Alibaba Cloud Model Studio:Qwen-Image Edit API reference

import json
import os
import dashscope
from dashscope import MultiModalConversation

# The following is the URL for the Singapore region. Replace {WorkspaceId} with your Bailian workspace ID. URLs vary by region.
dashscope.base_http_api_url = 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1'

# The model supports one to three input images.
messages = [
    {
        "role": "user",
        "content": [
            {"image": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250925/thtclx/input1.png"},
            {"image": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250925/iclsnx/input2.png"},
            {"image": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250925/gborgw/input3.png"},
            {"text": "The girl from Image 1 is wearing the black dress from Image 2 and sitting in the pose from Image 3."}
        ]
    }
]

# The API keys for the Singapore and Beijing regions are different. To get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key.
# If you have not configured the environment variable, replace the next line with: api_key="sk-xxx"
api_key = os.getenv("DASHSCOPE_API_KEY")

# The qwen-image-2.0, qwen-image-edit-max, and qwen-image-edit-plus series support one to six output images. This example generates two.
response = MultiModalConversation.call(
    api_key=api_key,
    model="qwen-image-2.0-pro",
    messages=messages,
    stream=False,
    n=2,
    watermark=False,
    negative_prompt=" ",
    prompt_extend=True,
    size="1024*1536",
)

if response.status_code == 200:
    # To view the full response, uncomment the next line.
    # print(json.dumps(response, ensure_ascii=False))
    for i, content in enumerate(response.output.choices[0].message.content):
        print(f"URL of output image {i+1}: {content['image']}")
else:
    print(f"HTTP status code: {response.status_code}")
    print(f"Error code: {response.code}")
    print(f"Error message: {response.message}")
    print("For more information, see https://www.alibabacloud.com/help/en/model-studio/error-code")

import json
import os
import dashscope
from dashscope import MultiModalConversation
import base64
import mimetypes

# The following is the URL for the Singapore region. Replace {WorkspaceId} with your Bailian workspace ID. URLs vary by region.
dashscope.base_http_api_url = 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1'

# --- For Base64 encoding ---
# Format: data:{mime_type};base64,{base64_data}
def encode_file(file_path):
    mime_type, _ = mimetypes.guess_type(file_path)
    if not mime_type or not mime_type.startswith("image/"):
        raise ValueError("Unsupported or unrecognized image format")

    try:
        with open(file_path, "rb") as image_file:
            encoded_string = base64.b64encode(
                image_file.read()).decode('utf-8')
        return f"data:{mime_type};base64,{encoded_string}"
    except IOError as e:
        raise IOError(f"Error reading file: {file_path}, Error: {str(e)}")

# Get the Base64 encoding of the image.
# Call the encoding function. Replace "/path/to/your/image.png" with the path to your local image file. Otherwise, the code will not run.
image = encode_file("/path/to/your/image.png")

messages = [
    {
        "role": "user",
        "content": [
            {"image": image},
            {"text": "Generate an image that matches the depth map, following this description: A red, dilapidated bicycle is parked on a muddy path, with a dense primeval forest in the background."}
        ]
    }
]

# The API keys for the Singapore and Beijing regions are different. To get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key.
# If you have not configured the environment variable, replace the next line with: api_key="sk-xxx"
api_key = os.getenv("DASHSCOPE_API_KEY")

# The qwen-image-2.0, qwen-image-edit-max, and qwen-image-edit-plus series support one to six output images. This example generates two.
response = MultiModalConversation.call(
    api_key=api_key,
    model="qwen-image-2.0-pro",
    messages=messages,
    stream=False,
    n=2,
    watermark=False,
    negative_prompt=" ",
    prompt_extend=True,
    size="1536*1024",
)

if response.status_code == 200:
    # To view the full response, uncomment the next line.
    # print(json.dumps(response, ensure_ascii=False))
    for i, content in enumerate(response.output.choices[0].message.content):
        print(f"URL of output image {i+1}: {content['image']}")
else:
    print(f"HTTP status code: {response.status_code}")
    print(f"Error code: {response.code}")
    print(f"Error message: {response.message}")
    print("For more information, see https://www.alibabacloud.com/help/en/model-studio/error-code")

