Sign In

Broly Culo Meme [PonyXL]

276
1.4k
5.7k
106
Updated: May 2, 2024
conceptmeme
Verified:
SafeTensor
Type
LoRA
Stats
1,146
5,441
813
Reviews
Published
Apr 28, 2024
Base Model
Pony
Training
Steps: 12,000
Epochs: 134
Usage Tips
Clip Skip: 1
Strength: 1
Trigger Words
broly culo
Hash
AutoV2
0D92781E2C

LoRA for recreating the Broly Culo Meme with your favorite characters (also known as the "Omni-man with the fat ass" meme). It's up to you whether you use this LoRA for the funny, the horny or both.

If you like the LoRA, please leave a reaction, review and/or tip. Enjoy!

Usage

  • Trigger word (optional): broly culo

  • Support tags: squatting, looking back

  • Recommended strength 0.8 - 1.0 (try scaling the strength of the trigger word before scaling the LoRA strength!)

  • Use Clip skip=1 or Clip skip=2 (other values may also work, use at own risk)

  • Use at 1024x1024 or wider resolutions. Using less width without increasing height accordingly causes characters to not recreate the pose accurately.

Example

See preview images (generated with pruned version).

Unpruned vs. Pruned vs. Lite

I offer three variations of the model, which only differ in the file size and quality. Pick the one that best suits your preferences. If you can not decide, simply pick the "pruned" version. Note that the quality is relative, even the lite version usually produces images which closely resemble the intended subject.

  • unpruned: The originally trained model. Largest file size, best quality. Pick if you want the best possible quality, at the cost of disk space.

  • pruned: Downsized model. Almost same quality as the unpruned version, with noticably smaller file size.

  • lite: Drastically downsized model. Smallest file size. Still has good quality, but noticeably worse than unpruned and pruned.

Notes

Even though the training dataset for this one is really small, it turned out pretty well. I really like the Helltaker image I made, for some reason it is unreasonably funny to me. I got a bit lazy with the preview images, but I'm sure you get the gist.

Using training data

Feel free to contact me if you want access to the training data.