SDXL
TovaMix - Ultimate Illustrious & NoobAI Hybrid [Anime/Furry/Realism] v1.6
- 上傳時間
- 2026年7月9日 凌晨1:01
- 使用數
- 2.94k
- 評論
- 非常好 (1)
- 取樣步數
20
- 取樣方式
Euler a
- CFG Scale
5
- 許可權
- 允許圖片生成與分享
- 允許使用者下載此模型
- 允許生成圖片用於商業用途
描述
v.1.6 Thank you for choosing TovaMix for your image generation all these months. I originally made this merge for myself just to combine my favorite models, and I never expected so many people to appreciate my work. It gave me the motivation to keep experimenting! Version 1.6 (or hybrid_v20/16c) is my final attempt to get the best possible results from Illustrious XL and NoobAI before Anima and Krea 2 take over, just as it happened with Pony XL. This version keeps all the features from v1.1 and adds prompt adherence similar to XAVIER. The recommendations are the same as for previous versions, except for the Negative Prompt, which has become a bit more sensitive to weights.
Key Features: Works very well in a wide range of artistic styles, including anime, furry, semi-realistic and realistic. Does everything other checkpoints based on NoobAI (Epsilon-pred) and Illustrious XL do, so your usual prompts will work just fine. Fully compatible with LoRAs for these models, and also works with some LoRAs for Pony XL! Create your own unique styles by adding artists to the prompt: (by [artist name a]:1.0), (by [artist name b]:0.9), etc. Models used for the merge (v1.0): Indigo Furry Mix XL, WAI-illustrious-SDXL, WAI-Mature-illustrious, XAVIER. Recommended Settings: Sampler: Euler a, Euler Scheduler: Automatic, Normal, Simple Steps: 15-40 CFG Scale: 4-7 Clip Skip: 2 Hires upscaler: R-ESRGAN 4x+ Anime6B Prompt: masterpiece, best quality, highres, absurdres... Since this is a mix of anime and furry models, it primarily uses tags from Danbooru and e621. Negative Prompt: 3d, sketch, (worst quality, low quality:1.2), bad anatomy, bad hands, bad fingers, (signature:1.3), (artist name:1.2), (patreon link), jpeg artifacts, (watermark:1.3), lowres, artist logo, (text:1.3),