🦑 Ikastrious 🦑
クリアな線と発色が特徴の、高品質な汎用アニメモデル
A high-quality, versatile anime-style model featuring clear linework and vibrant colors.
--prompt--
(explicit|general), masterpiece, best quality, anime coloring (if you need)
--negative--
lowres, worst quality, bad quality, worst detailRecommend Settings
Sampling method & Schedule type: Euler a & automatic
Sampling steps: 10~40
CFG Scale: 4~7
Resolution: 1024x1024, 896x1152, 832x1216 / 1216x1216, 1024x1344,
My Favorite Settings:
Sampler: Euler a, Schedule type: Automatic, Steps: 27, CFG scale: 4.5
Hires upscaler: 4x-UltraSharpV2_Lite (fast!) or 4x-AnimeSharp
Hires steps: 10, Denoising strength: 0.2, Hires upscale: 1.5, Hires CFG Scale: 1Description
v14.2
安定性の向上を図りました。Hires. fixを使用しなくてもそこそこきれいな線が出ます
Improved stability. Even without using Hires. fix, you can get reasonably clean lines.
raehoshiIllustXL_v51x0.6+((novaAnimeXL_ilV90x1.2+matureRitual_v069x-0.2)x0.85+toonify_Illustriousx0.15)x0.4
FAQ
Comments (3)
IF YOU ARE HAVING PROBLEMS WITH YOUR IMAGE COMING OUT TOO FLAT/LOW DETAIL:
Try putting in the negative prompt "flat color, high contrast, muted color, pale color, flat shading, plain shading" and see which ones work best. This usually happens when a lora is trained on mostly screencaps or overtrained in general. (Was using v14.2 when testing these)
Consider putting in the negative prompt "scan, scan artifacts, color issue" as they generally improve the output
Also for some reason simply adding "beautiful, gorgeous" (positive prompt) will create more detailed images for better or worse (might deviate from style you are looking for).
How do I unlock this?
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.