https://civitai.com/models/118841/hyper-bottm-heavy-sdxl

Extremely bottom-heavy concept LoRA. Tends to produce back view shots, recommend specifying "front" or putting "rear view" in negatives to circumvent. Results may vary.

Original notes:

This is a test LoRA of my bottomheavy dataset, but trained on SDXL. I wanted to see how SDXL would handle the same data/config as my last released model.

The results came out better than I expected and it was pretty quick to train compared to SD1, so I'm uploading it just for fun. Still, don't expect to much from this LoRA. I just wanted to see what SDXL was capable of. And I have no idea how to prompt for SDXL yet, so keep that in mind.

See Training Data for tags list

I will probably train Hyperfusion on SDXL eventually but it will be quite a while before I get around to it.

This model is not to be used for commercial purposes and generations should never be sold.