Artscale (SuperResV13) is a 2× EDSR-style super-resolution network (256 channels, 64 residual channel-attention blocks, ICNR PixelShuffle head) with a fixed, phase-correct Lanczos-3 baseline added at the output. It was trained to restore lightly degraded art-site images (ArtStation / X / DeviantArt artifacts, mild under-sizing) to 2× without hallucinating texture. Three files are provided:

  1. The original (SuperResV13), trained on 100,000 source resolution image tiles for 80 epochs.
  2. The finetune (SuperResV13FT), trained on an additional 200,000 source resolution image tiles for an additional 10 epochs.
  3. The ComfyUI custom node zip, containing the necessary inference and tiling code.
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support