My first commission workA model of Milkwarmy, trained over 94 images at 1024 using <a target="_blank" rel="ugc" href="https://civarchive.com/models/257749?modelVersionId=290640">Pony Diffusion V6 XL</a> as a training model<ul><li>Trigger word: miwalryk</li><li>Looks tags: brown eyes, long hair, black hair</li><li>Weight: 1 to 0.7 is recommended, if you're encountering an issue where you're getting selfie images when you don't want them I suggest you lower the weight to 0.6 to 0.5 and use the negative tags if you want</li><li>Negative tags: selfie, taking picture, phone, holding phone, cellphone, iphone, smartphone</li></ul>Additional information:<ul><li><a target="_blank" rel="ugc" href="https://github.com/lshqqytiger/stable-diffusion-webui-amdgpu-forge">Webui </a>I use</li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/660673/pony-standard-vae">VAE </a>I use</li><li>R-ESRGAN 4x+ Anime6B upscaler for anime</li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/141491/4x-nmkd-superscale">4x NMKD Superscale</a> upscaler for realistic</li><li>Imagine dimensions vary depending on what I'm trying to do</li><li>Sampling steps I go 20-30</li><li>hires steps I go 10-15 (I don't always use hires fix)</li><li>Denoising strength I go 0.4</li><li>I use 3 CFG Scale and <a target="_blank" rel="ugc" href="https://github.com/mcmonkeyprojects/sd-dynamic-thresholding">CFG Scale Fix</a> set at 7</li><li><a target="_blank" rel="ugc" href="https://github.com/wkpark/uddetailer">uddetailer</a> for faces</li></ul>If you wanna support me <a target="_blank" rel="ugc" href="https://ko-fi.com/infamousfish">ko-fi</a>

Files with SHA256: 259449092f0436a6fa89e8e665463ec5ce77a4346f50c184eaf82fcb3db92965