通义千问VL

Python

import os
from openai import OpenAI


client = OpenAI(
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    base_url="https://dashscope.aliyuncs.com/compatible-mode/v1"
)

completion = client.chat.completions.create(
    model="qwen-vl-max-latest",
    messages=[
        {"role": "user", "content": [
            {"type": "image_url", "image_url": {"url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"}},
            {"type": "text", "text": "这是什么"}
        ]}
    ]
)

print(completion.choices[0].message.content)

返回结果

这是一张在海滩上拍摄的照片。照片中，一个人和一只狗坐在沙滩上，背景是大海和天空。人和狗似乎在互动，狗的前爪搭在人的手上。阳光从画面的右侧照射过来，给整个场景增添了一种温暖的氛围。

Node.js

import OpenAI from "openai";

const openai = new OpenAI(
    {
        // 若没有配置环境变量，请用百炼API Key将下行替换为：apiKey: "sk-xxx",
        apiKey: process.env.DASHSCOPE_API_KEY,
        baseURL: "https://dashscope.aliyuncs.com/compatible-mode/v1"
    }
);

async function main() {
    const response = await openai.chat.completions.create({
        model: "qwen-vl-max-latest",
        messages: [{role: "user",content: [
            { type: "image_url",image_url: {"url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"}},
            { type: "text", text: "这是什么？" }
        ]}]
    });
    console.log(response.choices[0].message.content);
}

main()

这是一张在海滩上拍摄的照片。照片中，一位穿着格子衬衫的女性坐在沙滩上，与一只戴着项圈的黄色拉布拉多犬互动。背景是大海和天空，阳光洒在她们身上，营造出温暖的氛围。

curl

curl --location 'https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
  "model": "qwen-vl-max",
  "messages": [{
    "role": "user",
    "content": [
      {"type": "image_url", "image_url": {"url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"}},
      {"type": "text", "text": "这是什么"}
    ]
  }]
}'

返回结果

{
  "choices": [
    {
      "message": {
        "content": "这张图片展示了一位女士和一只狗在海滩上互动。女士坐在沙滩上，微笑着与狗握手。背景是大海和天空，阳光洒在她们身上，营造出温暖的氛围。狗戴着项圈，显得很温顺。",
        "role": "assistant"
      },
      "finish_reason": "stop",
      "index": 0,
      "logprobs": null
    }
  ],
  "object": "chat.completion",
  "usage": {
    "prompt_tokens": 1270,
    "completion_tokens": 54,
    "total_tokens": 1324
  },
  "created": 1725948561,
  "system_fingerprint": null,
  "model": "qwen-vl-max",
  "id": "chatcmpl-0fd66f46-b09e-9164-a84f-3ebbbedbac15"
}

Python

import os
import dashscope

messages = [
    {
        "role": "user",
        "content": [
            {"image": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"},
            {"text": "这是什么?"}
        ]
    }
]

response = dashscope.MultiModalConversation.call(
    # 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'),
    model='qwen-vl-max-latest',
    messages=messages
)

print(response.output.choices[0].message.content[0]["text"])

返回结果

是一张在海滩上拍摄的照片。照片中有一位女士和一只狗。女士坐在沙滩上，微笑着与狗互动。狗戴着项圈，似乎在与女士握手。背景是大海和天空，阳光洒在她们身上，营造出温馨的氛围。

Java

import java.util.Arrays;
import java.util.Collections;
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;
public class Main {
    public static void simpleMultiModalConversationCall()
            throws ApiException, NoApiKeyException, UploadFileException {
        MultiModalConversation conv = new MultiModalConversation();
        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/20241022/emyrja/dog_and_girl.jpeg"),
                        Collections.singletonMap("text", "这是什么?"))).build();
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                .model("qwen-vl-max-latest")
                .message(userMessage)
                .build();
        MultiModalConversationResult result = conv.call(param);
        System.out.println(result.getOutput().getChoices().get(0).getMessage().getContent().get(0).get("text"));
    }
    public static void main(String[] args) {
        try {
            simpleMultiModalConversationCall();
        } catch (ApiException | NoApiKeyException | UploadFileException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}

返回结果

这是一张在海滩上拍摄的照片。照片中有一个穿着格子衬衫的人和一只戴着项圈的狗。人和狗面对面坐着，似乎在互动。背景是大海和天空，阳光洒在他们身上，营造出温暖的氛围。

curl

curl -X POST https://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
    "model": "qwen-vl-max",
    "input":{
        "messages":[
            {
                "role": "user",
                "content": [
                    {"image": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"},
                    {"text": "这是什么?"}
                ]
            }
        ]
    }
}'

返回结果

{
  "output": {
    "choices": [
      {
        "finish_reason": "stop",
        "message": {
          "role": "assistant",
          "content": [
            {
              "text": "这是一张在海滩上拍摄的照片。照片中有一个穿着格子衬衫的人和一只戴着项圈的狗。他们坐在沙滩上，背景是大海和天空。阳光从画面的右侧照射过来，给整个场景增添了一种温暖的氛围。"
            }
          ]
        }
      }
    ]
  },
  "usage": {
    "output_tokens": 55,
    "input_tokens": 1271,
    "image_tokens": 1247
  },
  "request_id": "ccf845a3-dc33-9cda-b581-20fe7dc23f70"
}

Python

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    base_url="https://dashscope.aliyuncs.com/compatible-mode/v1",
)

completion = client.chat.completions.create(
    model="qwen-vl-max-latest",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"
                    },
                },
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/tiger.png"
                    },
                },
                {"type": "text", "text": "这些是什么"},
            ],
        }
    ],
)

print(completion.choices[0].message.content)

返回结果

图1中是一位女士和一只拉布拉多犬在海滩上互动的场景。女士穿着格子衬衫，坐在沙滩上，与狗进行握手的动作，背景是海浪和天空，整个画面充满了温馨和愉快的氛围。

图2中是一只老虎在森林中行走的场景。老虎的毛色是橙色和黑色条纹相间，它正向前迈步，周围是茂密的树木和植被，地面上覆盖着落叶，整个画面给人一种野生自然的感觉。

Node.js

import OpenAI from "openai";

const openai = new OpenAI(
    {
        // 若没有配置环境变量，请用百炼API Key将下行替换为：apiKey: "sk-xxx",
        apiKey: process.env.DASHSCOPE_API_KEY,
        baseURL: "https://dashscope.aliyuncs.com/compatible-mode/v1"
    }
);

async function main() {
    const response = await openai.chat.completions.create({
        model: "qwen-vl-max-latest",
        messages: [{role: "user",content: [
            { type: "image_url",image_url: {"url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"}},
            { type: "image_url",image_url: {"url": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/tiger.png"}},
            { type: "text", text: "这些是什么？" },
        ]}]
    });
    console.log(response.choices[0].message.content);
}

main()

