Downloads · 30 days
0
anime-score-model
ntkuhn/anime-score-model
anime-score-model is a machine learning model from ntkuhn. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
A score-based generative model trained to generate 64x64 anime-style faces using Denoising Score Matching.
Access
Public
Updated Nov 20, 2025
Repo size
214 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt214 MB · 100%
At a glance
- License
- mit
- Access
- Public
- Created
- Nov 20, 2025
- Updated
- Nov 20, 2025
- SHA
- cdcd83f5
Model card
From the Hugging Face model README
Anime Face Score Matching Model
A score-based generative model trained to generate 64x64 anime-style faces using Denoising Score Matching.
Model Details
- Model type: NCSN / Score Matching
- Training data: Anime faces dataset
- Image size: 64x64 RGB
- Sigma: 0.15
- Architecture: Improved U-Net
Usage
import torch
# Load your model class definitions here
# Load the model
checkpoint = torch.load("model.pt")
model = ImprovedScoreNetwork(in_channels=3)
model.load_state_dict(checkpoint['ema_model_state_dict']) # Use EMA weights
model.eval()
# Generate samples using Langevin Dynamics
# (See sample_langevin function in training code)
- License
- mit
- Created
- Nov 20, 2025
- Updated
- Nov 20, 2025