# You need to install requests to download the image: pip install requests
import requests

def download_image(image_url, save_path='output.png'):
    try:
        response = requests.get(image_url, stream=True, timeout=300)  # Set a timeout.
        response.raise_for_status()  # Raise an exception if the HTTP status code is not 200.
        with open(save_path, 'wb') as f:
            for chunk in response.iter_content(chunk_size=8192):
                f.write(chunk)
        print(f"Image successfully downloaded to: {save_path}")

    except requests.exceptions.RequestException as e:
        print(f"Image download failed: {e}")

image_url = "https://dashscope-result-sz.oss-cn-shenzhen.aliyuncs.com/xxx.png?Expires=xxx"
download_image(image_url, save_path='output.png')

import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversation;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationParam;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationResult;
import com.alibaba.dashscope.common.MultiModalMessage;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.exception.UploadFileException;
import com.alibaba.dashscope.utils.JsonUtils;
import com.alibaba.dashscope.utils.Constants;

import java.io.IOException;
import java.util.Arrays;
import java.util.Collections;
import java.util.HashMap;
import java.util.Map;
import java.util.List;

public class QwenImageEdit {

    static {
        // The following is the URL for the Singapore region. Replace {WorkspaceId} with your Bailian workspace ID. URLs vary by region.
        Constants.baseHttpApiUrl = "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1";
    }

    // The API keys for the Singapore and Beijing regions are different. To obtain an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key.
    // If you have not configured the environment variable, replace the following line with your DashScope API key: apiKey="sk-xxx".
    static String apiKey = System.getenv("DASHSCOPE_API_KEY");

    public static void call() throws ApiException, NoApiKeyException, UploadFileException, IOException {

        MultiModalConversation conv = new MultiModalConversation();

        // The model supports one to three input images.
        MultiModalMessage userMessage = MultiModalMessage.builder().role(Role.USER.getValue())
                .content(Arrays.asList(
                        Collections.singletonMap("image", "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250925/thtclx/input1.png"),
                        Collections.singletonMap("image", "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250925/iclsnx/input2.png"),
                        Collections.singletonMap("image", "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250925/gborgw/input3.png"),
                        Collections.singletonMap("text", "The girl from Image 1 is wearing the black dress from Image 2 and sitting in the pose from Image 3.")
                )).build();
        // The qwen-image-2.0, qwen-image-edit-max, and qwen-image-edit-plus series models support one to six output images. This example generates two images.
        Map<String, Object> parameters = new HashMap<>();
        parameters.put("watermark", false);
        parameters.put("negative_prompt", " ");
        parameters.put("n", 2);
        parameters.put("prompt_extend", true);
        parameters.put("size", "1024*1536");

        MultiModalConversationParam param = MultiModalConversationParam.builder()
                .apiKey(apiKey)
                .model("qwen-image-edit-max")
                .messages(Collections.singletonList(userMessage))
                .parameters(parameters)
                .build();

        MultiModalConversationResult result = conv.call(param);
        // To view the complete response, uncomment the following line.
        // System.out.println(JsonUtils.toJson(result));
        List<Map<String, Object>> contentList = result.getOutput().getChoices().get(0).getMessage().getContent();
        int imageIndex = 1;
        for (Map<String, Object> content : contentList) {
            if (content.containsKey("image")) {
                System.out.println("URL of output image " + imageIndex + ": " + content.get("image"));
                imageIndex++;
            }
        }
    }

    public static void main(String[] args) {
        try {
            call();
        } catch (ApiException | NoApiKeyException | UploadFileException | IOException e) {
            System.out.println(e.getMessage());
        }
    }
}

import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversation;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationParam;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationResult;
import com.alibaba.dashscope.common.MultiModalMessage;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.exception.UploadFileException;
import com.alibaba.dashscope.utils.JsonUtils;
import com.alibaba.dashscope.utils.Constants;

import java.io.IOException;
import java.nio.file.Files;
import java.nio.file.Path;
import java.nio.file.Paths;
import java.util.Arrays;
import java.util.Base64;
import java.util.Collections;
import java.util.HashMap;
import java.util.Map;
import java.util.List;

public class QwenImageEdit {

    static {
        // The following is the URL for the Singapore region. Replace {WorkspaceId} with your Bailian workspace ID. URLs vary by region.
        Constants.baseHttpApiUrl = "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1";
    }

    // The API keys for the Singapore and Beijing regions are different. To obtain an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key.
    // If you have not configured the environment variable, replace the following line with your DashScope API key: apiKey="sk-xxx".
    static String apiKey = System.getenv("DASHSCOPE_API_KEY");

    public static void call() throws ApiException, NoApiKeyException, UploadFileException, IOException {