返回结果

第一张图片中，一个人和一只狗在海滩上互动。人穿着格子衬衫，狗戴着项圈，他们似乎在握手或击掌。

第二张图片中，一只老虎在森林中行走。老虎的毛色是橙色和黑色条纹，背景是绿色的树木和植被。

curl

curl -X POST https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
  "model": "qwen-vl-max",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "image_url",
          "image_url": {
            "url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"
          }
        },
        {
          "type": "image_url",
          "image_url": {
            "url": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/tiger.png"
          }
        },
        {
          "type": "text",
          "text": "这些是什么"
        }
      ]
    }
  ]
}'

返回结果

{
  "choices": [
    {
      "message": {
        "content": "图1中是一位女士和一只拉布拉多犬在海滩上互动的场景。女士穿着格子衬衫，坐在沙滩上，与狗进行握手的动作，背景是海景和日落的天空，整个画面显得非常温馨和谐。\n\n图2中是一只老虎在森林中行走的场景。老虎的毛色是橙色和黑色条纹相间，它正向前迈步，周围是茂密的树木和植被，地面上覆盖着落叶，整个画面充满了自然的野性和生机。",
        "role": "assistant"
      },
      "finish_reason": "stop",
      "index": 0,
      "logprobs": null
    }
  ],
  "object": "chat.completion",
  "usage": {
    "prompt_tokens": 2497,
    "completion_tokens": 109,
    "total_tokens": 2606
  },
  "created": 1725948561,
  "system_fingerprint": null,
  "model": "qwen-vl-max",
  "id": "chatcmpl-0fd66f46-b09e-9164-a84f-3ebbbedbac15"
}

Python

import os
import dashscope

messages = [
    {
        "role": "user",
        "content": [
            {"image": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"},
            {"image": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/tiger.png"},
            {"image": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/hbygyo/rabbit.jpg"},
            {"text": "这些是什么?"}
        ]
    }
]

response = dashscope.MultiModalConversation.call(
    # 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'),
    model='qwen-vl-max-latest',
    messages=messages
)

print(response.output.choices[0].message.content[0]["text"])

返回结果

这些图片展示了一些动物和自然场景。第一张图片中，一个人和一只狗在海滩上互动。第二张图片是一只老虎在森林中行走。第三张图片是一只卡通风格的兔子在草地上跳跃。

Java

import java.util.Arrays;
import java.util.Collections;
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;
public class Main {
    public static void simpleMultiModalConversationCall()
            throws ApiException, NoApiKeyException, UploadFileException {
        MultiModalConversation conv = new MultiModalConversation();
        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/20241022/emyrja/dog_and_girl.jpeg"),
                        Collections.singletonMap("image", "https://dashscope.oss-cn-beijing.aliyuncs.com/images/tiger.png"),
                        Collections.singletonMap("image", "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/hbygyo/rabbit.jpg"),
                        Collections.singletonMap("text", "这些是什么?"))).build();
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                .model("qwen-vl-max-latest")
                .message(userMessage)
                .build();
        MultiModalConversationResult result = conv.call(param);
        System.out.println(result.getOutput().getChoices().get(0).getMessage().getContent().get(0).get("text"));    }
    public static void main(String[] args) {
        try {
            simpleMultiModalConversationCall();
        } catch (ApiException | NoApiKeyException | UploadFileException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}

返回结果

这些图片展示了一些动物和自然场景。

1. 第一张图片：一个女人和一只狗在海滩上互动。女人穿着格子衬衫，坐在沙滩上，狗戴着项圈，伸出爪子与女人握手。
2. 第二张图片：一只老虎在森林中行走。老虎的毛色是橙色和黑色条纹，背景是树木和树叶。
3. 第三张图片：一只卡通风格的兔子在草地上跳跃。兔子是白色的，耳朵是粉红色的，背景是蓝天和黄色的花朵。

这些图片展示了不同的动物和自然环境。

curl

curl --location 'https://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "model": "qwen-vl-plus",
    "input":{
        "messages":[
            {
                "role": "user",
                "content": [
                    {"image": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"},
                    {"image": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/tiger.png"},
                    {"image": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/hbygyo/rabbit.jpg"},
                    {"text": "这些是什么?"}
                ]
            }
        ]
    }
}'

返回结果

{
  "output": {
    "choices": [
      {
        "finish_reason": "stop",
        "message": {
          "role": "assistant",
          "content": [
            {
              "text": "这张图片显示了一位女士和她的狗在海滩上。她们似乎正在享受彼此的陪伴，狗狗坐在沙滩上伸出爪子与女士握手或互动。背景是美丽的日落景色，海浪轻轻拍打着海岸线。\n\n请注意，我提供的描述基于图像中可见的内容，并不包括任何超出视觉信息之外的信息。如果您需要更多关于这个场景的具体细节，请告诉我！"
            }
          ]
        }
      }
    ]
  },
  "usage": {
    "output_tokens": 81,
    "input_tokens": 1277,
    "image_tokens": 1247
  },
  "request_id": "ccf845a3-dc33-9cda-b581-20fe7dc23f70"
}

Python

from openai import OpenAI
import os


client = OpenAI(
    # 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"),
    base_url="https://dashscope.aliyuncs.com/compatible-mode/v1"
)
messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image_url",
                "image_url": {
                    "url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"
                },
            },
            {"type": "text", "text": "这是什么"},
        ],
    }
]
completion = client.chat.completions.create(
    model="qwen-vl-max-latest",
    messages=messages,
    )
print(f"第一轮输出：{completion.choices[0].message.content}")
assistant_message = completion.choices[0].message
messages.append(assistant_message.model_dump())
messages.append({
        "role": "user",
        "content": [
        {
            "type": "text",
            "text": "做一首诗描述这个场景"
        }
        ]
    })
completion = client.chat.completions.create(
    model="qwen-vl-max-latest",
    messages=messages,
    )
print(f"第二轮输出：{completion.choices[0].message.content}")

返回结果

第一轮输出：这是一张在海滩上拍摄的照片。照片中，一位穿着格子衬衫的女士坐在沙滩上，与一只戴着项圈的金毛犬互动。背景是大海和天空，阳光洒在她们身上，营造出温暖的氛围。
第二轮输出：沙滩上，阳光洒，
女子与犬，笑语哗。
海浪轻拍，风儿吹，
快乐时光，心儿醉。

Node.js

import OpenAI from "openai";

const openai = new OpenAI(
    {
        // 若没有配置环境变量，请用百炼API Key将下行替换为：apiKey: "sk-xxx",
        apiKey: process.env.DASHSCOPE_API_KEY,
        baseURL: "https://dashscope.aliyuncs.com/compatible-mode/v1"
    }
);

let messages = [{
    role: "user", content: [
        { type: "image_url", image_url: { "url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg" } },
        { type: "text", text: "这是什么？" },
    ]
}]
async function main() {
    let response = await openai.chat.completions.create({
        model: "qwen-vl-max-latest",
        messages: messages
    });
    console.log(`第一轮输出：${response.choices[0].message.content}`);
    messages.push(response.choices[0].message);
    messages.push({"role": "user", "content": "做一首诗描述这个场景"});
    response = await openai.chat.completions.create({
        model: "qwen-vl-max-latest",
        messages: messages
    });
    console.log(`第二轮输出：${response.choices[0].message.content}`);
}

main()

返回结果

第一轮输出：这是一张在海滩上拍摄的照片。照片中有一个穿着格子衬衫的人和一只戴着项圈的狗。人和狗面对面坐着，似乎在互动。背景是大海和天空，阳光从画面的右侧照射过来，营造出温暖的氛围。
第二轮输出：沙滩上，人与狗，  
面对面，笑语稠。  
海风轻拂，阳光柔，  
心随波浪，共潮头。  

项圈闪亮，情意浓，  
格子衫下，心相通。  
海天一色，无尽空，  
此刻温馨，永铭中。

curl

curl -X POST https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
  "model": "qwen-vl-max",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "image_url",
          "image_url": {
            "url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"
          }
        },
        {
          "type": "text",
          "text": "这是什么"
        }
      ]
    },
    {
      "role": "assistant",
      "content": [
        {
          "type": "text",
          "text": "这是一个女孩和一只狗。"
        }
      ]
    },
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "写一首诗描述这个场景"
        }
      ]
    }
  ]
}'

返回结果

{
    "choices": [
        {
            "message": {
                "content": "海风轻拂笑颜开，  \n沙滩上与犬相陪。  \n夕阳斜照人影短，  \n欢乐时光心自醉。",
                "role": "assistant"
            },
            "finish_reason": "stop",
            "index": 0,
            "logprobs": null
        }
    ],
    "object": "chat.completion",
    "usage": {
        "prompt_tokens": 1295,
        "completion_tokens": 32,
        "total_tokens": 1327
    },
    "created": 1726324976,
    "system_fingerprint": null,
    "model": "qwen-vl-max",
    "id": "chatcmpl-3c953977-6107-96c5-9a13-c01e328b24ca"
}

Python

import os
from dashscope import MultiModalConversation

messages = [
    {
        "role": "user",
        "content": [
            {
                "image": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"
            },
            {"text": "这是什么?"},
        ],
    }
]
response = MultiModalConversation.call(
    # 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'),
    model='qwen-vl-max-latest',
    messages=messages)
print(f"模型第一轮输出：{response.output.choices[0].message.content[0]['text']}")
messages.append(response['output']['choices'][0]['message'])
user_msg = {"role": "user", "content": [{"text": "做一首诗描述这个场景"}]}
messages.append(user_msg)
response = MultiModalConversation.call(
    # 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'),
    model='qwen-vl-max-latest',
    messages=messages)
print(f"模型第二轮输出：{response.output.choices[0].message.content[0]['text']}")

返回结果

模型第一轮输出：这是一张在海滩上拍摄的照片。照片中有一个穿着格子衬衫的人和一只戴着项圈的狗。人和狗面对面坐着，似乎在互动。背景是大海和天空，阳光洒在他们身上，营造出温暖的氛围。
模型第二轮输出：在阳光照耀的海滩上，人与狗共享欢乐时光。

Java

import java.util.ArrayList;
import java.util.Arrays;
import java.util.Collections;
import java.util.List;
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;
public class Main {
    private static final String modelName = "qwen-vl-max-latest";
    public static void MultiRoundConversationCall() throws ApiException, NoApiKeyException, UploadFileException {
        MultiModalConversation conv = new MultiModalConversation();
        MultiModalMessage systemMessage = MultiModalMessage.builder().role(Role.SYSTEM.getValue())
                .content(Arrays.asList(Collections.singletonMap("text", "You are a helpful assistant."))).build();
        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/20241022/emyrja/dog_and_girl.jpeg"),
                        Collections.singletonMap("text", "这是什么?"))).build();
        List<MultiModalMessage> messages = new ArrayList<>();
        messages.add(systemMessage);
        messages.add(userMessage);
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                // 若没有配置环境变量，请用百炼API Key将下行替换为：.apiKey("sk-xxx")
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))                .model(modelName)
                .messages(messages)
                .build();
        MultiModalConversationResult result = conv.call(param);
        System.out.println("第一轮输出："+result.getOutput().getChoices().get(0).getMessage().getContent().get(0).get("text"));        // add the result to conversation
        messages.add(result.getOutput().getChoices().get(0).getMessage());
        MultiModalMessage msg = MultiModalMessage.builder().role(Role.USER.getValue())
                .content(Arrays.asList(Collections.singletonMap("text", "做一首诗描述这个场景"))).build();
        messages.add(msg);
        param.setMessages((List)messages);
        result = conv.call(param);
        System.out.println("第二轮输出："+result.getOutput().getChoices().get(0).getMessage().getContent().get(0).get("text"));    }

