Post #2623585
2025-12-19 20:41 UTC
Upscalers usually don't have context for text or smaller graphics, so the patches don't look much better. Hopefully OP can provide a better source.
Replies (2)
-
@Draupnir@lemmy.world 2025-12-20 05:45
Yeah that’s fine, but by doing so someone else will have an easier time recognizing the image or matching the details to their memory
-
@howrar@lemmy.ca 2025-12-20 14:52
If the upscaler was trained on data that contains that exact patch in other contexts, it'll theoretically be capable of upscaling it properly.