        // Replace "/path/to/your/image.png" with the path to your local image file. Otherwise, the code cannot run.
        String image = encodeFile("/path/to/your/image.png");

        MultiModalConversation conv = new MultiModalConversation();

        MultiModalMessage userMessage = MultiModalMessage.builder().role(Role.USER.getValue())
                .content(Arrays.asList(
                        Collections.singletonMap("image", image),
                        Collections.singletonMap("text", "Generate an image that matches the depth map, following this description: A dilapidated red bicycle is parked on a muddy path, with a dense primeval forest in the background.")
                )).build();
        // The qwen-image-2.0, qwen-image-edit-max, and qwen-image-edit-plus series models support one to six output images. This example generates two images.
        Map<String, Object> parameters = new HashMap<>();
        parameters.put("watermark", false);
        parameters.put("negative_prompt", " ");
        parameters.put("n", 2);
        parameters.put("prompt_extend", true);
        parameters.put("size", "1536*1024");

        MultiModalConversationParam param = MultiModalConversationParam.builder()
                .apiKey(apiKey)
                .model("qwen-image-edit-max")
                .messages(Collections.singletonList(userMessage))
                .parameters(parameters)
                .build();

        MultiModalConversationResult result = conv.call(param);
        // To view the complete response, uncomment the following line.
        // System.out.println(JsonUtils.toJson(result));
        List<Map<String, Object>> contentList = result.getOutput().getChoices().get(0).getMessage().getContent();
        int imageIndex = 1;
        for (Map<String, Object> content : contentList) {
            if (content.containsKey("image")) {
                System.out.println("URL of output image " + imageIndex + ": " + content.get("image"));
                imageIndex++;
            }
        }
    }

    /**
     * Encodes a file into a Base64 string.
     * @param filePath The path to the file.
     * @return A Base64 string in the format: data:{mime_type};base64,{base64_data}.
     */
    public static String encodeFile(String filePath) {
        Path path = Paths.get(filePath);
        if (!Files.exists(path)) {
            throw new IllegalArgumentException("File does not exist: " + filePath);
        }
        // Detect the MIME type.
        String mimeType = null;
        try {
            mimeType = Files.probeContentType(path);
        } catch (IOException e) {
            throw new IllegalArgumentException("Cannot detect file type: " + filePath);
        }
        if (mimeType == null || !mimeType.startsWith("image/")) {
            throw new IllegalArgumentException("Unsupported or unrecognized image format.");
        }
        // Read the file content and encode it.
        byte[] fileBytes = null;
        try{
            fileBytes = Files.readAllBytes(path);
        } catch (IOException e) {
            throw new IllegalArgumentException("Cannot read file content: " + filePath);
        }

        String encodedString = Base64.getEncoder().encodeToString(fileBytes);
        return "data:" + mimeType + ";base64," + encodedString;
    }

    public static void main(String[] args) {
        try {
            call();
        } catch (ApiException | NoApiKeyException | UploadFileException | IOException e) {
            System.out.println(e.getMessage());
        }
    }
}

import java.io.FileOutputStream;
import java.io.InputStream;
import java.net.HttpURLConnection;
import java.net.URL;

public class ImageDownloader {
    public static void downloadImage(String imageUrl, String savePath) {
        try {
            URL url = new URL(imageUrl);
            HttpURLConnection connection = (HttpURLConnection) url.openConnection();
            connection.setConnectTimeout(5000);
            connection.setReadTimeout(300000);
            connection.setRequestMethod("GET");
            InputStream inputStream = connection.getInputStream();
            FileOutputStream outputStream = new FileOutputStream(savePath);
            byte[] buffer = new byte[8192];
            int bytesRead;
            while ((bytesRead = inputStream.read(buffer)) != -1) {
                outputStream.write(buffer, 0, bytesRead);
            }
            inputStream.close();
            outputStream.close();

            System.out.println("Image downloaded successfully to: " + savePath);
        } catch (Exception e) {
            System.err.println("Image download failed: " + e.getMessage());
        }
    }

    public static void main(String[] args) {
        String imageUrl = "http://dashscope-result-bj.oss-cn-beijing.aliyuncs.com/xxx?Expires=xxx";
        String savePath = "output.png";
        downloadImage(imageUrl, savePath);
    }
}