[SD 2.1 768][Checkpoint]TrulyAnything V1
<p>Can the (in)famous anything series generate <em>literally anything</em>? <strong>No.</strong> They can't generate anything apart from anime styles.</p><p>So here you go. An ambitious model that can generate literally anything; from anime style to photorealistic "atashi".</p><p>The model was trained based on <a target="_blank" rel="ugc" href="https://huggingface.co/ThePioneer/ChaosMix"><strong><u>ChaosMix</u></strong></a>, with images generated from <a target="_blank" rel="ugc" href="https://huggingface.co/ThePioneer/MoeSharpV1"><strong><u>MoeSharpV1</u></strong></a> and <a target="_blank" rel="ugc" href="https://huggingface.co/datasets/ThePioneer/Artificial-Super-Girlfriend-for-Dreambooth"><strong><u>"atashi" the artificial girlfriend</u></strong></a>.</p><p>It is NAI leak free, and yet powerful because the basic model is the latest Stable Diffusion 2.1 768.</p><p>I didn't upload a yaml because it's no longer necessary when using webUI. If you need one, just download and rename it from somewhere.</p><p>Sample images will be added later.</p>
页:
[1]