Detail Slider LoRA | PonyXL SDXL

For best results using this LoRA I recommend you use this merge of PonyXL (Autism Mix).

👇👀 Read me! 👇👀

This is a slider for SDXL PonyXL. Trained on AutismMix Confetti. The purpose of this slider is to enhance the overall detail in an image and the goal is to have it be robust and versatile enough so that you can put it in pretty much all your prompts.

As of v1.0 it does a better job at adding detail to the background than it does for the foreground. I plan on working on that for a v2.0 as well as adding better support for negative values in case you want to actively degrade quality for whatever reason.

No activation tag. Recommended weighting is anywhere from -4 to 4 . Example prompt:

score_9, score_8_up, score_7_up, source_anime, 1girl, v, standing on one leg, full body, green hair, ahoge, short hair, elbow gloves, headphones, red eyes, (grin), fingerless gloves, skirt, knee boots, looking at viewer, bare shoulders, skindentation, stage background, concert, <lora:StS_detail_slider_v1:3>

No special negative prompting needed. A nice side effect is that largely replaces the need to put anything like "masterpiece" or "high quality" in the positive prompt.

If you generate images with this, please share! I love seeing what people make with my LoRAs and it helps keep me motivated to make more. If you have PonyXL LoRA requsts, feel free to leave a comment and I'll look into into it 👍

Changelog:
April 15, 2024 - Initial release