Downloads · 30 days
0
INT8_2_INT16_EdgeAware
Felldude/INT8_2_INT16_EdgeAware
INT8_2_INT16_EdgeAware is a image-to-image model from Felldude. Use it when you need one image transformed into another. The card lists the license as cc-by-nc-nd-4.0.
This model reconstructs 16‑bit per channel images from standard 8‑bit input images. It is trained on paired 8‑bit and 16‑bit data and optimized to preserve color fidelity and high‑frequency detail.
Access
Public
Updated Mar 28, 2026
Parameters
890K
3.6 MB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors3.6 MB · 100%
At a glance
- Task
- Image-to-Image
- License
- cc-by-nc-nd-4.0
- Access
- Public
- Created
- Mar 28, 2026
- Updated
- Mar 28, 2026
- SHA
- 3329f668
Datasets
Model card
From the Hugging Face model README
16bit-from-8bit Image Reconstruction Model
This model reconstructs 16‑bit per channel images from standard 8‑bit input images. It is trained on paired 8‑bit and 16‑bit data and optimized to preserve color fidelity and high‑frequency detail.
Dataset
-
Total images: 54,580
- RAW patch images: 46,000 (~10 GB)
- 48‑bit synthetic images: 8,580 (~2 GB)
-
Edge Aware has hand selected 1,975 patches.
Evaluation Summary
| MAE is increased from base model, however edge aware training increased sharpness in many cases. Both Entropy and Edge Density has incresed vs. simply scaling 8bit images to 16bit.
Intended Use
Primary Use Cases
- Reconstruction of 16‑bit per channel images from 8‑bit input.
- HDR post‑processing and enhancement.
- Archival and art restoration workflows.
Not Intended For
- Lossless scientific measurement or precision tasks.
- Task
- Image-to-Image
- License
- cc-by-nc-nd-4.0
- Languages
- en
- Created
- Mar 28, 2026
- Updated
- Mar 28, 2026