Downloads · 30 days
8
17% of all-time downloads
SwinIR-4x-SuperResolution
itznoor998/SwinIR-4x-SuperResolution
SwinIR-4x-SuperResolution is a image-to-image model from itznoor998. Use it when you need one image transformed into another. It is set up for pytorch. The card lists the license as mit.
This repository contains a fine-tuned SwinIR model for 4x image super-resolution.
All-time downloads
48
Public
Repo size
100 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pth67.9 MB · 67%
At a glance
- Task
- Image-to-Image
- Library
- pytorch
- License
- mit
- Model type
- SwinIR
- Access
- Public
- Created
- Sep 6, 2026
- Updated
- Sep 6, 2026
- SHA
- ab5e4f22
Model card
From the Hugging Face model README
SwinIR 4x Super-Resolution
This repository contains a fine-tuned SwinIR model for 4x image super-resolution.
Model
-
Architecture: SwinIR
-
Task: Image Super-Resolution
-
Scale factor: 4x
-
Input: RGB low-resolution image
-
Output: RGB high-resolution image
Architecture
- Embed dimension: 180
- Depths: [6, 6, 6, 6, 6, 6]
- Number of heads: [6, 6, 6, 6, 6, 6]
- Window size: 8
- Upsampler: PixelShuffle
- Residual connection: 1conv
Usage
Install dependencies:
pip install torch torchvision pillow
Then:
python inference.py
Training
The model was initialized from the official SwinIR 4x classical super-resolution model and fine-tuned on the project dataset.
- Task
- Image-to-Image
- Library
- pytorch
- Type
- SwinIR
- License
- mit
- Created
- Sep 6, 2026
- Updated
- Sep 6, 2026