<ul><li>download the YAML </li><li>use a webui that supports v-pred, turn on ZTSNR betas, and use CFG Rescale=0.7 (InvokeAI with diffusers link recommended because it handles this for you</li><li>use NON-K samplers (ZTSNR does not work with Karras)</li><li></li></ul><h3 id="if-you-don't-you-will-get-blackbrokenweird-images-8n20ubx84">if you don't YOU WILL GET BLACK/BROKEN/WEIRD IMAGES</h3>Photography model, resumed from <a target="_blank" rel="ugc" href="https://civarchive.com/models/120851">Pretty Girls Next Door </a>with new training data - prompting tips can be found <a target="_blank" rel="ugc" href="https://civarchive.com/models/120851">here</a>. The model uses an OpenClip-H text encoder. The prompting style is halfway between SD1.5 and SDXL. Some of the training data is booru tags, some is moondream English sentences, some is hand-labelled.Recommended settingsThis is a v-pred model trained with ZTSNR. Use CFG Rescale = 0.7 and enable zero-terminal SNR betas. For best results, use InvokeAI.Image size; 640x896Steps; 50Scheduler; DPM++ 3M or DPM++ 2M SDE (NOT KARRAS)

Files with SHA256: ce37e9f71adbc99580f33e8bd399103c4b397104d5a8136e6050257defc0fe3f