composited images) - Quantization task (transparent images) ## Capabilities 1. **Pixel Art Quantization**: Removes blur, noise, and interpolation artifacts 2. **Background Matting**: Extracts transparency from composited images 3. **Unified Processing**: Handles both tasks in a single forward pass ## Usage ```python import torch from PIL import Image import numpy as np # Load model (you'll need the model architecture from train_v1.1.3.py) from train_v1_1_1 import AntiCorruptionUNet model = AntiCorruptionUNet() checkpoint = torch.load("model.safetensors") model.load_state_dict(checkpoint) model.eval() # Process image image = Image.open("input.png").convert("RGBA") image_tensor = torch.from_numpy( np.array(image, dtype=np.float32).transpose(2, 0, 1) / 255.0 ).unsqueeze(0) with torch.no_grad(): output = model(image_tensor) output = model.post_process(output) # Convert back to PIL output_np = output[0].permute(1, 2, 0).numpy() output_np = np.clip(output_np * 255, 0, 255).astype(np.uint8) output_image = Image.fromarray(output_np, mode='RGBA') ``` ## Training Details - Corruption pipeline: nearest neighbor upscaling → noise → blur → translation → bicubic downscaling - Loss: Weighted RGB + Alpha loss with contrast and whiteness weighting - Data augmentation: Color shifts, flips, grayscale conversion ## Limitations - Input must be 128x128 pixels - Best results on pixel art and sprites - May struggle with very complex transparency patterns ## License MIT

Source context: 17 downloads · 1 likes · Pipeline image-to-image · Repo sprited/sprite-dx-anti-corruption-v1

Source context: 8 downloads · 1 likes · Pipeline image-to-image · Repo sprited/sprite-dx-anti-corruption-v1