This is Illustrious-XL v0.1 - "Early Release" Illustrious XL is an advanced Stable Diffusion XL (SD XL)-based model, developed by OnomaAI Research, optimized specifically for illustration and animation tasks. It is built upon the Kohaku XL-Beta - Revision 5 checkpoint, leveraging its robust foundation to deliver high-quality generative capabilities. The full technical specifications for Illustrious XL are available in https://arxiv.org/abs/2409.19946. For detailed information and updates, please refer to https://civitai.com/models/795765/illustrious-xl Illustrious XL has been developed with resources provided by OnomaAI --- This model is extremely strong and can do things PonyXL could only do with LoRAs, they are not needed for Illustrious to make work. It has a slightly different prompting system and may require time to learn how to fully utilize it, though usual SDXL can work too. It has *LOTS* of artist styles fully built into it and has *WAY* more characters than PonyXL so character LoRAs aren't needed unless it's a super niche character. 🎲 Settings : Sampler: Euler Ancestral, Euler Ancestral CFG++ (Not in Yodayo yet) Steps: 25 - 30 CFG: 1 - 7 📈 Recommended Positives : (best quality, amazing quality, very aesthetic, absurdres), 🌟 For artist styles you can use either: "by artistname", "made by: artistname", "artist: artistname" ❗ Depending on the artist used you may probably have some accidental NSFW results ❗ 📉 Recommended Negatives : worst quality, bad quality, bad hands, very displeasing, extra digit, fewer digits, jpeg artifacts, signature, username, reference, mutated, lineup, manga, comic, disembodied, futanari, yaoi, dickgirl, turnaround, 2koma, 4koma, monster, cropped, amputee, text, bad foreshortening, what, guro, logo, bad anatomy, bad perspective, bad proportions, artistic error, anatomical nonsense, amateur, see-through, out of frame, nsfw, nude, loli, child,