This was a Lora I made quite a while ago as an experiment.
I only used five photos that I had taken myself, and then trained a Lora based on what AI said all my photos had in common.
I suppose this could be considered a liminal space lora.
Look at the prompts used in my images for example language used.
It might even work better if you ignore the way I captioned it so you can get more diverse output.
Description
FAQ
Comments (1)
Your exceptional photographic talent is evident in this LoRA, which enables us to replicate its enchantment in our renders.
It is true that sometimes less is more when training a LoRA; this principle absolutely applies here. By employing only 200 steps, the LoRA acquired sufficient of the style and compensation elements to give our renders a distinct feel without overfitting, thereby enabling it to perform its magic while maintaining remarkable versatility.
This is an example of exemplary LoRA planning, design, and training strategy done right.
Bravo! I extend my utmost admiration to you. Thank you for sharing this remarkable creation.
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.