UPDATE: Added SDXL version trained on same dataset. Much more versatile than the 1.5 version.
(Gallery images are placeholder previews generated during training so I can use the model for generation and make better ones.)
Testing Civitai's FLUX training capabilities by updating https://civarchive.com/models/183131/reina-tanakas-graduation-dress. I used the same 36 screenshots, but with new captions in natural language.
As before, the intent of the LoRA is to reproduce the outfit while allowing freedom to prompt for someone else wearing it. If no specific instructions on the appearance are given in the prompt, the subject will look like Reina Tanaka.
Description
Version 2 is probably overtrained as it's very difficult to get anyone except Reina wearing the dress. But it's very good if you want Reina to be the one wearing the dress, so I'll post it anyway.
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.