A very powerful LoRA trained to recreate many styles and concepts, based on League of Legends splash art. This is not meant to just be a "set it and forget" it LoRA, you need to use it properly. Read below. I recommend starting with this default prompt: POSITIVE<pre><code>l0lspl4sh, source_anime, score_9, score_8_up, score_7_up, year2024, year2023, West Studio, sixmorevodka, {prompt}</code></pre>NEGATIVE<pre><code>score_4, score_5, year2009, year2010, year2011, year2012, year2013, year2014, crazy eyes, constricted pupils, legacy, {prompt}</code></pre>This LoRA really loves highres fix, as it brings out a ton of detail. Additionally, i can only recommend using <a target="_blank" rel="ugc" href="https://github.com/Bing-su/adetailer">Adetailer</a>, to get perfect faces.I recommend using these parameters: <img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/cb216cf4-4a1c-4aad-9808-50b9368d275e/width=525/cb216cf4-4a1c-4aad-9808-50b9368d275e.jpeg" /> The recommended prompt "template" is as follows:<pre><code>l0lspl4sh, source_anime, score_9, score_8_up, score_7_up, &lt;yearXXXX&gt;, &lt;CHARACTER|1girl/1boy&gt;, &lt;SKIN NAME 1girl&gt;, &lt;SKIN SERIES&gt;, &lt;Artist1&gt;, &lt;Artist2&gt;, &lt;general tags&gt;</code></pre>The images were tagged exactly as they appear on the <a target="_blank" rel="ugc" href="https://leagueoflegends.fandom.com/wiki/Ahri/LoL">league of legends wiki</a>: <img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/58630b42-8267-487a-b5f3-cb4efd6441ae/width=525/58630b42-8267-487a-b5f3-cb4efd6441ae.jpeg" />So if you're going for something specific, maybe look up skins for inspiration from the wiki.The model was trained on 3000~ appropriately tagged images, with many new concepts introduced. Take a look at the wordclouds below to see which tags are most prominent in the training set. (the bigger the words, the more images had the tags) Artist Name<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/cad6bf09-5280-4630-8a10-1b0b3f1c57b3/width=525/cad6bf09-5280-4630-8a10-1b0b3f1c57b3.jpeg" />Release Date<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/8fb3614f-8722-4aae-9901-571e727c13e6/width=525/8fb3614f-8722-4aae-9901-571e727c13e6.jpeg" />Skin Name <img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/ee640f67-0a64-43c6-a6f8-fab55e7e2273/width=525/ee640f67-0a64-43c6-a6f8-fab55e7e2273.jpeg" />Skin Series<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/5152a66c-c058-45f5-a003-89396b0fa990/width=525/5152a66c-c058-45f5-a003-89396b0fa990.jpeg" />

League of Legends / LoL Splash | PDXL | Style LoRA

"Initial" version. Many iterations in, the first I think is ready. Unlikely to be updated.

L0LSPL4SH_40epochs.safetensors

v1.0

A very powerful LoRA trained to recreate many styles and concepts based on League of Legends splash art.This is not meant to just be a "set it and forget" it LoRA, you need to use it properly. Read below.I recommend starting with this default prompt: POSITIVEl0lspl4sh, source_anime, score_9, score_8_up, score_7_up, year2024, year2023, West Studio, sixmorevodka, {prompt}NEGATIVEscore_4, score_5, year2009, year2010, year2011, year2012, year2013, year2014, crazy eyes, constricted pupils, legacy, {prompt}This LoRA really loves highres fix, as it brings out a ton of detail. Additionally, i can only recommend using Adetailer to get perfect faces.The recommended prompt "template" is as follows:l0lspl4sh, source_anime, score_9, score_8_up, score_7_up, &lt;yearXXXX&gt;, &lt;CHARACTER|1girl/1boy&gt;, &lt;SKIN NAME 1girl&gt;, &lt;SKIN SERIES&gt;, &lt;Artist1&gt;, &lt;Artist2&gt;, &lt;general tags&gt;The images were tagged exactly as they appear on the <a target="_blank" rel="ugc" href="https://leagueoflegends.fandom.com/wiki/Ahri/LoL">League of Legends wiki</a>. So if you're going for something specific, maybe look up skins for inspiration from the wiki.The model was trained on 3000~ appropriately tagged images, with many new concepts introduced.

THIS IS A REPRINT!

Go to original author to check their other models or to support them.

Files with SHA256: 37d5738bc15d5b87b957003deaed30815e3556d348063191c75a3f040e212c39