---
title: AWPortraitCN2
canonical_url: "https://www.modelscope.cn/models/LiblibAI/AWPortraitCN2"
md_url: "https://www.modelscope.cn/models/LiblibAI/AWPortraitCN2.md"
repository: LiblibAI/AWPortraitCN2
last_updated: 2025-03-30
license: other
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
parameters: 306.3M
tensor_type:
  - BF16
library_name:
  - lora
  - diffusers
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 974
stars: 4
tags:
  - text-to-image
  - stable-diffusion
  - diffusers
  - image-generation
  - flux
  - safetensors
---

# AWPortraitCN2

> AWPortraitCN2 - LiblibAI 在 ModelScope 开源的模型。The new version of AWPortraitCN2, as an upgraded version of AWPortraitCN, delves deeper into and explores a broader spectrum of Eastern aesthetics. In terms of character portrayal, it now encompasses a wider range…

LiblibAI/AWPortraitCN2 是 ModelScope 魔搭社区上的 306.3M 参数text-to-image-synthesis模型，采用 other 许可。

- **Repository**: LiblibAI/AWPortraitCN2
- **License**: other
- **Tasks**: text-to-image-synthesis
- **Parameters**: 306.3M
- **Tags**: text-to-image, stable-diffusion, diffusers, image-generation, flux, safetensors
- **Downloads**: 974
- **Stars**: 4
- **Last updated**: 2025-03-30

Source: https://www.modelscope.cn/models/LiblibAI/AWPortraitCN2

---

# AWPortraitCN2

<div class="container">
  <img src="./poster.jpg" width="1024"/>
</div>

The new version of AWPortraitCN2, as an upgraded version of [AWPortraitCN](https://huggingface.co/Shakker-Labs/AWPortraitCN), delves deeper into and explores a broader spectrum of Eastern aesthetics. In terms of character portrayal, it now encompasses a wider range of facial data across all age groups. It also responds more effectively to themes such as cuisine, architecture, environments, and a variety of traditional ethnic costumes. Whether you’re drawn to minimalist, poetic landscapes or the vibrant, everyday life of streets and neighborhoods, this update allows for a richer and more intuitive creative journey.

<div class="container">
  <img src="./cover.jpg" width="1024"/>
</div>

## Showcases
<style>
  .container {
    display: flex;
    gap: 10px; /* 图片之间的间隔 */
  }
</style>
<div class="container">
  <img src="./samples/317eec87b980d6f8f8d785a1cfaab3b482a43cd61b5122ebd1763e1a6ae6ba68.png" width="256"/>
  <img src="./samples/3cecc38c07bc12afbfa5cbc690e8b684cc34ef7d6e809cbd912d461cc14f0338.png" width="256"/>
  <img src="./samples/4569ff6307471eb4629bbd10d51d2656a7832068bbd66febcb47e7c259321b4b.png" width="256"/>
</div>
<div class="container">
  <img src="./samples/9bd338b0ae2fbc0f3f439c42bf731268696e48148f31a5056efda2b631a8294b.png" width="256"/>
  <img src="./samples/c78a685376a61cf0781ee793bbc8543f59c030673533955d818d812e97d33676.png" width="256"/>
  <img src="./samples/f08aa1b139c3586d16c406009ab7bd8415407a85ab00f95201567da76c415394.png" width="256"/>
</div>

## Trigger words
No trigger words are requireds. LoRA recommends a weight of 0.9-1.

## Acknowledgements
This model is trained by our copyrighted users [DynamicWang](https://www.shakker.ai/userpage/dfca7abc67c04a9492ea738d864de070/publish). We release this model under permissions. The model follows [flux-1-dev-non-commercial-license](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md).