Name: HL's Styles - NoobAI-XL
Rating: 5 (245 reviews)
Author: civitai

Krea 2 LoRA training is 50% off, and we're running a Krea 2 Training Contest with 1.8 million Buzz in prizes across four LoRA categories.

⚡ Krea 2 Training Contest + 50% Off Training

<h1 id="!!!-lora-can-be-difficult-to-use-!!!-nt2fb1rco">!!! LoRA can be difficult to use !!!</h1><h3 id="this-is-my-first-attempt-at-creating-loras-so-they-aren't-perfect.-they-have-some-flaws-and-might-be-a-bit-unstable-but-you-can-still-use-them.-44n15rwsb">This is my first attempt at creating LoRAs, so they aren't perfect. They have some flaws and might be a bit unstable, but you can still use them.</h3><h3 id="on-this-page-i-will-share-various-styles-that-i-use-in-my-own-works.-w33iaungm">On this page, I will share various styles that I use in my own works.</h3><h3 id="you-can-find-more-details-about-each-lora-in-the-&quot;about-this-version&quot;-section.-yehucs584">You can find more details about each LoRA in the “About this version” section.</h3><h2 id="waiillustrious-version-is-here.-ihrq38mfj">WAI/ILLUSTRIOUS version is <a target="_blank" rel="ugc" href="https://civitai.com/models/1116233/hls-styles-wai-or-illustrious?modelVersionId=1254358">here</a>.</h2><h3 id="many-thanks-to-@wwhey-i-couldn't-have-done-it-without-her-advice!-zjilm4xr9">Many thanks to @<a target="_blank" rel="ugc" href="https://civitai.com/user/wwHEY">wwHEY</a> — I couldn’t have done it without her advice!</h3><h3 id="but-she's-not-responsible-for-the-crappy-quality-of-my-loras.-x)-2tjyj18hs">But she's not responsible for the crappy quality of my LoRAs. x)</h3>

This model provides decent aesthetics and depth, however..... it is VERY difficult to use. I don't know what's wrong with my models, they always turn out like this, but... yeah. :(Trained on artworks of artist kan liu (666k). I edited all dataset in photoshop to improve the quality and effects.A few tips on how I USE IT. You might do better in a different workflow. Feel free to experiment.<ul><li>Using artist tags will stabilize the generation greatly. It is better to write them at the end of your prompt. For some reason they work better that way. The kan liu \(666k\) tag is for more similarity to the artist's style. Also you can use stabilizer LoRAs, there are plenty of them already.</li><li>2) Use a klskx tag with a weight of 1.1 for better result (in my workflow it is better smh)</li><li>3) The recommended weight of the LoRA is something I haven't fully determined myself yet. Currently using 0.75-0.85. Experiment.</li><li>4) "blurry background, depth of field, bokeh" - to create depth, this LoRA does a great job with them.</li><li>5) "dynamic pose, dutch angle" - more dynamics.</li><li>6) "outdoors, day, sunrays, sunlight" - for better lighting. I will try more tags later to update this section.</li><li>7) Sometimes ‘hydrokinesis’ and ‘water’ appear. Just add them to the negative prompt. Or in the positive if you want to see it in the picture.</li></ul>I'll probably retrain this model again, but for now, I will keep it like this.

KLSKX - Depth and Blurry

This version is inspired by the work of the wonderful artist 96yottea. Trained on edited artworks to be more gritty, sketchy, darker. So if you want style one-to-one, check out <a target="_blank" rel="ugc" href="https://civitai.com/models/966483/96yottea-style-or-illustrious">loras </a>from other authors, they work great!<ul><li>Trained on the NoobAI-XL EPS version 1.1.</li><li>No trigger word for this lora. But you can add “film grain” and “chromatic aberration” to stabilize the style.</li><li>I recommend using hires.fix + adetailer/inpaiting, because sometimes the clarity of eyes and face can be... meh.</li><li>Weight is around 0.6-0.8. I recommend using 0.7.</li><li>Works great with artist tags! This is exactly the purpose I trained lora for, so I recommend experimenting and getting interesting variations. Have fun!</li></ul>

YTSKX - Dark and Gritty

Trained on the EPS version NOOBAI-XL 1.1. Used Landscape artworks from various artists, then processed them in photoshop, setting the “mood” and few effects.Recommended Tags:<ul><li>aestx, brushstroke \(medium\)</li></ul>Available tags:<ul><li>brushstroke \(medium\), scenery, landscape,</li></ul>Additional tips:<ol><li>Trained to be used in vertical orientation, but can be used in horizontal orientation as well.</li><li>The model works more as a “tool” rather than a standalone style. I guess.</li><li>Blends well with artists' styles. Experiment!</li><li>Weight something between 0.35-1. I use 0.75-1 Feel free to experiment.</li><li>Ironic, but a poor fit for the “no humans” landscape. The f*cking samurai keeps showing up.</li><li>You can add “realistic” tag.</li><li>Quality comes after upscaling.</li></ol>

AESTX - Painting Feel

Trained on the EPS version NOOBAI-XL 1.0. Splash artwork from League of Legends was used.Recommended Tags:<ul><li>lgspx, dynamic pose, detailed background</li></ul>Available tags:<ul><li>dynamic pose, detailed background, narrow waist, wide hips, armored dress, magic, sharp fingernails</li></ul>Additional tips:<ol><li>Trained to be used in horizontal orientation, but can be used in vertical orientation as well.</li><li>The face and eyes are easily fixable with Adetailer/Inpainting.</li><li>The model works more as a “tool” rather than a standalone style. I guess.</li><li>Blends well with artists' styles. Experiment!</li><li>Weight something between 0.6-0.8. I use 0.7. Feel free to experiment.</li><li>If it is unstable, you can add another stabilizer lora.</li><li>You can add “league of legends” and “realistic” tags.</li><li>Quality comes after upscaling.</li></ol>

HL's Styles - NoobAI-XL

!!! LoRA can be difficult to use !!!

This is my first attempt at creating LoRAs, so they aren't perfect. They have some flaws and might be a bit unstable, but you can still use them.

You can find more details about each LoRA in the “About this version” section.

WAI/ILLUSTRIOUS version is here.

Many thanks to @wwHEY — I couldn’t have done it without her advice!

But she's not responsible for the crappy quality of my LoRAs. x)