HerRAW-zimage-v0.2

HerRAW - Z-Image v0.2 | 女性摄影 LoRA

HerRAW 是一个面向 Z-Image 的通用女性真实摄影 LoRA，目标是在尽量保持原始 Prompt、人物特征、构图和场景控制能力的前提下，提升女性人像的自然摄影质感。

本模型无需触发词。加载 LoRA 后，可以直接使用正常的自然语言 Prompt 进行生成。

v0.2 是 HerRAW 的 Z-Image 版本，基于 Z-Image 基座（Tongyi-MAI/Z-Image）训练，训练至 5000 步。

---

HerRAW is a general-purpose female photography LoRA for Z-Image, designed to improve natural photographic realism while preserving as much of the original prompt, subject characteristics, composition, and scene control as possible.

The model requires no trigger word. Simply load the LoRA and use normal natural-language prompts.

v0.2 is the Z-Image flavor of HerRAW, trained on the Z-Image base model (Tongyi-MAI/Z-Image) for 5000 steps.

---

Training details

Usage (ComfyUI)

1. Load the Z-Image base checkpoint (Tongyi-MAI/Z-Image).
2. Add a Load LoRA node and select HerRAW-zimage-v0.2.safetensors.
3. Set the LoRA strength to taste (start low and adjust).
4. Generate with normal natural-language prompts — no trigger word needed.

Files

License

other — LoRA weights trained on top of the Z-Image base model (Apache-2.0). See Tongyi-MAI/Z-Image for the base model terms.