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

返回结果

第一轮输出：这是一张在海滩上拍摄的照片。照片中有一个穿着格子衬衫的人和一只戴着项圈的狗。人和狗面对面坐着，似乎在互动。背景是大海和天空，阳光洒在他们身上，营造出温暖的氛围。
第二轮输出：在阳光洒满的海滩上，人与狗共享欢乐时光。

curl

curl -X POST https://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
    "model": "qwen-vl-max",
    "input":{
        "messages":[
            {
                "role": "user",
                "content": [
                    {"image": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"},
                    {"text": "这是什么?"}
                ]
            },
            {
                "role": "assistant",
                "content": [
                    {"text": "这是一只狗和一只女孩。"}
                ]
            },
            {
                "role": "user",
                "content": [
                    {"text": "写一首七言绝句描述这个场景"}
                ]
            }
        ]
    }
}'

{
    "output": {
        "choices": [
            {
                "finish_reason": "stop",
                "message": {
                    "role": "assistant",
                    "content": [
                        {
                            "text": "海浪轻拍沙滩边，女孩与狗同嬉戏。阳光洒落笑颜开，快乐时光永铭记。"
                        }
                    ]
                }
            }
        ]
    },
    "usage": {
        "output_tokens": 27,
        "input_tokens": 1298,
        "image_tokens": 1247
    },
    "request_id": "bdf5ef59-c92e-92a6-9d69-a738ecee1590"
}

Python

from openai import OpenAI
import os

client = OpenAI(
    # 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"),
    base_url="https://dashscope.aliyuncs.com/compatible-mode/v1",
)

completion = client.chat.completions.create(
    model="qwen-vl-max-latest",
    messages=[
        {"role": "user",
        "content": [{"type": "image_url",
                    "image_url": {"url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"},},
                    {"type": "text", "text": "这是什么"}]}],
    stream=True
)
print("流式输出内容为：")
for chunk in completion:
    print(chunk.model_dump_json())

返回结果

流式输出内容为：
{"id":"chatcmpl-a6f201a2-0f82-9260-ae13-23243b78239c","choices":[{"delta":{"content":"","function_call":null,"refusal":null,"role":"assistant","tool_calls":null},"finish_reason":null,"index":0,"logprobs":null}],"created":1731683175,"model":"qwen-vl-max-latest","object":"chat.completion.chunk","service_tier":null,"system_fingerprint":null,"usage":null}
{"id":"chatcmpl-a6f201a2-0f82-9260-ae13-23243b78239c","choices":[{"delta":{"content":"这","function_call":null,"refusal":null,"role":null,"tool_calls":null},"finish_reason":null,"index":0,"logprobs":null}],"created":1731683175,"model":"qwen-vl-max-latest","object":"chat.completion.chunk","service_tier":null,"system_fingerprint":null,"usage":null}
{"id":"chatcmpl-a6f201a2-0f82-9260-ae13-23243b78239c","choices":[{"delta":{"content":"是一","function_call":null,"refusal":null,"role":null,"tool_calls":null},"finish_reason":null,"index":0,"logprobs":null}],"created":1731683175,"model":"qwen-vl-max-latest","object":"chat.completion.chunk","service_tier":null,"system_fingerprint":null,"usage":null}
{"id":"chatcmpl-a6f201a2-0f82-9260-ae13-23243b78239c","choices":[{"delta":{"content":"张","function_call":null,"refusal":null,"role":null,"tool_calls":null},"finish_reason":null,"index":0,"logprobs":null}],"created":1731683175,"model":"qwen-vl-max-latest","object":"chat.completion.chunk","service_tier":null,"system_fingerprint":null,"usage":null}
{"id":"chatcmpl-a6f201a2-0f82-9260-ae13-23243b78239c","choices":[{"delta":{"content":"在","function_call":null,"refusal":null,"role":null,"tool_calls":null},"finish_reason":null,"index":0,"logprobs":null}],"created":1731683175,"model":"qwen-vl-max-latest","object":"chat.completion.chunk","service_tier":null,"system_fingerprint":null,"usage":null}
{"id":"chatcmpl-a6f201a2-0f82-9260-ae13-23243b78239c","choices":[{"delta":{"content":"海滩上拍摄的照片","function_call":null,"refusal":null,"role":null,"tool_calls":null},"finish_reason":null,"index":0,"logprobs":null}],"created":1731683175,"model":"qwen-vl-max-latest","object":"chat.completion.chunk","service_tier":null,"system_fingerprint":null,"usage":null}
{"id":"chatcmpl-a6f201a2-0f82-9260-ae13-23243b78239c","choices":[{"delta":{"content":"。照片中，","function_call":null,"refusal":null,"role":null,"tool_calls":null},"finish_reason":null,"index":0,"logprobs":null}],"created":1731683175,"model":"qwen-vl-max-latest","object":"chat.completion.chunk","service_tier":null,"system_fingerprint":null,"usage":null}
{"id":"chatcmpl-a6f201a2-0f82-9260-ae13-23243b78239c","choices":[{"delta":{"content":"一位女士和一只","function_call":null,"refusal":null,"role":null,"tool_calls":null},"finish_reason":null,"index":0,"logprobs":null}],"created":1731683175,"model":"qwen-vl-max-latest","object":"chat.completion.chunk","service_tier":null,"system_fingerprint":null,"usage":null}
{"id":"chatcmpl-a6f201a2-0f82-9260-ae13-23243b78239c","choices":[{"delta":{"content":"狗坐在沙滩上","function_call":null,"refusal":null,"role":null,"tool_calls":null},"finish_reason":null,"index":0,"logprobs":null}],"created":1731683175,"model":"qwen-vl-max-latest","object":"chat.completion.chunk","service_tier":null,"system_fingerprint":null,"usage":null}
{"id":"chatcmpl-a6f201a2-0f82-9260-ae13-23243b78239c","choices":[{"delta":{"content":"，女士正在与","function_call":null,"refusal":null,"role":null,"tool_calls":null},"finish_reason":null,"index":0,"logprobs":null}],"created":1731683175,"model":"qwen-vl-max-latest","object":"chat.completion.chunk","service_tier":null,"system_fingerprint":null,"usage":null}
{"id":"chatcmpl-a6f201a2-0f82-9260-ae13-23243b78239c","choices":[{"delta":{"content":"狗互动，似乎","function_call":null,"refusal":null,"role":null,"tool_calls":null},"finish_reason":null,"index":0,"logprobs":null}],"created":1731683175,"model":"qwen-vl-max-latest","object":"chat.completion.chunk","service_tier":null,"system_fingerprint":null,"usage":null}
{"id":"chatcmpl-a6f201a2-0f82-9260-ae13-23243b78239c","choices":[{"delta":{"content":"在握手或击","function_call":null,"refusal":null,"role":null,"tool_calls":null},"finish_reason":null,"index":0,"logprobs":null}],"created":1731683175,"model":"qwen-vl-max-latest","object":"chat.completion.chunk","service_tier":null,"system_fingerprint":null,"usage":null}
{"id":"chatcmpl-a6f201a2-0f82-9260-ae13-23243b78239c","choices":[{"delta":{"content":"掌。背景是","function_call":null,"refusal":null,"role":null,"tool_calls":null},"finish_reason":null,"index":0,"logprobs":null}],"created":1731683175,"model":"qwen-vl-max-latest","object":"chat.completion.chunk","service_tier":null,"system_fingerprint":null,"usage":null}
{"id":"chatcmpl-a6f201a2-0f82-9260-ae13-23243b78239c","choices":[{"delta":{"content":"大海和天空，","function_call":null,"refusal":null,"role":null,"tool_calls":null},"finish_reason":null,"index":0,"logprobs":null}],"created":1731683175,"model":"qwen-vl-max-latest","object":"chat.completion.chunk","service_tier":null,"system_fingerprint":null,"usage":null}
{"id":"chatcmpl-a6f201a2-0f82-9260-ae13-23243b78239c","choices":[{"delta":{"content":"阳光从画面的","function_call":null,"refusal":null,"role":null,"tool_calls":null},"finish_reason":null,"index":0,"logprobs":null}],"created":1731683175,"model":"qwen-vl-max-latest","object":"chat.completion.chunk","service_tier":null,"system_fingerprint":null,"usage":null}
{"id":"chatcmpl-a6f201a2-0f82-9260-ae13-23243b78239c","choices":[{"delta":{"content":"右侧照射过来，","function_call":null,"refusal":null,"role":null,"tool_calls":null},"finish_reason":null,"index":0,"logprobs":null}],"created":1731683175,"model":"qwen-vl-max-latest","object":"chat.completion.chunk","service_tier":null,"system_fingerprint":null,"usage":null}
{"id":"chatcmpl-a6f201a2-0f82-9260-ae13-23243b78239c","choices":[{"delta":{"content":"营造出温暖的","function_call":null,"refusal":null,"role":null,"tool_calls":null},"finish_reason":null,"index":0,"logprobs":null}],"created":1731683175,"model":"qwen-vl-max-latest","object":"chat.completion.chunk","service_tier":null,"system_fingerprint":null,"usage":null}
{"id":"chatcmpl-a6f201a2-0f82-9260-ae13-23243b78239c","choices":[{"delta":{"content":"氛围。","function_call":null,"refusal":null,"role":null,"tool_calls":null},"finish_reason":"stop","index":0,"logprobs":null}],"created":1731683175,"model":"qwen-vl-max-latest","object":"chat.completion.chunk","service_tier":null,"system_fingerprint":null,"usage":null}

