<a target="_blank" rel="ugc" href="https://kenshin.fandom.com/wiki/Gatotsu">Gatotsu Stance</a> Trained over 25 images for 1024 using <a target="_blank" rel="ugc" href="https://civarchive.com/models/833294?modelVersionId=1116447">NoobAI Epsilon-pred 1.1</a> as a training model<ul><li>Weight: 1 is perfect</li><li>Main Tags: fighting stance, gatotsu stance, foreshortening, holding weapon, katana</li><li>Optional Tags: hand on blade (can be a bit hit or miss)</li><li>You can make images in portrait and landscape but it works a lot better on portrait</li></ul>If you wanna support me or request a commission <a target="_blank" rel="ugc" href="https://ko-fi.com/infamousfish">ko-fi</a>Additional information:<ul><li><a target="_blank" rel="ugc" href="https://github.com/Panchovix/stable-diffusion-webui-reForge">Webui </a>I use</li><li><a target="_blank" rel="ugc" href="https://huggingface.co/Anzhc/Anzhcs-VAEs/blob/main/MS%20DPipe%20fp32%20112k%20Anime%20VAE%20SDXL.safetensors">MS DPipe fp32 112k Anime VAE SDXL</a> as VAE</li><li>Sampling method: Euler a</li><li>Schedule type: Align Your Steps</li><li>Sampling steps: 24-30</li><li>Hires steps: 12-15</li><li>Denoising strength: 0.4</li><li>Upscale by 1.2-2.0</li><li>Imagine dimensions vary depending on what I'm trying to do</li><li>I use 3 to 6 CFG Scale</li><li><a target="_blank" rel="ugc" href="https://github.com/Bing-su/adetailer">ADetailer</a> for faces</li></ul>

Files with SHA256: b8fdf50e5b6ca4b7abd6361f14dbcbbda9a162d45e5f1c9b87cd132deb791eeb