---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
- qwen-image
widget:
- output:
    url: images/7e329cb5f01a81b72219f94f5708a4f258514e810976111fd553986c.jpg
  text: >-
    Black and white portrait of an Asian woman with dynamic hair
    movement,wearing a dark jacket against a light background.,
  parameters:
    negative_prompt: blurry, bad faces, bad hands,worst quality, low quality, jpeg artifacts
- output:
    url: images/d722529f47767f3b446c829aa0681f6d155643e80f92e1c62d2f7075.jpg
  text: >-
    A Polaroid style photograph with a white frame captures a vintage Hong Kong
    ambiance. A young woman in a red tank top and blue jeans stands in the
    scene. She has long black curls, red lipstick, and holds a red soda can with
    white text in her right hand. Her body faces left, and her gaze meets the
    camera with a natural expression. The dimly lit indoor setting features blue
    columns and softly blurred decorations behind her, enhancing the nostalgic
    atmosphere.
  parameters:
    negative_prompt: blurry, bad faces, bad hands,worst quality, low quality, jpeg artifacts
- output:
    url: images/08fdaf6b644b61136340d5c908ca37993e47f34cdbe2e8e8251c4c72.jpg
  text: >-
    photo,photography,realisitc,Caucasian,fashion portrait,1girl,blue
    dress,standing,whole body,huge blue flowers,huge flowers,light spot,particle
    light,glow,depth of field level,deep mottled background,
  parameters:
    negative_prompt: blurry, bad faces, bad hands,worst quality, low quality, jpeg artifacts
base_model: Qwen/Qwen-Image
instance_prompt: null
license: apache-2.0
language:
- en
library_name: diffusers
---
# 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.