---
title: AWPortrait-QW
canonical_url: "https://www.modelscope.cn/models/LiblibAI/AWPortrait-QW"
md_url: "https://www.modelscope.cn/models/LiblibAI/AWPortrait-QW.md"
repository: LiblibAI/AWPortrait-QW
last_updated: 2026-06-16
license: apache-2.0
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
base_model:
  - Qwen/Qwen-Image
base_model_relation: adapter
parameters: 235.9M
tensor_type:
  - BF16
library_name:
  - pytorch
  - lora
  - diffusers
  - safetensors
frameworks:
  - pytorch
language:
  - en
supports_inference: txt2img
downloads: 431
stars: 3
tags:
  - text-to-image
  - lora
  - diffusers
  - "template:diffusion-lora"
  - qwen-image
---

# AWPortrait-QW

> AWPortrait-QW - LiblibAI 在 ModelScope 开源的模型。AWPortrait-QW is based on the Qwen-Image. It's trained using a training set that better reflects Chinese facial features and aesthetics. It covers a wide range of genres, including indoor and outdoor portraits,…

LiblibAI/AWPortrait-QW 是 ModelScope 魔搭社区上的 235.9M 参数text-to-image-synthesis模型，采用 apache-2.0 许可，基于 Qwen/Qwen-Image 构建，并支持在线推理（txt2img）。

- **Repository**: LiblibAI/AWPortrait-QW
- **License**: apache-2.0
- **Tasks**: text-to-image-synthesis
- **Parameters**: 235.9M
- **Base model**: Qwen/Qwen-Image
- **Online inference**: txt2img
- **Tags**: text-to-image, lora, diffusers, template:diffusion-lora, qwen-image
- **Downloads**: 431
- **Stars**: 3
- **Last updated**: 2026-06-16

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

---

# AWPortrait-QW

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

AWPortrait-QW is based on the Qwen-Image. It's trained using a training set that better reflects Chinese facial features and aesthetics. It covers a wide range of genres, including indoor and outdoor portraits, fashion, and studio portraits, ensuring strong generalization. Compared to the original Qwen-Image, AWPortrait-QW delivers a more detailed and realistic rendering of skin texture.

## Showcases
<Gallery />

## Trigger words

No trigger words are requireds. LoRA recommends a weight of 1.0.

## Inference

```python
import torch
from diffusers import QwenImagePipeline

pipe = QwenImagePipeline.from_pretrained("Qwen/Qwen-Image", torch_dtype=torch.bfloat16)
pipe.load_lora_weights("Shakker-Labs/AWPortrait-QW", weight_name="AWPortrait-QW_1.0.safetensors")
pipe.fuse_lora(lora_scale=1.0)
pipe.to("cuda")

prompt = "Black and white portrait of an Asian woman with dynamic hair movement,wearing a dark jacket against a light background."

image = pipe(
    prompt=prompt,
    negative_prompt="blurry, bad faces, bad hands, worst quality, low quality, jpeg artifacts",
    width=1328,
    height=1328,
    num_inference_steps=30,
    true_cfg_scale=4.0,
    generator=torch.Generator(device="cuda").manual_seed(0),
).images[0]
image.save(f"example.png")
```

## Online Inference

You can also try this model on [Liblib AI](https://www.liblib.art/modelinfo/cadba03ead404ea3bc1cda3d30803d84?from=feed&versionUuid=52ac709e59be444ba5965bb73493a9db&rankExpId=RVIyX0wyI0VHMTEjRTE3X0wzI0VHMjAjRTMw).


## Acknowledgements
This model is trained by our copyrighted users [DynamicWang](https://www.liblib.art/userpage/43d9ee875a6288176ac10d689a2770c7/publish). We release this model under permissions.