模型卡片 / Model Card

模型名称 / Model Name: yoiko_style_model
基础模型 / Parent Model: WAI-NSFW-illustrious-SDXL Ver15.0
许可证 / License: Illustrious License
训练数据 / Training Data: 我生成的图像（包括未公开的）/ Images generated by me (including some not publicly released)

---

介绍文（日语）

本模型是在 WAI-NSFW-illustrious-SDXL Ver15.0 的基础上，通过额外的 SFT（监督微调） 进行优化的公开基础模型。
其画风与过去的 yoiko_lora_OD 接近，这是因为训练数据和使用的图像来源相似，我旨在更细致地更新 yoiko_lora_OD 所具有的底层表现权重。

此外，我还特别关注了减少图像瑕疵的问题。尽管改进有限，但通过提升训练图像的质量与数量来实现优化，最终使用的图像量约为 LoRA 阶段的 3 至 4 倍，生成图像中的明显瑕疵已大幅减少。

模型名称中的“kadenz”源自音乐术语，意为“终止”或“终结”。
我选择这个名字，是想表达：本模型既是某个阶段的终点，也是新起点的开端。
我对模型的完成度充满信心，但若存在任何问题，敬请谅解。

我选择 WAI-NSFW-illustrious-SDXL Ver15.0 作为基础，不仅因其压倒性的完成度，更因为其许可证相比“noob ai”类模型更为宽松，允许更广泛的试验与调整。
尽管命名为“kadenz”，生成图像的品质仍存在未知因素，恳请各位提供反馈。

那么，请尽情使用吧。

---

描述（英语）

This model is a public base release built upon WAI-NSFW-illustrious-SDXL Ver15.0, with additional Supervised Fine-Tuning (SFT) applied.
Its visual style is similar to yoiko_lora_OD, as both share comparable training data and image sources. The goal was to refine and update the lower-level representational weights that define the yoiko_lora_OD aesthetic.

Another key objective was reducing visual artifacts.
While the improvements are incremental, I increased both the quality and quantity of training images—using roughly 3 to 4 times more images than in the LoRA stage. This helped significantly reduce visible breakdowns in generated outputs.

The name “kadenz” comes from a musical term meaning cadence or closure.
I chose it because this model represents both an ending and a new beginning in my development cycle.
I’m confident in its completeness and balance—but if you find any issues, my apologies in advance.

I selected WAI-NSFW-illustrious-SDXL Ver15.0 as the foundation for its exceptional quality and flexible licensing, which allows for broader experimentation compared to some noob ai variants.
Even so, as the name kadenz suggests, the output quality may still hold unknowns—so your feedback is very welcome.

Enjoy creating with it.