from pixiv みのり
v2.0 added : trained using only his recent images (not overlap with v1.0)
vpred ver added :
left: IL ver , Right : vpred ver
Description
FAQ
Comments (3)
Looks good, definitely going to give it a whirl later, How do you make the seperate Versions of the same post but with a more up to date style. Trying to do it myself for some of my styles but haven't the faintest on how its done correctly.
The v1.0 datasets consisted of images up to March. So, I trained v2.0 using only his latest images from now until April. This was possible because he is an AI creator. I was able to collect many images (more than 100) in a short period of time. If there had not been enough images, I would have added to the existing datasets for training.
Great model. Their inactivity pushed me to experiment with generation for the first time, much thanks~
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.