[SD 1.5][LORA]Objection! (Ace Attorney) LoRA objection
<h2>Objection! (Ace Attorney) LoRA</h2><p><strong>Making models is expensive. Do you like what I do? Feel free to </strong><a target="_blank" rel="ugc" href="https://www.buymeacoffee.com/lykon"><strong>buy me a coffee</strong></a><strong> ☕</strong></p><p>Just an experiment with a very dirty dataset. Turned out better than expected, so I'm still gonna post it for the lol. Requires some triggers with <code>objection, ace attorney, pointing</code> and if you add <code>phoenix wright</code> you can also get the character (and the style changes a lot, I made an example with and without, which are the first image and the very last one). I used Anything4.5 as base model because it doesn't add too much style, but you're welcome to try other models.</p><p>Of course SD will never get the words correctly, but it should be easy to inpaint or just photoshop.</p><p>Have fun!</p><p><br /><strong>How to use LoRA's in auto1111:</strong></p><ul><li><p>Update webui (use <code>git pull</code> <a target="_blank" rel="ugc" href="https://www.youtube.com/embed/mn8fMF10XN4?start=31&end=60">like here</a> or redownload it)</p></li><li><p>Copy the file to <code>stable-diffusion-webui/models/lora</code></p></li><li><p>Select your LoRA like in <a target="_blank" rel="ugc" href="https://www.youtube.com/watch?v=-bMeyXOZwN0">this video</a></p></li><li><p><strong>Make sure to change the weight</strong> (by default it's <code>:1</code> which is usually too high)</p></li></ul>
页:
[1]