Skip to content

🌟 AniScale 2 & AniScale 2 Refiner

Sirosky edited this page Oct 8, 2023 · 12 revisions

Introduction

AniScale 2 is a versatile anbd faithful anime model trained for use on a variety of post ~2000 sources. As the name suggests, this is the successor to the original AniScale, and a substantial upgrade in nearly every respect. Superb blur and depth of field handling, thorough WEB and DVD compression repair, and pleasing line art refinement are the hallmarks of AniScale 2.

AniScale 2 Variants

AniScale 2 is trained first and foremost as an OmniSR model, but it is also intended to be a platform to explore multiple SISR archs. While I consider the OmniSR variant to the best starting point, the Compact variant can certainly have superior output on certain sources.

Currently, the following variants of AniScale 2 exist:

  • OmniSR: Currently, I consider this the best overall AniScale 2 variant. While nowhere near as fast as Compact, it is a good balance of speed and quality. It is superior to the Compact variant in terms of blur/DOF handling and detail retention.
  • Compact: Unsurprisingly, the Compact variant is incredibly fast. It seems to do a better job of fixing certain issues with line art compared to the OmniSR variant. While it suffers in the detail retention department compared to its bigger brother, the detail retention is still more than adequate.

AniScale Refiner

AniScale Refiner is an optional add-on model which can be used if AniScale 2's output isn't sharp enough, and also serves the following two purposes:

  • When run before AniScale 2, it'll fix help fix line art that AniScale 2 doesn't do enough work on. Example here.
  • When run after AniScale 2, it'll apply apply line thinning, though this effect will likely be lessened on newer sources. Example here.

Thus, Refiner is as the name suggests-- a lightweight model that helps with touch-up of AniScale 2's output. Note that the sharpening effect will unavoidably impact shallower blur / DOF effects. Still, it remains a helpful tool to increase the versatility of the base model.