1mb LORA that's trained on single picture featuring limited blue pallete with illumination using <a target="_blank" rel="ugc" href="https://civarchive.com/models/6596/luisap-lora-dont-need-to-be-bigger-new-recipe">luisa_pinguin guide</a>.Main trigger: limited paletteRefer to examples to see possible results, aimed for result is at strength 1, but feel free to experiment.You can also use LORA without trigger for some interesting and less transformative outputs. It also has small tendency to sometimes add more people when using 1boy\1girl prompts, so add 2boys, multiple people, etc., into negatives if that happens.If you liked my work, you can donate <a target="_blank" rel="ugc" href="https://www.buymeacoffee.com/gertan">here</a>.Trained on Anything V4.5 with anime.vae.pt and CLIP Skip 2.Samples are 512x768, using <a target="_blank" rel="ugc" href="https://civarchive.com/models/4355/orangecocoa-5050-mix">OrangeCocoa 50/50 Mix</a> , with <a target="_blank" rel="ugc" href="https://huggingface.co/WarriorMama777/OrangeMixs/blob/main/VAEs/orangemix.vae.pt">OrangeMix VAE</a>, and using <a target="_blank" rel="ugc" href="https://civarchive.com/models/7808/easynegative">EasyNegative</a> embedding, CLIP Skip 2.

Files with SHA256: 24ddfad52b1a524ef8f654675817611385ad8613803c0301e0f32dc65dd2daef