This LoRA is, literally, pog (or more accurately: pogchamp).

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

Usage

• Trigger word: pog

• Support tags: looking to the side, lips, open mouth

• 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 (may stretch the head a little if using non-square resolutions)

• Works for close-ups, portraits and upper body shots. Anything else will likely not work, unless using in-paint magic.

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 concept.

• 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

The difference between unpruned, pruned and lite is pretty noticable with this one, but all three versions work. Since the training set was pretty small, the LoRA got some quirks and biases, but I doubt anyone is trying to create pixel perfect masterworks with this one.

Using training data

All training data has been sourced from publicly available sources. Feel free to contact me if you want access to the training data.