Annemarie Kuus (b. 1996) is a Dutch model-turned-fashion-photographer, currently based in Paris.
This embedding is based on 30 images, cooked for a total of 300 steps on base SD1.5 — 16 vectors per token, a 0.004 learning rate, a batch size of 6, and 5 gradient steps.
Description
First release.
FAQ
Comments (2)
Hey mate! Just wanted to say congrats because the TI is really good. If I may suggest something, I'd add the CLIP skip version you trained the TI with to the version details. Most people probably use CLIP skip 1 and they're gonna be missing on the real quality of this TI if they don't change it.
When I click on your name, nothing appears "No Result Found".
It's only by clicking on one of your posted images, and then on the name of the embedding (a link at the top) that I can get to this specific embedding.
Please fix that.
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.