Please consider joining my <a target="_blank" rel="ugc" href="https://patreon.com/Zavy376">Patreon </a>so I can keep most of my work available for everyone - I'll be releasing early access models there for a cheaper monthly fee than buying them here individually, and also will be providing exclusive models and more! For business inquiries, commercial licensing, custom models, and consultations, please get in touch at <a target="_blank" rel="ugc" href="mailto:hello@zavyai.com">hello@zavyai.com</a> or <a target="_blank" rel="ugc" href="mailto:sales@zavyai.com">sales@zavyai.com</a>. You can also contact me here through CivitAI DM or join my <a target="_blank" rel="ugc" href="https://discord.gg/jZZA4Dzmta">Discord</a>.<hr /><h1 id="introduction-z6l2d2qem">Introduction</h1>A new model line for anime, manga and western comics artworks. The primary focus is to get a mix between Disney-esque and Japanese anime style, creating an unique blend that excels at a soft tone but still very contrasting and sharp images. This model does much better without the refiner, at this point it's rather destructive than a boon. Recommended to use high-res fix and ultimate SD upscaler to get the most amazing results, but absolutely not as necessary than with photorealism models.Continue reading for more information and some tips and tricks.I kindly request that you share your creations both here and on my <a target="_blank" rel="ugc" href="https://discord.gg/jZZA4Dzmta">Discord </a>server, as I would greatly appreciate the opportunity to see them and motivate me to spend more time in further ventures here.<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/2b988a76-bd50-4f61-ac72-e5cb64b830f1/width=525/2b988a76-bd50-4f61-ac72-e5cb64b830f1.jpeg" /><h1 id="pros-and-cons-bzjwq8o1x">Pros and cons</h1><h3 id="pros-o95kyw9rt">Pros</h3><ul><li>Much better anatomy, including nsfw.</li><li>Much better teeth, eyes, hands and feet.</li><li>Generates very cute images on average.</li><li>Sharp drawn lines that are a must for anime and manga, currently much better than any other finetuned SDXL model.</li><li>Switches easily between Disney style, anime style, western comics style with the same quality.</li><li>Great tonality.</li></ul><h3 id="cons-qtkp6fqyk">Cons</h3><ul><li>Male nsfw anatomy has not been trained, needs LORAs for that. To-do for an upcoming update.</li></ul><h1 id="roadmap-a2whdfd8t">Roadmap</h1><ol><li>Training the SDXL models continuously.</li><li>Pioneering uncharted LORA subjects (withholding specifics to prevent preemption).</li></ol><h1 id="tips-n7ydv6zuj">Tips</h1><ul><li>To better understand the preferences of the model, individuals are encouraged to utilise the provided prompts as a foundation and then customise, modify, or expand upon them according to their desired objectives.</li><li>Ditch the refiner.</li><li>If you find that the details in your work are lacking, consider using one of the detail enhancer models if you’re unable to fix it with prompt alone. Wowifier or similar tools can enhance and enrich the level of detail, possibly resulting in a more compelling output.</li><li>ComfyUI is the UI I use for my SDXL images.</li><li>1.5 LORAs won't work in SDXL.</li><li>Consider finding new prompts, don't use the standard 1.5 ones. SDXL likes a combination of a natural sentence with some keywords added behind.</li><li>To maintain optimal results and avoid excessive duplication of subjects, limit the generated image size to a maximum of 1024x1024 pixels or 640x1536 (or vice versa). If you require higher resolutions, it is recommended to utilise the Hires fix, followed by the img2img upscale technique, with particular emphasis on the controlnet tile upscale method. This approach will help you achieve superior results when aiming for higher resolution outputs. However, as this workflow doesn't work with SDXL yet, you may want to use an SD1.5 model for the img2img step.</li></ul><h1 id="prompts-and-ti-jtd1v3ija">Prompts and TI</h1>Recommended positive prompts: disney style, soft outlines, magnificent, ethereal, painterly, epic, fantasy art, dreamy, or other anime related tokens.Recommended negative prompts: low quality, worst quality, lowres, monochrome, photographic, realistic, realism, 35mm film, dslr, cropped, frame, text, deformed, glitch, noise, noisy, signature, watermark, and possibly the anatomy related tokens that are not going well in your particular prompt.You are further encouraged to include additional specific details regarding the desired output. This should involve specifying the preferred style, 'camera' angle, lighting techniques, poses, color schemes, and other relevant factors.<h1 id="recommended-settings-3wwp8yyf0">Recommended settings</h1><ul><li>sdxl_vae.safetensors.</li><li>Euler A</li><li>Steps 30~50 (lower range for DPM, higher range for Euler).</li><li>Hires upscaler: 4x_foolhardy_Remacri.</li><li>Hires upscale: Whatever maximum your GPU is capable of, but preferably between 1.5x~2x.</li><li>CFG scale 4-14</li></ul><h1 id="model-recipe-5zkdyxjyy">Model recipe</h1>Trained from SDXL 1.0.<h1 id="social-media-4vey55zqy">Social media</h1>You are welcome to join my recently created <a target="_blank" rel="ugc" href="https://discord.gg/jZZA4Dzmta">Discord </a>server, where we can engage in discussions, share our experiences in AI, and showcase the things we’ve made with AI. You are encouraged to join and ask any questions or seek additional tips and tricks related to my models or AI in general. Your participation would be greatly appreciated. Furthermore, I will be releasing early testing versions of my models on <a target="_blank" rel="ugc" href="https://discord.gg/jZZA4Dzmta">Discord</a>. If you are interested in being among the first to try them out, I invite you to join the <a target="_blank" rel="ugc" href="https://discord.gg/jZZA4Dzmta">Discord </a>server.

ZavyYumeXL

First release - instant v1.0 because of how good it is.

Files with SHA256: 5ebd6720d4414ae5d6f75c0007facf5dbaef498feb84a50318ae50a10d168134