[SD 1.5][LORA]Akari Watanabe V1.0
<p><strong>This is my new Model! If you want your own style/person trained, just DM me with a dataset of ~20 imgs on discord Flonix#4022 and ill train it for you!</strong></p><p>Lora made on Capivara's Akira Dataset, set the weight lower than 1 to get it to follow your prompt more. Also remember to <strong>set CLIP skip to 2</strong>.</p><p></p><p>example prompt:</p><p>in the distance ona hill, akariWatanabe anime woman, wedding dress<br />Negative prompt: hands<br />Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 2494829530, Size: 512x624, Model hash: a7bd5ab091, Denoising strength: 0.36, Clip skip: 2, ENSD: 31337, AddNet Enabled: True, AddNet Module 1: LoRA, AddNet Model 1: akariWatanabe(a99b2cfff4c1), AddNet Weight A 1: 1, AddNet Weight B 1: 1, Hires upscale: 2, Hires upscaler: 4x_foolhardy_Remacri<br />Keep in mind <strong>this is a LoRA</strong>, so you need to use it as such. It's not a standalone model and it's not a TI.<br /><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><p>usage by <a target="_blank" rel="ugc" href="https://civitai.com/user/Lykon">@Lykon</a></p>
页:
[1]