XUPLX_UglyPeopleLoRA - v1.0 Showcase
XUPLX was trained with "mood-tags" (see the prompts in the images). Within the workflow, the LoRA is activated by "moody" keywords; the mood image is generated within the first couple of steps with XUPLX, and then the rest of the generation is processed by a second Ksampler with a proper natural language prompt - without the LoRA.
XUPLX_UglyPeopleLoRA can be used on it's own (see "After and Before" images), or within the workflow.
Use of the "XUPLX" trigger is not necessary - until it is. Z-Image-Turbo has weird behavior with certain hyphenated words (ie. "art-house" will stubbornly prioritize generating Kimonos over the generating your prompt).
NOTE: You can use "Black and white", "cigarette" or "smoking" in your prompt with XUPLX to see it in action (the LoRA reacts strongly).
HOW TO USE IT: Here's the article that explains the worklow a bit more in depth: https://civitai.com/articles/23657/how-to-merge-image-styles-quickly-with-xuplx-and-zimage-turbo
DON'T BUY ME A COFFEE!!
DOWNLOAD ExportGPT - Media & Chat Export Toolkit from the Chrome Web Store. It's a "download anything" Chrome Extension for ChatGPT and Sora. I update it regularly, it has 5 starts, and it's free forever!
See it in action: exportgpt.org