Oopeve is a young Thai model.
This LoRa was only trained on the face, which unfortunately makes it a bit difficult to produce full-body shots. The weight should be between 0.8 - 1.0.
The training set consists of 90 high-resolution facial photos (close-up). The background has been removed from all photos. The captioning was done with WD14 Captioning.
I think that LoRa delivers good results in the portrait area, but is otherwise not very flexible. I will therefore create another LoRa, which will also be trained with portrait and full body photos.
Description
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.