This lora was made with only ONE high definition image as a dataset. (240 repeats/10 epochs total 600 steps)
Another experiment to see how things turn out.
As expected the facial expressions doesn't change much due to only have 1 example.
But the clothing can be changed at will.
The background are really terrible, which I don't get since that's not trained in and should be done by FLUX itself. But it is what it is.
The reason I am testing FLUX loras with free resources or low image count is to find free/cheaper/easier ways for users who are not so knowledgable about Lora creation to be able to create models.
My previous high quality Fictional Model loras required paid subscriptions to AI services. And take around 6+ hours to make for just ONE lora. Which I upload and don't even earn the buzz back for.
This isn't really an option for new and inexperienced users.
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.