You can use the same settings from SD 1.5 for PonyA lora model of <a target="_blank" rel="ugc" href="https://www.instagram.com/alexa_bliss_wwe_/">Alexa Bliss</a>, Trained over 91 pictures at 768<ul><li>Trigger word: Alexa Bliss</li><li>Weight: 1 to 0.4 (0.6 is recommended)</li><li>Optional tags: blue eyes, long hair, multicolored hair, pink hair, blonde hair</li></ul>Additional information:<ul><li>You can see the models I have used/recommend below</li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/118561?modelVersionId=131658">VAE </a>I use</li><li>For anime I use R-ESRGAN 4x+ Anime6B upscaler</li><li>For realistic I use <a target="_blank" rel="ugc" href="https://civarchive.com/models/141491/4x-nmkd-superscale">4x NMKD Superscale</a> upscaler</li><li>For semi-realistic I use <a target="_blank" rel="ugc" href="https://civarchive.com/models/116225/4x-ultrasharp">4x-Ultrasharp</a> upscaler</li><li>For Sampling steps I go 40-50</li><li>For Hires steps I go 10-15</li><li>For Denoising strength I go 0.45-0.6</li><li>I use 3-9 CFG Scale for my pics</li></ul>If you wanna support me <a target="_blank" rel="ugc" href="https://ko-fi.com/infamousfish">ko-fi</a>

Files with SHA256: dae8646e8cc2f153f240d89b5d2583af1e4b45e2bf20fc4f4c73979a5386b5ce