---
title: AWPortrait-Z
canonical_url: "https://www.modelscope.cn/models/LiblibAI/AWPortrait-Z"
md_url: "https://www.modelscope.cn/models/LiblibAI/AWPortrait-Z.md"
repository: LiblibAI/AWPortrait-Z
last_updated: 2026-06-16
license: apache-2.0
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
base_model:
  - Tongyi-MAI/Z-Image-Turbo
base_model_relation: adapter
parameters: 340.1M
tensor_type:
  - BF16
library_name:
  - lora
  - diffusers
  - safetensors
  - pytorch
frameworks:
  - pytorch
supports_inference: txt2img
downloads: 3786
stars: 35
tags:
  - text-to-image
  - lora
  - diffusers
  - z-image
---

# AWPortrait-Z

> AWPortrait-Z - LiblibAI 在 ModelScope 开源的模型。AWPortrait-Z is a portrait-beauty LoRA meticulously built on the Z-Image.

LiblibAI/AWPortrait-Z 是 ModelScope 魔搭社区上的 340.1M 参数text-to-image-synthesis模型，采用 apache-2.0 许可，基于 Tongyi-MAI/Z-Image-Turbo 构建，并支持在线推理（txt2img）。

- **Repository**: LiblibAI/AWPortrait-Z
- **License**: apache-2.0
- **Tasks**: text-to-image-synthesis
- **Parameters**: 340.1M
- **Base model**: Tongyi-MAI/Z-Image-Turbo
- **Online inference**: txt2img
- **Tags**: text-to-image, lora, diffusers, z-image
- **Downloads**: 3786
- **Stars**: 35
- **Last updated**: 2026-06-16

Source: https://www.modelscope.cn/models/LiblibAI/AWPortrait-Z

---

# AWPortrait-Z

AWPortrait-Z is a portrait-beauty LoRA meticulously built on the [Z-Image](https://huggingface.co/Tongyi-MAI/Z-Image-Turbo).

- Native-noise reduction: fixed Zimage’s chronic grain—those downy, high-frequency artifacts that plagued skin tones—so complexions now look flawlessly real.
- Relit lighting: tamed the base model’s excessive HDR, restoring punchy contrast and saturation; re-engineered artificial-light behavior so studio strobes sit naturally in-scene instead of floating above it.
- Diverse faces: expanded multi-ethnic feature coverage, breaking the “same-face” barrier and delivering portraits that are both authentic and unmistakably individual.

## Showcases
<div class="container">
  <img src="./images/example.png" width="1024"/>
</div>

## Comparison
<div class="container">
  <img src="./images/compare.png" width="1024"/>
</div>


## Acknowledgements
This model is released by [DynamicWang](https://www.liblib.art/userpage/43d9ee875a6288176ac10d689a2770c7/publish).