通义千问-图像编辑Qwen-Image-Edit

import json
import os
from dashscope import MultiModalConversation

messages = [
    {
        "role": "user",
        "content": [
            {"image": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"},
            {"text": "将图中的人物改为站立姿势，弯腰握住狗的前爪"}
        ]
    }
]

# 若没有配置环境变量，请用百炼API Key将下行替换为：api_key="sk-xxx"
api_key = os.getenv("DASHSCOPE_API_KEY")

response = MultiModalConversation.call(
    api_key=api_key,
    model="qwen-image-edit",
    messages=messages,
    result_format='message',
    stream=False,
    watermark=True,
    negative_prompt=""
)

if response.status_code == 200:
    print(json.dumps(response, ensure_ascii=False))
else:
    print(f"HTTP返回码：{response.status_code}")
    print(f"错误码：{response.code}")
    print(f"错误信息：{response.message}")
    print("请参考文档：https://help.aliyun.com/zh/model-studio/developer-reference/error-code")

响应示例

图像链接的有效期为24小时，请及时下载图像。

{
    "status_code": 200,
    "request_id": "3daccb10-10ca-9399-8b6a-xxxxxx",
    "code": "",
    "message": "",
    "output": {
        "text": null,
        "finish_reason": null,
        "choices": [
            {
                "finish_reason": "stop",
                "message": {
                    "role": "assistant",
                    "content": [
                        {
                            "image": "https://dashscope-result-sz.oss-cn-shenzhen.aliyuncs.com/xxx.png?Expires=xxx"
                        }
                    ]
                }
            }
        ]
    },
    "usage": {
        "input_tokens": 0,
        "output_tokens": 0,
        "width": 1248,
        "image_count": 1,
        "height": 832
    }
}

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

public class QwenImageEdit {

    // 若没有配置环境变量，请用百炼API Key将下行替换为：apiKey="sk-xxx"
    static String apiKey = System.getenv("DASHSCOPE_API_KEY");

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

        MultiModalConversation conv = new MultiModalConversation();

        MultiModalMessage userMessage = MultiModalMessage.builder().role(Role.USER.getValue())
                .content(Arrays.asList(
                        Collections.singletonMap("image", "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"),
                        Collections.singletonMap("text", "将图中的人物改为站立姿势，弯腰握住狗的前爪")
                )).build();

        Map<String, Object> parameters = new HashMap<>();
        parameters.put("watermark", true);
        parameters.put("negative_prompt", "");

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

        MultiModalConversationResult result = conv.call(param);
        System.out.println(JsonUtils.toJson(result));
    }

    public static void main(String[] args) {
        try {
            call();
        } catch (ApiException | NoApiKeyException | UploadFileException | IOException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}

curl --location 'https://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation' \
--header 'Content-Type: application/json' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--data '{
    "model": "qwen-image-edit",
    "input": {
        "messages": [
            {
                "role": "user",
                "content": [
                    {
                        "image": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"
                    },
                    {
                        "text": "将图中的人物改为站立姿势，弯腰握住狗的前爪"
                    }
                ]
            }
        ]
    },
    "parameters": {
        "negative_prompt": "",
        "watermark": false
    }
}'