This is my first model mix. :)DLADmix's objective is to be able to do art with a 2.5d/Semi-realistic feeling. I created a <a target="_blank" rel="ugc" href="https://discord.gg/RkuBguCE">Discord</a> server where you can post images that you generated, discuss prompts and/or ask for help. <a target="_blank" rel="ugc" href="https://discord.gg/mM8HF5UWfu">https://discord.gg/mM8HF5UWfu</a>I also have a <a target="_blank" rel="ugc" href="https://ko-fi.com/diffusionlad">ko-fi</a> and <a target="_blank" rel="ugc" href="https://www.patreon.com/DiffusionLAD">Patreon </a>page where you can support me or buy me a coffee, it will be very much appreciated: <a target="_blank" rel="ugc" href="https://ko-fi.com/diffusionlad">https://ko-fi.com/diffusionlad</a> and <a target="_blank" rel="ugc" href="https://www.patreon.com/DiffusionLAD">https://www.patreon.com/DiffusionLAD</a>Recommendations of use: --------------------------------------------------------------------------------Use Hires.Fix for better but You can use imgtoimg UpscaleHires.fix is needed to drastically improve the quality of face and eyes! All of the sample images were generated in 512x768/1024 and upscaled 2x twice, hires and extra. -------------------------------------------------------------------------------- Recommendations: Sampler: Eular a, 20 to 30 steps. CFG Scale: 7-9. Resolutions: 512x768, 512x1024 for Portrait Resolutions: 768x512, 1024x512, 1536x512 for Landscape Hires.fix: <a target="_blank" rel="ugc" href="https://mega.nz/file/Wh1FWZzK#Uhlhclyt3UQwm_WCQ_852dXmXxZ4fgGcetYcWdcZYuk">4x-Animesharp</a>, with 20 to 30 steps at 0.3 up to 0.5 denoising. Clip Skip: 1 or 2. You can use any ClipSkip but for anime images use ClipSkip 2 Negatives: (bad-artist:1.0), (loli:1.2), (worst quality, low quality:1.4), EasyNegative, ((Bad-hands-5))

Files with SHA256: f613600e435683c34007542745ea2f5ea4cbd24e55ce98b219692e393c2e5324