I created it for batch upscaling a dataset of images before LoRa training. It works well with characters and portraits in general, but you can use it for other purposes as well.
You can disable extra processing on the ControlPanel
There is options to restore the colors and resolution of the input image/Batch at the end of the chain.
If you reach 99% VRAM usage (assuming you have a 24GB GPU), it's most likely because your image is already large.
It's better to decrease the size of your input image instead of decreasing the scale factor of SUPIR, especially if your image is blurry or lacks sharpness and details.
But you can set the SUPIR scale factor to 0.50 instead of 0.75 for faster processing/less VRAM usage
Description
FAQ
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.