HarroweD/HarrlogosXL
🚀HarrlogosXL - Bringing Custom Text Generation to SDXL!🚀
<p><b>Teaching Stable Diffsuion to spell, one LoRA at a time!</b></p> </center> <Gallery /> <p>Harrlogos is an SDXL LoRA trained on my own art and graphic design work, unlocking the ability to generate custom text.</p> <p>It does not require any control net, any img2img, or characters from fonts on the canvas.</p> <p>All you need is the LoRA, and you're ready to go!</p>
<h2>Versatile, Responsive, Powerful</h2 <p>The model comes with a plethora of styles, modifiers, and extra content built in, but that's only where it begins.</p> <p>One of the greatest aspects of the model is how well and how seemlessly it works with almost any checkpoint, other LoRA, or even things like Stable Video Diffusion!</p>
<h2>Using Harrlogos:</h2> <p>Harrlogos works with individual terms, separated by commas, in a specific order. You do not need all of these in every prompt, but this is the general format:</p> <ol> <li>YOURTEXT text logo</li> <li>Text Color: blue, teal, gold, rainbow, red, orange, white, cyan, purple, green, yellow, grey, silver, black</li> <li>Accent Color</li> <li>Background color</li> <li>Style Modifiers: dripping, colorful, graffiti, tattoo, anime, pixel art, 8-bit, 16-bit, 32-bit, metal, metallic, spikey, stone, splattered, comic book, 80s, neon, 3D</li> <li>Accent Modifiers: smoke, fire, flames, tentacles, hell, glow, horns, wings, halo, roots, embossed, blood, digital, ice, frozen, japanese, chrome, pastel, robotic, hearts, cute, egyptian, viking</li> <li>Additional Content: cat, sword, owl, cat ears, cthulhu, sun, roses, clouds, space, stars, skeletons, demons, fog, trees, moon, skulls, bones, planet, earth, cherry blossom, pentagram, crosses, lightning, bolts, crown, circle, moth</li> </ol>
<p><strong>Example of a prompt with the resulting image:</strong></p> <p>HarroweD text logo, white, grey, red, spikey, splattered, dripping, blood, hell, crown</p> <img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/1a55d578-aeba-408e-b282-03f4c75024bb/width=525/1a55d578-aeba-408e-b282-03f4c75024bb.jpeg" alt="Example Image"/>
<h2>Helpful Tips/FAQ:</h2> <ul> <li>Harrlogos is trained on a 1024x1024 data set, so it works best at resolutions: 1024x1024, 1024x768, 768x1024, 768x768</li> <li>You will not get the correct spelling of every word, every time. Some text may take multiple tries to get right</li> <li>The model works best with single words, multiple words are very achievable but it may be more difficult</li> <li>Try weighting the text in the prompt, ex: ("Harrowed":1.5) text logo, red, black....</li> <li>There's two schools of thought in achieving the perfect Harrlogo - A. Brute force spam through seeds B. Find a good starting point and lock the seed in, then slightly asjust the other paramters up or down, which will create slight changes to the image.</li> <li>With a fixed seed, raising or lowering the CFG, Steps, or even resolution will modify the image, potentially fixing things or correcting spelling.</li> <li>In the negative prompt, consider things like: Double letters, repeating letters, malformed letters, and more than X letters. If your renders keep coming out with a specific double letter, also try putting that in the negatives.</li> </ul>
<p>This is a work in progress!</p>
<p><a href="https://ko-fi.com/harrowed" target="blank">Support us on Ko-fi</a></p> <p><a href="https://www.tiktok.com/@the.harrowed" target="blank">Follow us on TikTok</a></p> <p><a href="https://www.instagram.com/the.harrowed/" target="_blank">Follow us on Instagram</a></p>