Downloads · 30 days
0
2xSPAN_ch48_clean
oylo-io/2xSPAN_ch48_clean
2xSPAN_ch48_clean is a machine learning model from oylo-io. 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 apache-2.0.
2× SPAN (Swift Parameter-free Attention Network) super-resolution, featurechannels=48, trained clean on DIV2K (no degradation/JPEG-compensation). Repackaged from the official hongyuanyu/SPAN release (spanx2ch48.pth),…
Access
Public
Updated Jul 13, 2026
Repo size
8.9 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors8.9 MB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Jul 13, 2026
- Updated
- Jul 13, 2026
- SHA
- 97799fd2
Model card
From the Hugging Face model README
2xSPAN_ch48_clean
2× SPAN (Swift Parameter-free Attention Network) super-resolution, feature_channels=48,
trained clean on DIV2K (no degradation/JPEG-compensation). Repackaged from the official
hongyuanyu/SPAN release (spanx2_ch48.pth), Apache-2.0.
params wrapper stripped → flat state_dict saved as .safetensors for direct loading.
Why clean (not degradation-trained): for upscaling clean VAE-decoded diffusion frames, degradation-trained SPANs (multijpg/ldl) over-smooth real texture by "correcting" compression artifacts that aren't present. The clean DIV2K variant matches-or-beats compact-pretrain sharpness.
- License
- apache-2.0
- Created
- Jul 13, 2026
- Updated
- Jul 13, 2026