<h3 id="heading-2321">Introduction</h3><p>Are you tired of models that make too much sense, are too reliable, or have a clear purpose or application?<br />Me too.<br /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/1b601d31-1c12-4251-9889-4ccc82f0e228/width=525/1b601d31-1c12-4251-9889-4ccc82f0e228.jpeg" /></p><h3 id="heading-2322">Instructions For Use:</h3><p>counterfeit v3 and counterfeit v3's easynegative would work with this model, but I do not habitually use negative prompts, and i didn't render my test images with counterfeit.</p><p></p><p>try like, typing some words into the text prompt and seeing what they do. <br />fusing this with a basemodel and training another lora on <em>that</em> would be very funny. someone should do that.</p><p></p><p>7/22/2023 update: I now specially recommend using the 'dynamic thresholding' addon for automatic1111's ui.</p><p> I like a 'mimic CFG scale' of 12,</p><p> a 'mimic scale scheduler' of 'linear up' with 4 'minimum mimic scale scheduler',</p><p>and a 'CFG scale scheduler' of 'half cosine down' with 4 'minimum CFG scale scheduler'.</p><p>Self attention guidance is good too, with values of 1.0 , 1.0.</p><h3 id="heading-2323">Cautionaries And Caveats:</h3><p>This lora is a synthesis of multiple other Loras made by unknown authors using unknown datasets made at the middle of the night &amp; tested on '1girl' before release.</p><p>It could do literally anything.</p>

Files with SHA256: cb883add6ccf61930229fd74badcbb9e94e2530b12f0fa71eb69a89472ac5806