Nova Canvas - Mask prompt

使用mask prompt进行背景替换

替换图像背景的一种方法是使用"OUTPAINTING"任务类型。这个功能的一个常见用例是将真实产品放置在生成的环境中。

下面的脚本将使用左边的图像作为输入。它将通过使用mask prompt(咖啡机)和文本提示(“一台咖啡机在一个简约时尚的厨房里, 旁边有一个小盘子的糕点, 一杯咖啡。高度细节,最高质量,产品图像”)来替换咖啡机后面的背景。结果将类似于第二/三张图像。

img

img

image-20241215103659979

image-20241215103913626

将第一张图片下载为coffee-maker-1.png并保存到代码同级目录，运行下面代码：

from random import randint
import json
import base64
import boto3

client = boto3.client(service_name='bedrock-runtime', region_name="us-east-1")

# Set the image to be edited.
source_image = "coffee-maker-1.png"

# Load the input image from disk.
with open(source_image, "rb") as image_file:
    source_image_base64 = base64.b64encode(image_file.read()).decode("utf-8")



inference_params = json.dumps({
    "taskType": "OUTPAINTING",
    "outPaintingParams": {
        "image": source_image_base64,
        "text": "a coffee maker in a sparse stylish kitchen, a single plate of pastries next to the coffee maker, a single cup of coffee. highly detailed, highest quality, product imagery",  # Description of the background to generate
        "maskPrompt": "coffee maker",  # The element(s) to keep
        "outPaintingMode": "PRECISE",  # "DEFAULT" softens the mask. "PRECISE" keeps it sharp.
    },
    "imageGenerationConfig": {
        "numberOfImages": 1,  # Number of variations to generate. 1 to 5.
        "quality": "standard",  # Allowed values are "standard" and "premium"
        "cfgScale": 7.0,  # How closely the prompt will be followed
        "seed": randint(0, 858993459),  # Use a random seed
    },
})

response = client.invoke_model(
    body=inference_params,
    modelId="amazon.nova-canvas-v1:0",
    accept="application/json",
    contentType="application/json",
)

response_body = json.loads(response.get("body").read())  # 读取并解析响应体
base64_image = response_body.get("images")[0]  # 获取返回的 Base64 编码图片数据

# 将 Base64 编码的图片解码为二进制数据
base_64_image = base64.b64decode(base64_image)

# 将解码后的图片保存为文件
file_path = "1.png"
with open(file_path, "wb") as f:
    f.write(base_64_image)

print(f"图片已成功保存为: {file_path}")