because SDXL sucks at fundoshi1.5 images sample images upsampled.The 1.5 model is preferrredSDXL INSTRUCTIONS<ul><li>Likes turning into a loincloth style fundoshi below 0.7 LoRa strength (working on a fix)</li><li>Try LoRa strength 0.6 - 0.9 and cfg 4 - 30 with 0.7 and 10 as your starting point</li><li>The suggested resources are not necessary and were used to fix some issues with hands</li></ul>the cover's data is trying to find the prompt for two images, the realistic one was prompted by using words like "high definition, realism, realistic"<a target="_blank" rel="ugc" href="https://ko-fi.com/alightbulb">https://ko-fi.com/alightbulb</a> if you're feeling generous

Files with SHA256: f66b92dd8106df5441c766a4fca073fb2dc99e22b109656955ebcf1728dc7db5