This is my first LoRA for Flux. Hope you enjoy.
If you're not familiar with Karl Pilkington, none of my sample images will make sense. Fans of Karl will be able to have endless fun illustrating his adventures, musings, mumblings and anecdotes. Can't wait to see what you come up with!
Sample images are very much cherrypicked, but no inpainting or ControlNet shenanigans involved.
Description
Version 1.0 - trained on the Flux.1.D base model with AI Toolkit, using a dataset of 2000 images, 7000 steps, EMA and cosine annealing.
The trigger word seems to be mostly unnecessary. I would avoid using the name "Karl Pilkington", as the output may be adversely influenced by the model's existing concept which is inaccurate.
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.