<h3 id="ver-noob-v-pred-v1-eq">Ver NOOB V-PRED V1 EQ</h3><span style="background-color:rgb(26, 27, 30);color:rgb(141, 141, 143);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px">Trained with improved parameters based on NOOB V-PRED EQ VAE exprimental version: <a target="_blank" rel="ugc" href="https://civarchive.com/models/1858821/noobai-v-pred-10-with-eq-vae">https://civarchive.com/models/1858821/noobai-v-pred-10-with-eq-vae</a><h3 id="ver-noob-e-pred-v1">Ver NOOB E-PRED V1</h3>Trained based on NOOB E-PRED V1.0. Different trigger words set to precise concepts. See about the version for training details.<h2 id="updated">Updated</h2>Used PonyXL to train this one. Updated dataset to achieve better performance. It enhanced this concept on PonyXL and related models.With PonyXL many concepts can be easily generated. So I will focus on the weak concept in PonyXL. Concept like hyper_futanari that can easily generated with Pony model will not updated to XL version.Strength 0.8 recommended.<h3 id="introduction">Introduction</h3>This is the subLyCORIS of <a target="_blank" rel="ugc" href="https://civarchive.com/models/18230/hyperfuta">hyperfuta | Stable Diffusion LORA | Civitai</a>Use this to generate futanari with larger glan. It can be used alone. But it seems a little overbaked.<h3 id="how-to-use-it">How to use it</h3>I recommand using it in weight 0.6-0.7 or lower combined with hyperfuta LyCORIS.<s>Not enough tests for other tags. </s>It seemsworks well.<h3 id="training-details:">Training details:</h3>Traingset is of about 130 images. They are mirrored before training. Total steps are about 5500.Regularization = falseresolution=768batch_size=1epoch=10network_dim=32network_alpha=32clip_skip=2Using AdamW8bits as optimizer:<ul><li>lr="1e-4"</li><li>unet_lr="1e-4"</li><li>text_encoder_lr="1e-5"</li></ul>Locon parameters:<ul><li>conv_dim=4</li><li>conv_alpha=4</li></ul>

Big glans (NOOB and Pony version)

Files with SHA256: e47fa84aa6394e8c3e2b1f6098c8483199b79aaf27ed07806f4c3a501da97dcf