Please share your creations. I would love to see how you have used the LoRA.
The Whimsical London LoRA was trained to produce images that have an English feel, though other images can be created. It has a touch of whimsy and a little abstract style thrown in.
V03
When it came time to produce versions for Qwen and SD3.5, I discovered that the training images produced too many artifacts for clean results. I produced new training images and regenerated each of the models I support. The results are inevitably different than the preceding version, but may still be of interest.
V02
This version has more of the atmosphere, whimsy and character I was hoping to produce in version 1. Start with a weight of 0.85.
V01
Weight range: 0.6 - 1.2, depending on the intensity of effect desired. Start around 0.8 and go from there. This version is more realistic than V02
Description
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.