Qwen-Image Edit

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

import os
from PIL import Image
import torch
from diffusers import QwenImageEditPipeline

pipeline = QwenImageEditPipeline.from_pretrained("Qwen/Qwen-Image-Edit")
print("pipeline loaded")
pipeline.to(torch.bfloat16)
pipeline.to("cuda")
pipeline.set_progress_bar_config(disable=None)

image = Image.open("./input.png").convert("RGB")
prompt = "Change the rabbit's color to purple, with a flash light background."

inputs = {
    "image": image,
    "prompt": prompt,
    "generator": torch.manual_seed(0),
    "true_cfg_scale": 4.0,
    "negative_prompt": " ",
    "num_inference_steps": 50,
}

with torch.inference_mode():
    output = pipeline(**inputs)

output_image = output.images[0]
output_image.save("output_image_edit.png")
print("image saved at", os.path.abspath("output_image_edit.png"))

pip install dashscope>=1.20.7

import dashscope
from dashscope import ImageSynthesis

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

# Image-to-image generation
response = ImageSynthesis.call(
    model='qwen-vlo',
    prompt='Transform this coffee shop into a futuristic cyber cafe with neon lights',
    negative_prompt='blurry, low quality',
    n=1,  # Number of images to generate
    size='1024*1024',  # Image size
    steps=50,  # Diffusion steps
    image='path/to/input_image.jpg'  # Input image for editing
)

# 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}')