LoRA trained on ZIT, Anima and Krea2 all have different trigger words. Sometimes you get the style even without using trigger words (especially on Krea2)P.S. * I use local ComfyUI for image generation.<h2 id="for-krea2:">For Krea2:</h2>Strength: 1.0 - 1.5.A bit tricky on Krea2 because of prompt adherence or god knows what:<ul><li>If you try to use words that creates realism, you will absolutely need 1.5 strength</li><li>If you try to use known celebrity fanart words with specific styling like Disney Princesses then you will need 1.2+ strength.</li><li>If above two is False then 1.0 is enough in most cases.</li></ul>Add words like comic, 2d, flat color to help boost the lora styling<h2 id="for-anima:">For Anima:</h2>Strength: 0.8 recommended. 1.0 will give some anatomy issues.Anima Version is Trained on Anima Base 1.0<h2 id="for-zit:">For ZIT:</h2>Strength: 0.8 - 0.9 recommended. 1.0 might give some anatomy issues.Used 25+ images of comics style from old times, they have more like hand drawn feel but a slight exaggerated expressiveness.<hr />Enjoy and follow me on <a target="_blank" rel="ugc" href="https://www.deviantart.com/wheeman">https://www.deviantart.com/wheeman</a> ❤️

Files with SHA256: 341edb1cde72de4422cc025f594209346d26d6d4d4026d02fffe9eac48e9b6ba