Used a different training strategy than my previous Illustrious models. SilvermoonMix-Illustrious-Evolved is good at:
Stable hands
Neutral art style to work with artist tags
Multiple characters
For instructions on how to use the V-pred model, please refer to https://civarchive.com/models/833294/noobai-xl-nai-xl
Recommended settings:
Sampling method: Euler a
CFG: 4-5
Start with no negative prompt. Sample images were generated without negative prompt.
Use ADetailer extension to enhance facial details: https://github.com/Bing-su/adetailer
推荐设置：
采样方法：Euler a
CFG: 4-5
先尝试不使用负面提示词。示例图片都没有使用负面提示词。
使用 ADetailer 扩展来增强面部细节：https://github.com/Bing-su/adetailer
Change notes:
v6.0: Further enhanced lighting, prompt obedience and compatibility with LoRAs that are trained on other models.
v5.0: Lights looks more nature now. Improved logic.
v4.0: Improved compatibility with LoRAs that are trained on other models.
v3.1: Improved logic, especially background. Adjusted saturation.
Description
FAQ
Comments (9)
a heads up, RF sdxl models are coming with upto jan 2026 knowledge cutoff.
I love all the models you make. This ‘evolved’ branch is really good, especially with hands
this model really cool. very good work.
这个模型，好也不好。
好在，画师风格练得很好，人物也练得很好，光暗对比和构图也不错。
不好在，因为人物练得很好，所以你出不同动漫和游戏的人物会严重影响画风，直出就可以出比较还原原作的画风，但是如果加了画师画风，画师画风会被人物画风严重影响。
11/10 model
Can i use Z-Image-Turbo with an Rtx 2060 6gb vram?
Hi! Could you please tell me why, sometimes when generating using this model, the character (only the character—not the environment or other details, just the character being described) is colored entirely pink or red, even though this doesn’t happen with other models (at least Illustrious), even though I’m using the recommended settings?
I solved this problem on my own using GPT. It turned out that the cfg value should be set to a maximum of 4–6, whereas mine had always been 7.
Is this checkpoint any good for feet?