Get early access to build and test build, be able to try all epochs and test them by yourself on <a target="_blank" rel="ugc" href="https://www.patreon.com/betterCuteAsians">Patreon </a>or contact me for support on DiscordTo support me you can buy me a coffe at <a target="_blank" rel="ugc" href="https://ko-fi.com/antonioriolo">https://ko-fi.com/antonioriolo</a>Recommended settings:<ul><li>Make sure you are aware on the usage instructions of LORA</li><li>Sampler: DPM++ SDE Karras (Recommended for best quality, you may try other samplers)</li><li>CFG Scale : 5 to 10</li><li>LORA weight for txt2img: reccomended 0.3-0.7. (I used 0.5)</li><li>Keys: relaxing_on_hammock, surrounded_by_water, surrounded_by_beach</li></ul>Works better with anime.This model has been trained mostly on not squared images, mostly larger then higher, so i tryied to generate images with larger width has it should be but i didn't find a checkpoint that didn't distort faces in this case. So i'm posting all images with a small hammock in 512x768. If you find a good prompt for larger images with bigger hammocks i invite you to post them with data for the others.keywords "surrounded" just select the environment where she/he is relaxing on hammock.There is also surrounded_by_green if you want to try but it seem that everything becomes green, i had probably to use another keyword.Enjoy!If you'd like to support my efforts and have access to early and bleeding edge builds, please think about joining my Patreon: <a target="_blank" rel="ugc" href="https://www.patreon.com/betterCuteAsians">https://www.patreon.com/betterCuteAsians</a>

Files with SHA256: 28a3fadd558733250b3d037665cdf281f7e3e2a700e543e7edfcf1572f5e95f8