Model · Civitai
XBX/AnimeXL-xuebiMIX
AnimeXL-xuebiMIX的最新版本,相比之前版本大幅度地改善了图片的光影,让图片层次感和氛围感更强 另外 本模型已经融合了LCM-LORA,无需再额外调用 ,因此使用本模型时推荐以下设置: 1. 采样算法选择Euler-a(根据琥珀大佬的意见,实测比LCM采样效果好很多) 2.迭代步数6-10即可产出高质量图片,大大加快出图速度 3.高分修复算法可自行选择尝试,迭代步数8-10为佳,重绘幅度根据算法不同自行尝试 4.CFG Scale设置3-4为佳 当然,这模型也并非完美,目前主要情况是肢体细节仍然不太理想,正在研究改进,希望大家能多多测试返图,谢谢
| Author / organization | XBX |
|---|---|
| Downloads | 14K (as reported by Civitai) |
| Likes | 1.2K |
| Task | text-to-image |
| Created | 13 December 2023 |
| Last updated at source | — |
Silytics shows public metadata from Civitai and links to the original. Information may be incomplete or out of date. Last refreshed 15 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.