Node.js

import OpenAI from "openai";

const openai = new OpenAI(
    {
        // 若没有配置环境变量，请用百炼API Key将下行替换为：apiKey: "sk-xxx",
        apiKey: process.env.DASHSCOPE_API_KEY,
        baseURL: "https://dashscope.aliyuncs.com/compatible-mode/v1"
    }
);

const completion = await openai.chat.completions.create({
    model: "qwen-vl-max-latest",
    messages: [
        {"role": "user",
        "content": [{"type": "image_url",
                    "image_url": {"url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"},},
                    {"type": "text", "text": "这是什么"}]}],
    stream: true,
});

console.log("流式输出内容为：")
for await (const chunk of completion) {
        console.log(JSON.stringify(chunk));
}

{"choices":[{"delta":{"content":"","role":"assistant"},"index":0,"logprobs":null,"finish_reason":null}],"object":"chat.completion.chunk","usage":null,"created":1731942585,"system_fingerprint":null,"model":"qwen-vl-max-latest","id":"chatcmpl-9d466dd4-7cbe-9eb1-a429-c0d5a81f2674"}
{"choices":[{"finish_reason":null,"delta":{"content":"这"},"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1731942585,"ystem_fingerprint":null,"model":"qwen-vl-max-latest","id":"chatcmpl-9d466dd4-7cbe-9eb1-a429-c0d5a81f2674"}
{"choices":[{"delta":{"content":"是一"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1731942585system_fingerprint":null,"model":"qwen-vl-max-latest","id":"chatcmpl-9d466dd4-7cbe-9eb1-a429-c0d5a81f2674"}
{"choices":[{"delta":{"content":"张"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1731942585,"ystem_fingerprint":null,"model":"qwen-vl-max-latest","id":"chatcmpl-9d466dd4-7cbe-9eb1-a429-c0d5a81f2674"}
{"choices":[{"delta":{"content":"在"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1731942585,"system_fingerprint":null,"model":"qwen-vl-max-latest","id":"chatcmpl-9d466dd4-7cbe-9eb1-a429-c0d5a81f2674"}
{"choices":[{"delta":{"content":"海滩上拍摄的照片"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created2585,"system_fingerprint":null,"model":"qwen-vl-max-latest","id":"chatcmpl-9d466dd4-7cbe-9eb1-a429-c0d5a81f2674"}
{"choices":[{"delta":{"content":"。照片中，"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":17315,"system_fingerprint":null,"model":"qwen-vl-max-latest","id":"chatcmpl-9d466dd4-7cbe-9eb1-a429-c0d5a81f2674"}
{"choices":[{"delta":{"content":"一位女士和一只"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":585,"system_fingerprint":null,"model":"qwen-vl-max-latest","id":"chatcmpl-9d466dd4-7cbe-9eb1-a429-c0d5a81f2674"}
{"choices":[{"delta":{"content":"狗坐在沙滩上"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1785,"system_fingerprint":null,"model":"qwen-vl-max-latest","id":"chatcmpl-9d466dd4-7cbe-9eb1-a429-c0d5a81f2674"}
{"choices":[{"delta":{"content":"，女士正在与"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1785,"system_fingerprint":null,"model":"qwen-vl-max-latest","id":"chatcmpl-9d466dd4-7cbe-9eb1-a429-c0d5a81f2674"}
{"choices":[{"delta":{"content":"狗互动，似乎"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1785,"system_fingerprint":null,"model":"qwen-vl-max-latest","id":"chatcmpl-9d466dd4-7cbe-9eb1-a429-c0d5a81f2674"}
{"choices":[{"delta":{"content":"在握手或击"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":17315,"system_fingerprint":null,"model":"qwen-vl-max-latest","id":"chatcmpl-9d466dd4-7cbe-9eb1-a429-c0d5a81f2674"}
{"choices":[{"delta":{"content":"掌。背景是"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":17315,"system_fingerprint":null,"model":"qwen-vl-max-latest","id":"chatcmpl-9d466dd4-7cbe-9eb1-a429-c0d5a81f2674"}
{"choices":[{"delta":{"content":"大海和天空，"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1785,"system_fingerprint":null,"model":"qwen-vl-max-latest","id":"chatcmpl-9d466dd4-7cbe-9eb1-a429-c0d5a81f2674"}
{"choices":[{"delta":{"content":"阳光从画面的"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1785,"system_fingerprint":null,"model":"qwen-vl-max-latest","id":"chatcmpl-9d466dd4-7cbe-9eb1-a429-c0d5a81f2674"}
{"choices":[{"delta":{"content":"右侧照射过来，"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":585,"system_fingerprint":null,"model":"qwen-vl-max-latest","id":"chatcmpl-9d466dd4-7cbe-9eb1-a429-c0d5a81f2674"}
{"choices":[{"delta":{"content":"营造出温暖的"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1785,"system_fingerprint":null,"model":"qwen-vl-max-latest","id":"chatcmpl-9d466dd4-7cbe-9eb1-a429-c0d5a81f2674"}
{"choices":[{"delta":{"content":"氛围。"},"finish_reason":"stop","index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1731945,"system_fingerprint":null,"model":"qwen-vl-max-latest","id":"chatcmpl-9d466dd4-7cbe-9eb1-a429-c0d5a81f2674"}

curl

curl --location 'https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "model": "qwen-vl-plus",
    "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "image_url",
          "image_url": {
            "url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"
          }
        },
        {
          "type": "text",
          "text": "这是什么"
        }
      ]
    }
  ],
    "stream":true,
    "stream_options":{"include_usage":true}
}'

返回结果

data: {"choices":[{"delta":{"content":"","role":"assistant"},"index":0,"logprobs":null,"finish_reason":null}],"object":"chat.completion.chunk","usage":null,"created":1721823635,"system_fingerprint":null,"model":"qwen-vl-plus","id":"chatcmpl-9a9ec75a-3109-9910-b79e-7bcbce81c8f9"}

data: {"choices":[{"finish_reason":null,"delta":{"content":"图"},"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1721823635,"system_fingerprint":null,"model":"qwen-vl-plus","id":"chatcmpl-9a9ec75a-3109-9910-b79e-7bcbce81c8f9"}

data: {"choices":[{"delta":{"content":"中"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1721823635,"system_fingerprint":null,"model":"qwen-vl-plus","id":"chatcmpl-9a9ec75a-3109-9910-b79e-7bcbce81c8f9"}

......

data: {"choices":[{"delta":{"content":"分拍摄的照片。整体氛围显得非常"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1721823635,"system_fingerprint":null,"model":"qwen-vl-plus","id":"chatcmpl-9a9ec75a-3109-9910-b79e-7bcbce81c8f9"}

data: {"choices":[{"finish_reason":"stop","delta":{"content":"和谐而温馨。"},"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1721823635,"system_fingerprint":null,"model":"qwen-vl-plus","id":"chatcmpl-9a9ec75a-3109-9910-b79e-7bcbce81c8f9"}

data: {"choices":[],"object":"chat.completion.chunk","usage":{"prompt_tokens":1276,"completion_tokens":85,"total_tokens":1361},"created":1721823635,"system_fingerprint":null,"model":"qwen-vl-plus","id":"chatcmpl-9a9ec75a-3109-9910-b79e-7bcbce81c8f9"}

data: [DONE]

Python

import os
from dashscope import MultiModalConversation

messages = [
    {
        "role": "user",
        "content": [
            {"image": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"},
            {"text": "这是什么?"}
        ]
    }
]
responses = MultiModalConversation.call(
    # 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"),
    model='qwen-vl-max-latest',
    messages=messages,
    stream=True,
    incremental_output=True
    )
print("流式输出内容为：")
for response in responses:
    print(response["output"])

返回结果

{"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": [{"text": "这"}]}}]}
{"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": [{"text": "是一"}]}}]}
{"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": [{"text": "张"}]}}]}
{"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": [{"text": "在"}]}}]}
{"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": [{"text": "海滩上拍摄的照片"}]}}]}
{"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": [{"text": "。照片中有一位"}]}}]}
{"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": [{"text": "女士和一只狗"}]}}]}
{"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": [{"text": "。女士坐在沙滩"}]}}]}
{"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": [{"text": "上，微笑着"}]}}]}
{"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": [{"text": "与狗互动。"}]}}]}
{"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": [{"text": "狗戴着项圈"}]}}]}
{"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": [{"text": "，似乎在与"}]}}]}
{"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": [{"text": "女士握手。背景"}]}}]}
{"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": [{"text": "是大海和天空"}]}}]}
{"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": [{"text": "，阳光洒在"}]}}]}
{"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": [{"text": "她们身上，营造"}]}}]}
{"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": [{"text": "出温馨的氛围"}]}}]}
{"text": null, "finish_reason": null, "choices": [{"finish_reason": "stop", "message": {"role": "assistant", "content": [{"text": "。"}]}}]}

