Snuffy (character) [3-in-1][PonyXL]: v1.0 lite: snuffy_v1_lite.safetensors

This is the lite version. It has a minor, but noticeable loss in quality compared to the unpruned version.

Use this version if you want to save some disk space.

Character LoRA for Snuffy the trash panda vtuber (Smilfy form, Smilfy v2 form and Avatar of decay form). Also, did you know that the human a**hole can expand up to 8 inches in diameter? And that a trash panda can fit in a hole 4 inches wide? Therefore you are able to fit 2 raccoons in your a**.

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


  • Trigger words:

    • snuffytrash: Smilfy, the big breasted trash panda

      • Outfit tags:

    • snuffydark: Smilfy v2, the big breasted goth trash panda

    • snuffydecay: Avatar of decay, the flat chested goth trash panda (aka. snuffys vrchat model)

  • Tags for smilfy outfit: cow print, crop top, scarf, open jacket

    • Works best with snuffytrash, but can also work with other triggers

  • Recommended strength 0.8 - 1.0

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

  • Works best at 1024x1024. Similar resolutions (e.g. 800x1200) also work well.


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.


I struggled a lot with this LoRA because it kept associating the cow print crop top with Smilfy, instead of the actual trigger word. Then I discovered that I am an idiot and made several mistakes while creating the dataset (wrong tags, bad trigger words, unbalanced dataset, etc.).

A lesson learned, I suppose.

Using training data

Feel free to contact me if you want access to the training data.
The training data (images and tags) have been mostly sourced from and other images boards. They have been cleaned up manually by me. When using the training data or modified versions of it to create models or datasets, please credit me as appropriate.


This LoRA is not affiliated with the character it is based on. If you like the character, check them out at one of their socials: