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>Training settings:40 images, 15 steps, 12 epochs, you find many epochs (with test images using plot xy script) on my <a target="_blank" rel="ugc" href="https://www.patreon.com/betterCuteAsians">Patreon</a> while supporting me. 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 9</li><li>LORA weight for txt2img: reccomended 0.4-0.7 (0.5-0.6 best results)</li><li>Keys: wearing bunny outfit, back view</li></ul>In my experience with this model, i saw very good images while starting the prompt with "a woman in a strip club, strip club lights, sitting on a couch" you can change it a bit to get what you want.Trigger words are not always necessary, but most of the time SD will try to draw a lingerie outfit with bunny ears, in that case try to give a bigger weight to "wearing bunny outfit" and move it at the beginning of your prompt.Also for the weight of the model, i advice 0.55, nice outfits that follows the model and no distortion in girl models.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: 5a22b87ffc785ded56645ce909d22e019a6a43bd5a7d6e7d7a9f019bf0b23a00