Java

import java.util.Arrays;
import java.util.HashMap;

import com.alibaba.dashscope.aigc.generation.GenerationResult;
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 io.reactivex.Flowable;

public class Main {
    public static void streamCall()
            throws ApiException, NoApiKeyException, UploadFileException {
        MultiModalConversation conv = new MultiModalConversation();
        // must create mutable map.
        MultiModalMessage userMessage = MultiModalMessage.builder().role(Role.USER.getValue())
                .content(Arrays.asList(new HashMap<String, Object>(){{put("image", "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg");}},
                        new HashMap<String, Object>(){{put("text", "这是什么");}})).build();
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                // 若没有配置环境变量，请用百炼API Key将下行替换为：.apiKey("sk-xxx")
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .model("qwen-vl-max-latest")
                .message(userMessage)
                .incrementalOutput(true)
                .build();
        Flowable<MultiModalConversationResult> result = conv.streamCall(param);
        result.blockingForEach(item -> {
            try {
                System.out.println(JsonUtils.toJson(item));
            } catch (Exception e){
                System.exit(0);
            }
        });
    }

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

返回结果

{"requestId":"a750aa02-e0c9-9c10-8542-2f38bf9de326","usage":{"input_tokens":1270,"output_tokens":1},"output":{"choices":[{"finish_reason":"null","message":{"role":"assistant","content":[{"text":"这"}]}}]}}
{"requestId":"a750aa02-e0c9-9c10-8542-2f38bf9de326","usage":{"input_tokens":1270,"output_tokens":2},"output":{"choices":[{"finish_reason":"null","message":{"role":"assistant","content":[{"text":"是一"}]}}]}}
{"requestId":"a750aa02-e0c9-9c10-8542-2f38bf9de326","usage":{"input_tokens":1270,"output_tokens":3},"output":{"choices":[{"finish_reason":"null","message":{"role":"assistant","content":[{"text":"张"}]}}]}}
{"requestId":"a750aa02-e0c9-9c10-8542-2f38bf9de326","usage":{"input_tokens":1270,"output_tokens":4},"output":{"choices":[{"finish_reason":"null","message":{"role":"assistant","content":[{"text":"在"}]}}]}}
{"requestId":"a750aa02-e0c9-9c10-8542-2f38bf9de326","usage":{"input_tokens":1270,"output_tokens":8},"output":{"choices":[{"finish_reason":"null","message":{"role":"assistant","content":[{"text":"海滩上拍摄的照片"}]}}]}}
{"requestId":"a750aa02-e0c9-9c10-8542-2f38bf9de326","usage":{"input_tokens":1270,"output_tokens":12},"output":{"choices":[{"finish_reason":"null","message":{"role":"assistant","content":[{"text":"。照片中，"}]}}]}}
{"requestId":"a750aa02-e0c9-9c10-8542-2f38bf9de326","usage":{"input_tokens":1270,"output_tokens":16},"output":{"choices":[{"finish_reason":"null","message":{"role":"assistant","content":[{"text":"一位穿着格子"}]}}]}}
{"requestId":"a750aa02-e0c9-9c10-8542-2f38bf9de326","usage":{"input_tokens":1270,"output_tokens":20},"output":{"choices":[{"finish_reason":"null","message":{"role":"assistant","content":[{"text":"衬衫的女士坐在"}]}}]}}
{"requestId":"a750aa02-e0c9-9c10-8542-2f38bf9de326","usage":{"input_tokens":1270,"output_tokens":24},"output":{"choices":[{"finish_reason":"null","message":{"role":"assistant","content":[{"text":"沙滩上，与"}]}}]}}
{"requestId":"a750aa02-e0c9-9c10-8542-2f38bf9de326","usage":{"input_tokens":1270,"output_tokens":28},"output":{"choices":[{"finish_reason":"null","message":{"role":"assistant","content":[{"text":"一只戴着项圈"}]}}]}}
{"requestId":"a750aa02-e0c9-9c10-8542-2f38bf9de326","usage":{"input_tokens":1270,"output_tokens":32},"output":{"choices":[{"finish_reason":"null","message":{"role":"assistant","content":[{"text":"的金毛犬"}]}}]}}
{"requestId":"a750aa02-e0c9-9c10-8542-2f38bf9de326","usage":{"input_tokens":1270,"output_tokens":36},"output":{"choices":[{"finish_reason":"null","message":{"role":"assistant","content":[{"text":"互动。背景是"}]}}]}}
{"requestId":"a750aa02-e0c9-9c10-8542-2f38bf9de326","usage":{"input_tokens":1270,"output_tokens":40},"output":{"choices":[{"finish_reason":"null","message":{"role":"assistant","content":[{"text":"大海和天空，"}]}}]}}
{"requestId":"a750aa02-e0c9-9c10-8542-2f38bf9de326","usage":{"input_tokens":1270,"output_tokens":44},"output":{"choices":[{"finish_reason":"null","message":{"role":"assistant","content":[{"text":"阳光洒在她们"}]}}]}}
{"requestId":"a750aa02-e0c9-9c10-8542-2f38bf9de326","usage":{"input_tokens":1270,"output_tokens":48},"output":{"choices":[{"finish_reason":"null","message":{"role":"assistant","content":[{"text":"身上，营造出"}]}}]}}
{"requestId":"a750aa02-e0c9-9c10-8542-2f38bf9de326","usage":{"input_tokens":1270,"output_tokens":52},"output":{"choices":[{"finish_reason":"null","message":{"role":"assistant","content":[{"text":"温暖的氛围。"}]}}]}}
{"requestId":"a750aa02-e0c9-9c10-8542-2f38bf9de326","usage":{"input_tokens":1270,"output_tokens":53},"output":{"choices":[{"finish_reason":"stop","message":{"role":"assistant","content":[]}}]}}

curl

curl -X POST https://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H 'Content-Type: application/json' \
-H 'X-DashScope-SSE: enable' \
-d '{
    "model": "qwen-vl-plus",
    "input":{
        "messages":[
            {
                "role": "system",
                "content": [
                    {"text": "You are a helpful assistant."}
                ]
            },
            {
                "role": "user",
                "content": [
                    {"image": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"},
                    {"text": "这是什么?"}
                ]
            }
        ]
    },
    "parameters": {
        "incremental_output": true
    }
}'

