AWPortrait-QW

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

Prompt

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

Negative Prompt

blurry, bad faces, bad hands,worst quality, low quality, jpeg artifacts

Prompt

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.

Negative Prompt

blurry, bad faces, bad hands,worst quality, low quality, jpeg artifacts

Prompt

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,

Negative Prompt

blurry, bad faces, bad hands,worst quality, low quality, jpeg artifacts

Trigger words

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

Inference

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.

Acknowledgements

This model is trained by our copyrighted users DynamicWang. We release this model under permissions.