一个效果不错的lora模型，第一次基于SDXL为底模训练的模型，意外的效果不错。
模型权重在0.5~0.9之间都有不错的效果，欢迎多多进行返图。
推荐采样步数Steps: 30,
推荐采样方法Sampler: DPM++ 2M SDE Karras,
CFG scale: 7,
Description
FAQ
Details
Downloads
178
Platform
SeaArt
Platform Status
Available
Created
4/1/2024
Updated
9/30/2025
Deleted
-
Trigger Words:
JSM
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.