Maintaining a stable diffusion model is very resource-burning. Please consider supporting me via <a target="_blank" rel="ugc" href="https://ko-fi.com/kayfahaarukku">Ko-fi</a>.KayWaii will ALWAYS BE FREE.Welcome to KayWaii, an anime-oriented model. This model is very capable of generating anime girls with thick line art.The model uses similar merging methods used to merge AingDiffusion, a powerful anime model, also merged by me.<h2 id="guide-to-generate-good-images-with-this-model">Guide to generating good images with this model</h2><ul><li>Use the VAE I included with the model. To set up VAE, <a target="_blank" rel="ugc" href="https://stable-diffusion-art.com/how-to-use-vae/#Install">you can refer to this guide</a>.</li><li>Use <a target="_blank" rel="ugc" href="https://civarchive.com/models/7808/easynegative">EasyNegative</a> (NOT EasyNegativeV2, it broke the hand fix I applied) for negative prompts (highly recommended), you can add other embeddings and negative prompts alongside it as well.</li><li>IMPORTANT: The recommended sampler is "DPM++ SDE Karras" for KayWaii v2.1 and up.</li><li>Hi-res fix is a must if you want to generate high-quality and high-resolution images. For the upscaler, I highly recommend SwinIR 4x or 4x-AnimeSharp.</li><li>Important: I spotted an issue that in a rare case, the VAE broke the upscaled output. You can set the VAE to "None" if the issue occurs.</li><li>Set Clip skip to 2, ENSD (eta noise seed delta) to 31337 and eta (noise multiplier) for ancestral samplers to 0.667.</li></ul><h2 id="heading-705">FAQ</h2>Q: What's up with the frequent updates?A: AingDiffusion and KayWaii are models I use daily, not something I merge just to gain popularity or for the sake of download count. I made constant efforts to improve the model whenever possible and wanted to share the improvements as quickly as possible.Q: I can't generate good images with your model.A: The first thing to remember is that every little change matters in the world of Stable Diffusion. Try adjusting your prompt, using different sampling methods, adding or reducing sampling steps, or adjusting the CFG scale.Q: What's the difference between AingDiffusion and KayWaii?A: The difference between AingDiffusion and KayWaii lies in their goals and styles. AingDiffusion aims to create an anime-style output with a touch of pastel aesthetics, as I appreciate how pastel art is colored. Back then, the art style of the pastel model available didn't suit my preferences. On the other hand, KayWaii was initially intended to generate cute girls.Here's a comparison:<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/fedd819e-4eb9-40c8-8bf9-8548e9e3bdf3/width=525/fedd819e-4eb9-40c8-8bf9-8548e9e3bdf3.jpeg" />Keep experimenting and have fun with the models! 😄

KayWaii

I work on this for approx. a week, with 69 work hours total (no joke, it's really is 69).Better foreground performance(?)There's something you should know:<ul><li>The model output is slightly burn on some cases. Hi-res fix have a little chance to "fix" it, but sometimes no.</li><li>Background is a mess. I work on this like, 4 days alone and still cannot resolve the issue. The model works better with simple backgrounds.</li><li>I'm lacking resources that I can merge into. Standard anime models with better backgrounds and linearts break the "kawaii" factor, so I cannot use them to fix the minuses I mention above.</li></ul>I wanna give up on KayWaii, but I also don't wanna give up at the same time.Maybe I should took a long rest after this. My poor RTX 2060 also need some rest I guess.Thank you.

Files with SHA256: d0dcf618c7f3317cae3610a052301a5b101be674fbb492d6c7c9aca2becec0c5