No trigger word needed for this LoRA. It should improve the quality of images generated for anime and digital illustration overall.You should pair it with another LoRA to steer the model towards the style you want your image to have, this one should only aims to increase quality.The images in the preview are NOT quality maxxing (you can do better with precise style LoRA &amp; up-scaling), it just showcases what the LoRA outputs.<hr /><h3 id="z-image-(base):">Z-Image (Base):</h3>It happears that LoRA trained on base seem to work on Turbo if you crank the strength very high (between 2 and 4)Honesty, Z-Image is such a good base you might even need a LoRA to steer it towards high quality illustration. It is the default. The LoRA has only a very light effect, especially if you already schizo-prompt for a specific style.This model can pretty much do anything with the right prompting, though it is a bit slow (Chroma like speed).Really hyped to see the fine-tune that will come out of this because the base model is already able to do some nsfw (Tongyi-MAI must have trained quite a bit on NSFW judging by how it does genitals / nsfw scenes, then abliterated before release)<hr /><h3 id="klein:">Klein:</h3>Klein (both 4b and 9b) are very schizo model, they are extremely good a certain things (landscape, geometry, high-res) and worse than flux 1 at other (style, text, spacial relations between objects).They will 80% of the time ignore half of your prompt while generating the worse body horror since SD1.4. Then generate a nearly perfect image the next seed.That being said, I think klein 4b will be the next SDXL. It is definitely a step up from Illustrious in some way for anime (and other styles). While still being faster than ZImage and it has edit abilities.For the time being both klein model are worse than Chroma if you just want to normal photo / anime images. I'll use Klein 4b and Z-Image as an upscale model for Chroma until good fine-tune come out. I invite you to give Chroma a shot, but keep in mind that the better instruction following and style of chroma comes with the cost of it being very slow. <a target="_blank" rel="ugc" href="https://civarchive.com/articles/21793/boost-speed-and-quality-of-your-chroma-generations-with-chroma-flash-heun-lora">Read this article before starting to use it.</a>

Style > People's Work

Trained on 1700 hand picked anime / digital illustration from civitai.V2 was trained in Onetrainer using <code>Prodigy Plus Schedule Free</code> at batch size 4 for 5000 steps at 512, 768, 1024pxThis LoRA is over-fitted since my dataset is too repetitive, it is a good first test, but I will definitely do another version once I have a less repetitive set of images. Batch size also needs to be increased to 8/16 to get better results.

Files with SHA256: 5c0f5bbf9ff5ddd36d5f67ca10a415bf6f7e391bf7778e2b4c391f522da764f2