<p>This is a non-anime model that can handle illustrated styles in addition to photorealistic (trends to semirealistic by default).</p><h1 id="heading-824">Prompting guide</h1><h2 id="heading-8">For Illustrated images</h2><p>For Illustrated, cartoon, or comic/graphic novel style results, make sure "illustration" is in the positive prompt.</p><p>Recommended negative prompt for illustrated images:</p><pre><code>3D digital, photo, blurred, grainy, low quality, artist name, signature, watermark, text, web address</code></pre><p>You can embellish an illustration with further styles, such as the specific artist names listed in the triggers for this model, or with a hybrid illustrated style using the keyword phrase "<strong>ligne claire illustration</strong>"</p><h2 id="heading-9">For Photorealistic images</h2><p>Recommended negative prompt for realistic photographs:</p><pre><code>3D digital illustration, blurred, grainy, low quality</code></pre><h2 id="heading-228">Artist styles</h2><p>Artist styles that this model was explicitly trained to on include Roy Krenkel, Jean-Pierre Gibrat, Milo Manara, Willy Vendersteen, Francois Schuiten, Edgar P Jacobs, Herge, Jacques Tardi, and Moebius.</p><p>To invoke a specific artist styles, simply add "by Artist Name" to the positive prompt, e.g., "illustration of a woman on a tropical beach, by Roy Krenkel"</p><p>Artist names can have a very strong impact; try them with weak weights, e.g. "(by Roy Krenkel:0.1)" or "(by Jean-Pierre Gibrat:0.1)" and see how a dash of their style influences the composition and color scheme.</p><h2 id="heading-229">Ligne claire</h2><p>This model contains a general activation keyword phrase to evoke a certain hybrid comic book style and composition. This phrase is "ligne claire" meaning "clear line" after the Franco-Belgian comic book tradition.</p><p>For example: "A ligne claire illustration of a female science fiction bounty hunter."</p><h1 id="heading-825">Background/history</h1><p>A funny thing happened when I was training my photorealistic <a target="_blank" rel="ugc" href="https://civarchive.com/models/53573/centerfold-blend">Centerfold Blend</a>. I found that when I incorporated <em>illustrated</em> images in the training data (properly tagged, of course) the model produced better <em>photorealistic</em> images.</p><p>Centerflex is an extension of an older version of Centerfold Blend, with a great deal more non-photographic training data. It is intended to be more flexible than Centerfold (hence the name Center+Flex), especially regarding illustrated styles. It was trained with a variety of artist styles in addition to high quality photographs of people.</p>

Centerflex

<p>This is a completely new model resulting from more training, merging, and fine-tuning. Less capable of photorealism, but better at illustrations.</p>

Files with SHA256: 821ffe43afde59af01a0f326f7e4a8696ce3113eafb808317be18770ae686948