A model of <a target="_blank" rel="ugc" href="https://bloodborne.fandom.com/wiki/Bloodborne">Bloodborne</a>, trained over 67 images from in-game screenshots or concept art of the game for 1024 using <a target="_blank" rel="ugc" href="https://civarchive.com/models/353543/aaaaaaaaaaaaaaaaaaaaaaa-or-finetune-mix-on-whatever-model-i-want-at-that-point-which-is-illustrious-xl-right-nowbut-i-will-keep-pony-one-for-on-site-as-well">AAA</a> as a training model, might do another version where I only use fanart but that's for the future<ul><li>Trigger word: bloodstyleborne</li><li>Weight: 1 is perfect starting point, you can go as high as 1.5 and achieve even more horror if you want</li><li>Addtional tags: bloodborne, scenery, sky, building, city, night sky, tower, star \\(sky\\), starry sky, city lights, moon</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/353543/aaaaaaaaaaaaaaaaaaaaaaa-or-finetune-mix-on-whatever-model-i-want-at-that-point-which-is-illustrious-xl-right-nowbut-i-will-keep-pony-one-for-on-site-as-well">AAA Anime VAE SDXL v1_4</a> as VAE</li><li>Sampling method: Euler a</li><li>Schedule type I set it to automatic</li><li>Sampling steps I go 20-30</li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/116225/4x-ultrasharp">4x-Ultrasharp</a> as an Upscaler</li><li>Hires steps I go 8-15 (I don't always use hires fix)</li><li>Denoising strength I go 0.4</li><li>Upscale by 1.2 to 1.5 depending on the starting image dimensions</li><li><a target="_blank" rel="ugc" href="https://github.com/muerrilla/sd-webui-detail-daemon">Detail Daemon</a> at default settings</li><li>Imagine dimensions vary depending on what I'm trying to do</li><li>I use 5 CFG Scale and <a target="_blank" rel="ugc" href="https://github.com/mcmonkeyprojects/sd-dynamic-thresholding">CFG Scale Fix</a> set at 9</li><li><a target="_blank" rel="ugc" href="https://github.com/wkpark/uddetailer">uddetailer</a> for faces, I use mediapipe_face_mesh set Dilation to 50 and Y offset to 30 to get the full face</li></ul>If you wanna support me <a target="_blank" rel="ugc" href="https://ko-fi.com/infamousfish">ko-fi</a>

Bloodborne Style

Bloodborne_style.safetensors

1077818_training_data.zip

A model of <a href="https://bloodborne.fandom.com/wiki/Bloodborne" rel="ugc noopener noreferrer nofollow" target="_blank">Bloodborne</a>, trained over 67 images from in-game screenshots or concept art of the game for 1024 using <a href="https://civitai.com/models/353543/aaaaaaaaaaaaaaaaaaaaaaa-or-finetune-mix-on-whatever-model-i-want-at-that-point-which-is-illustrious-xl-right-nowbut-i-will-keep-pony-one-for-on-site-as-well" rel="ugc noopener noreferrer nofollow" target="_blank">AAA</a> as a training model, might do another version where I only use fanart but that's for the future<ul><li>Trigger word: bloodstyleborne</li><li>Weight: 1 is perfect starting point, you can go as high as 1.5 and achieve even more horror if you want</li><li>Addtional tags: bloodborne, scenery, sky, building, city, night sky, tower, star \\(sky\\), starry sky, city lights, moon</li></ul>Additional information:<ul><li><a href="https://github.com/lshqqytiger/stable-diffusion-webui-amdgpu-forge" rel="ugc noopener noreferrer nofollow" target="_blank">Webui </a>I use</li><li><a href="https://civitai.com/models/353543/aaaaaaaaaaaaaaaaaaaaaaa-or-finetune-mix-on-whatever-model-i-want-at-that-point-which-is-illustrious-xl-right-nowbut-i-will-keep-pony-one-for-on-site-as-well" rel="ugc noopener noreferrer nofollow" target="_blank">AAA Anime VAE SDXL v1_4</a> as VAE</li><li>Sampling method: Euler a</li><li>Schedule type I set it to automatic</li><li>Sampling steps I go 20-30</li><li><a href="https://civitai.com/models/116225/4x-ultrasharp" rel="ugc noopener noreferrer nofollow" target="_blank">4x-Ultrasharp</a> as an Upscaler</li><li>Hires steps I go 8-15 (I don't always use hires fix)</li><li>Denoising strength I go 0.4</li><li>Upscale by 1.2 to 1.5 depending on the starting image dimensions</li><li><a href="https://github.com/muerrilla/sd-webui-detail-daemon" rel="ugc noopener noreferrer nofollow" target="_blank">Detail Daemon</a> at default settings</li><li>Imagine dimensions vary depending on what I'm trying to do</li><li>I use 5 CFG Scale and <a href="https://github.com/mcmonkeyprojects/sd-dynamic-thresholding" rel="ugc noopener noreferrer nofollow" target="_blank">CFG Scale Fix</a> set at 9</li><li><a href="https://github.com/wkpark/uddetailer" rel="ugc noopener noreferrer nofollow" target="_blank">uddetailer</a> for faces, I use mediapipe_face_mesh set Dilation to 50 and Y offset to 30 to get the full face</li></ul>

Files with SHA256: d06075ed4e0dbca3a8f649c02c15225f89182f272b4d3e26c0db5cf3b4ec4208