LORA trained in style of Hades, 2 versions, 144mb and 32mb. Small version is a bit unstable, but I really liked stuff I was able to get from it during testing, so I throwed it in as well. Bigger one also seemingly plays better with other LORA's. My first attempt at capturing an existing style, would appreciate feedback on how well (or not) it works for you.Trigger:<ul><li>hadesstyle, you can do with just adding LORA though, difference seemed minimal with or without trigger.</li></ul>Tested on 0.5-1 weight, seems to work fine on whole spectrum, but when mixing LORA's a bit lower weight is recommended. A few other trained tags, like clothing or accessories:<ul><li>laurels crown, toga, dress, greaves, animal on the shoulder, glowing feet, skulls, fury (Meg and her sisters were tagged with this one)</li></ul>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.

Hades Style

Dataset of 68 images with deepbooru tags

Files with SHA256: 2b67e859fcd38b25d280d4ac84669c59a33e923a310a2598b302f327dd7ce9f4