<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/3be57d94-2cb6-4d93-a9bf-70714b9ba859/original=true/3be57d94-2cb6-4d93-a9bf-70714b9ba859.jpeg" />Use this with <img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/bd8825a1-8f3c-453b-b5e4-b1ffa4473f1f/original=true/bd8825a1-8f3c-453b-b5e4-b1ffa4473f1f.jpeg" />this lora has 105 epochs with 850 different images. its better quality for base than other loras and it can do a lot. there is an emphasis on butts for sure but it can do anything I will start posting images since this isn't gaining traction. get the workflow in my article about combination with base and turbo for quality. i

NSFW The Bean Effect

a more refined version with 39,000 steps on 460 images at about 84.7 passes per an image. The dataset featured a highly curated set of 465 images of my ideal feminine beauty in different poses with an emphasis on clothing fit and on and off clothing so that certain fits will land in the model . Essentially curvy and thin women but all with the "bean effect" tight clothing will look tight in the glutes and crotch, faces will be adorable . this is no overfitted and can handle very high and very low strengths due to the large dataset and training steps. I like to use anywhere from 0.5-0.9 but I would recommend trying anything for fun. blend it with other loras and more.

Files with SHA256: 70669a8ed39338c29766e6de3deb1dfd1f6319bb86fd7ff4fc01e0b842a9b85c