XUPLX UglyPetShopLoRA was trained on 250 images of popular toy animals at 1600 steps. You must use "xuplx:" as the trigger to force the style onto the subject of your prompt - whether they be animal or human. The "look" of the LoRA can be seen in just 8 steps with a CFG of 1, a ModelSampling of 2 to 3, and a LoRA model strength of 0.75 to 1.00.

NOTE: You'll need to emphasize "big eyes" and "painted details" to get the desired result - and the result is vastly different to the vanilla output as seen in the images above.

CHECK OUT MY UGLY PEOPLE LORA:

https://civarchive.com/models/2220894/xuplxuglypeoplelora

DON'T BUY ME A COFFEE!!

Download ExportGPT - Media & Chat Export Toolkit from the Chrome Web Store. The chrome extension works with ChatGPT and Sora to export assets quickly. I update it often, it has 5 stars, and it's free forever!

Visit exportgpt.org to see it in action.