Qwen-Image

pip install dashscope>=1.20.7

import dashscope
from dashscope import ImageSynthesis

# Set your API key
dashscope.api_key = "YOUR_API_KEY"

# Text-to-image generation
response = ImageSynthesis.call(
    model='qwen-vlo',
    prompt='A coffee shop entrance features a chalkboard sign reading "Qwen Coffee 😊 $2 per cup"',
    negative_prompt='blurry, low quality',
    n=1,  # Number of images to generate
    size='1024*1024',  # Image size
    steps=50  # Diffusion steps
)

# Save the generated image
if response.status_code == 200:
    with open('qwen_vlo_result.png', 'wb') as f:
        f.write(response.output.images[0].image)
        print('Image saved successfully!')
else:
    print(f'Failed to generate image: {response.message}')

pip install git+https://github.com/huggingface/diffusers

from diffusers import DiffusionPipeline
import torch

model_name = "Qwen/Qwen-Image"

# Load the pipeline
if torch.cuda.is_available():
    torch_dtype = torch.bfloat16
    device = "cuda"
else:
    torch_dtype = torch.float32
    device = "cpu"

pipe = DiffusionPipeline.from_pretrained(model_name, torch_dtype=torch_dtype)
pipe = pipe.to(device)

positive_magic = {
    "en": "Ultra HD, 4K, cinematic composition.", # for english prompt
    "zh": "超清，4K，电影级构图" # for chinese prompt
}

# Generate image
prompt = '''A coffee shop entrance features a chalkboard sign reading "Qwen Coffee 😊 $2 per cup," with a neon light beside it displaying "通义千问". Next to it hangs a poster showing a beautiful Chinese woman, and beneath the poster is written "π≈3.1415926-53589793-23846264-33832795-02384197". Ultra HD, 4K, cinematic composition'''

negative_prompt = " "

# Generate with different aspect ratios
aspect_ratios = {
    "1:1": (1328, 1328),
    "16:9": (1664, 928),
    "9:16": (928, 1664),
    "4:3": (1472, 1140),
    "3:4": (1140, 1472)
}

width, height = aspect_ratios["16:9"]

image = pipe(
    prompt=prompt + positive_magic["en"],
    negative_prompt=negative_prompt,
    width=width,
    height=height,
    num_inference_steps=50,
    true_cfg_scale=4.0,
    generator=torch.Generator(device="cuda").manual_seed(42)
).images[0]

image.save("example.png")