This LoRA is trained on 222 100*100px portrait images and makes it easier to generate, well, low res portraits. "Why would I want to make pictures for ants" you ask?

1 - You want to make a bunch of side character portraits for a game or picturebook
2 - You want to make pictures to use as stickers or emotes
3 - You want to make enourmous amounts of smaller images and shotgun for good seeds/starters to to refine in img2img later.

Naturally you can just use this to make bigger images as well if you want.

How to use
Use tag "portrait" and "1girl". "1boy" might work too despite the dataset being mostly female.
Minimum recommended resolution on NAI is 128 x 128px for square images. 128 x 144 / 144 x 128px for wide/tall portraits.
If you want to use it on AOM2 I recommend putting "3d" and "realistic" in negatives to keep the images clean.
Tip: "Eye focus" can be used to zoom in. "closeup" in negatives to zoom out a (very small) bit.

Don't forget to review and upload your own images, it's always fun to see what you're creating!
Like my LoRAs and want more? Please consider a small tip towards my electricity bill and further training >.<

Misc
512 resolution trained on NAI without noise offset option for best LoRA compatibility.
All images except the two rescales are untouched raw txt2imgs, no inpainting done, for quality transparency.
Recommended model is NAI or any other with good support for drawing styles.