Modify the weights of the LoRA to achieve the desired result.
This was also trained with the expanded VAE located here. Please use this VAE when inferring with this LoRA.
Description
Faces still don't look good at a distance, so you'll have to inpaint them.
Changelog:
Initial release
Training Data:
Used bmaltais's implementation of kohya_ss LoRA training scripts.
Total Images: 15 total high resolution images: six full body, four head shots, five chest-up
Regularization Images: 300 total "sexy woman" regularization images from ProGamerGov's dataset at huggingface.
Trigger word: lauren boebert
Training Steps: 2700
Unet Training Rate: 5.0e-06 (0.000005)
Text Encoder Training Rate: 5.0e-05 (0.00005)
FAQ
Comments (8)
Personally I feel like politicians is getting into sketchy territory. Celebrities is one thing but we don't need anymore heat brought down on this community than we already have. First, imagine lawmakers in DC discussing issues on AI Art in the future even without these specific models. Now... imaging them discussing AI Art and literally saying, "See? They're even targeting us!" I hope you see where I'm coming from.
Great stuff. You should do Kat Timpf and Megyn Kelly too. Maybe Tulsi Gabbard.
Finally, the naked hooker pictures I was promised for years has finally became a reality. My sides in will go into orbit if this is the straw that breaks the camels back and makes D.C. go total retard war over machine generated images.
Hey I noticed the samples from 1.0 look a little bit better than 2.0, which with what you said about the training, doesn't make sense.
But now I see the outputs were with the standard 1.5 for the 2nd version of this, but the original 1.0 version used Stably Diffused and Realistic Vision. Maybe that's it? I haven't done LoRAs but when I train TIs I do it on 1.5, but then use something different for the actual outputs since I just think 1.5 is good for training only.
I keep getting errors on the new version that didn't happen with the old one (hadn't used it before tonight, just was testing).
I tried it with several other models and prompts, same result, artifacts on the new version.
https://imgur.com/a/o6RyqcF
Who is she?
Love this LoRA soo much. Thanks for making.
lol, She's a MAGA cultist. Good job no less. Looks just like her.
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.