版本介绍/Version Overview：

v1.0：Features delicate skin textures, aesthetically pleasing default face shapes and body proportions, along with stable limb generation and richly detailed backgrounds.

🎨 Model Overview / 模型简介

​这是一个能够稳定产出统一画风的模型，角色兼具细腻真实的皮肤质感与出色的视觉表现。由于融入了特定 LoRA 增强画风稳定性，它能稳定呈现体态匀称、线条优美的男性与女性角色。所使用的模型与 LoRA 详情请参考下方的“制作思路与说明”。

​This model reliably produces a cohesive art style with rich skin textures and polished character aesthetics. Enhanced with specific LoRAs for stylistic consistency, it excels at generating male and female characters with well-proportioned, graceful physiques. Check the "Creator's Note & Model Story" below for the exact models and LoRAs utilized.

⚙️ Recommended Generation Settings / 推荐生成设置

Steps: 30

CFG Scale: 4.0 - 5.0

📝 Prompts / 提示词词条

Positive Prompt (Default) / 正向提示词（默认）:

best quality, score 7, score 9, sensitive, very aesthetic, ultra detailed, {Add Prompt here / 此处添加你的提示词}

Negative Prompt / 反向提示词:

worst quality, low quality, lowres, score 1, score 2, score 3, jpeg artifacts, bad anatomy, watermark, artist name, weibo watermark, toon \(style\), painterly, censor

——————

💡 Creator's Note & Model Story / 制作思路与说明

在使用 Anima 的期间，我一直想要复刻一种稳定的画风。但是奈何使用纯 LoRA 的话可能需要叠加 6-7 个画风 LoRA，如果再加上细节 LoRA、滑块 LoRA，最终生成一张图可能会需要用到 10-20 个 LoRA。而 LoRA 加载得越多，模型的语义理解能力就会下降很多。因此我在思考：如果将大模型进行融合来初步还原底层画风呢？经过一段时间的测试，效果确实比叠加 6-7 个画风 LoRA 更好。

While using Anima, I had been trying to recreate a stable art style. However, relying purely on LoRAs meant stacking 6–7 style LoRAs. Add in detail LoRAs and slider LoRAs, and generating a single image could require 10–20 LoRAs in total. The more LoRAs loaded, the worse the model's text comprehension (prompt adherence) becomes. This made me wonder: what if I merged Checkpoints to recreate the underlying style first? After a period of testing, the results were indeed much better than stacking 6–7 style LoRAs.

🧩 Merged Checkpoints / 融合的大模型

• MiaoMiao Harem 1.6

• Adonis Anima 2.0

• Q-ANIMA 2.0

Q-ANIMA 是我最喜欢的 Anima 模型，它本身就拥有符合我审美的画风和稳定的肢体与构图。因此我选择了一个稳定且强大的模型以及一个男性模型来进行 Merge，稍微微调了一下 Q-ANIMA 的原始画风，但构图方面依然保持偏向 Q-ANIMA 本身。

Q-ANIMA is my favorite Anima model, naturally featuring an aesthetic that matches my taste along with solid anatomy and composition. I merged it with a robust general model and a dedicated male model to subtly refine the original art style, while keeping the composition strongly aligned with Q-ANIMA.

🎨 Integrated LoRAs / 融合的 LoRA

此外，在大模型 Merge 完成后，我也融入了2-3个特定 LoRA 来进一步稳固画面的细节。除了我自己制作的 LoRA 外，还包含了其他创作者的优质 LoRA：

Additionally, after merging the base checkpoints, I baked in 2–3 specific LoRAs to further stabilize the fine visual details. Alongside my own custom LoRA, this includes high-quality LoRAs crafted by other creators:

• Anima - Jock Studio / Zael / Mikkoukun | Style

❤️ Credits & Acknowledgments / 致谢

综上，非常感谢这些大模型制作者和 LoRA 制作者！(●'◡'●)

All in all, huge thanks to all the amazing Checkpoint and LoRA creators mentioned above! (●'◡'●)