Original Character by Crydiaa https://twitter.com/Crydiaa
Trained quick n' dirty using different images uploaded to twitter and frames from the increasingly popular YouTube video:
I tried tagging twitter pics and youtube frames. Since YouTube frames are really similar, some features (background, spikes, jacket) may show up without being tagged. So make sure to use negatives.
I've trained 25 epochs, but later epochs are kinda burnt... If you want to try some, just ask me in the comments.
Description
Same dataset + a few new images. New set of tags though.
Fewer YT-Vid images. No longer recommend using the yt-vid tag though. The quality drop is too big for my liking.
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.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.