返回结果

iid:1
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":[{"text":"这张"}],"role":"assistant"},"finish_reason":"null"}]},"usage":{"input_tokens":1276,"output_tokens":1,"image_tokens":1247},"request_id":"00917f72-d927-9344-8417-2c4088d64c16"}

id:2
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":[{"text":"图片"}],"role":"assistant"},"finish_reason":"null"}]},"usage":{"input_tokens":1276,"output_tokens":2,"image_tokens":1247},"request_id":"00917f72-d927-9344-8417-2c4088d64c16"}

......

id:17
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":[{"text":"的欣赏。这是一个温馨的画面，展示了"}],"role":"assistant"},"finish_reason":"null"}]},"usage":{"input_tokens":1276,"output_tokens":112,"image_tokens":1247},"request_id":"00917f72-d927-9344-8417-2c4088d64c16"}

id:18
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":[{"text":"人与动物之间深厚的情感纽带。"}],"role":"assistant"},"finish_reason":"null"}]},"usage":{"input_tokens":1276,"output_tokens":120,"image_tokens":1247},"request_id":"00917f72-d927-9344-8417-2c4088d64c16"}

id:19
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":[],"role":"assistant"},"finish_reason":"stop"}]},"usage":{"input_tokens":1276,"output_tokens":121,"image_tokens":1247},"request_id":"00917f72-d927-9344-8417-2c4088d64c16"}

Python

from openai import OpenAI
import os
import base64


#  base 64 编码格式
def encode_image(image_path):
    with open(image_path, "rb") as image_file:
        return base64.b64encode(image_file.read()).decode("utf-8")


base64_image = encode_image("test.png")
client = OpenAI(
    # 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'),
    base_url="https://dashscope.aliyuncs.com/compatible-mode/v1",
)
completion = client.chat.completions.create(
    model="qwen-vl-max-latest",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    # 使用格式化字符串 (f-string) 创建一个包含 BASE64 编码图像数据的字符串。
                    "image_url": {"url": f"data:image/jpeg;base64,{base64_image}"}, 
                },
                {"type": "text", "text": "这是什么"},
            ],
        }
    ],
)
print(completion.choices[0].message.content)

返回结果

这是一只飞翔的鹰。鹰是一种猛禽，通常具有强壮的翅膀和锐利的爪子，擅长在高空翱翔和捕猎。图片中的鹰展翅高飞，背景是蓝天白云，显得非常壮观。

Node.js

import OpenAI from "openai";
import { readFileSync } from 'fs';


const openai = new OpenAI(
    {
        // 若没有配置环境变量，请用百炼API Key将下行替换为：apiKey: "sk-xxx",
        apiKey: process.env.DASHSCOPE_API_KEY,
        baseURL: "https://dashscope.aliyuncs.com/compatible-mode/v1"
    }
);

const encodeImage = (imagePath) => {
    const imageFile = readFileSync(imagePath);
    return imageFile.toString('base64');
  };
const base64Image = encodeImage("test.png")
async function main() {
    const completion = await openai.chat.completions.create({
        model: "qwen-vl-max-latest",
        messages: [
            {"role": "user",
            "content": [{"type": "image_url",
                        "image_url": {"url": `data:image/jpeg;base64,${base64Image}`},},
                        {"type": "text", "text": "这是什么"}]}]
    });
    console.log(completion.choices[0].message.content);
} 

main();

返回结果

这是一只飞翔的鹰。鹰是一种猛禽，通常具有强壮的翅膀和锐利的爪子，能够在高空翱翔并捕猎猎物。图片中的鹰展翅高飞，背景是蓝天白云，显得非常壮观。

HTTP

import os
import base64
import requests

#  base 64 编码格式
def encode_image(image_path):
    with open(image_path, "rb") as image_file:
        return base64.b64encode(image_file.read()).decode("utf-8")


base64_image = encode_image("test.png")
# 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")
headers = {"Content-Type": "application/json", "Authorization": f"Bearer {api_key}"}
payload = {
    "model": "qwen-vl-max-latest",
    "messages": [
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": {"url": f"data:image/jpeg;base64,{base64_image}"},
                },
                {"type": "text", "text": "这是什么"},
            ],
        }
    ],
}
response = requests.post(
    "https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions",
    headers=headers,
    json=payload,
)
print(response.json()["choices"][0]["message"]["content"])

返回结果

这是一只飞翔的鹰。鹰是一种猛禽，通常具有强壮的翅膀和锐利的爪子，能够在高空翱翔并捕猎猎物。图片中的鹰展翅高飞，背景是蓝天白云，显得非常壮观。

Python

import os
from dashscope import MultiModalConversation

local_path = "test.png"
image_path = f"file://{local_path}"
messages = [{'role': 'system',
                'content': [{'text': 'You are a helpful assistant.'}]}, 
                {'role':'user',
                'content': [{'image': image_path},
                            {'text': '这是什么'}]}]
response = MultiModalConversation.call(
    # 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'),
    model='qwen-vl-max-latest', 
    messages=messages)
print(response["output"]["choices"][0]["message"].content[0]["text"])

返回结果

这是一只飞翔的鹰。鹰是一种猛禽，通常具有强壮的翅膀和锐利的爪子，能够在高空翱翔并捕猎猎物。图片中的鹰展翅高飞，背景是蓝天白云，显得非常壮观。

Java

import java.util.Arrays;
import java.util.HashMap;
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;

public class Main {
    public static void callWithLocalFile(String localPath)
            throws ApiException, NoApiKeyException, UploadFileException {
        String filePath = "file://"+localPath;
        MultiModalConversation conv = new MultiModalConversation();
        MultiModalMessage userMessage = MultiModalMessage.builder().role(Role.USER.getValue())
                .content(Arrays.asList(new HashMap<String, Object>(){{put("image", filePath);}},
                        new HashMap<String, Object>(){{put("text", "这是什么?");}})).build();
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                // 若没有配置环境变量，请用百炼API Key将下行替换为：.apiKey("sk-xxx")
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .model("qwen-vl-max-latest")
                .message(userMessage)
                .build();
        MultiModalConversationResult result = conv.call(param);
        System.out.println(result.getOutput().getChoices().get(0).getMessage().getContent().get(0).get("text"));}

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

返回结果

这是一只飞翔的鹰。鹰是一种猛禽，通常具有强壮的翅膀和锐利的爪子，擅长在高空翱翔和捕猎。图片中的鹰展翅高飞，背景是蓝天白云，显得非常壮观。

Python

import os
from openai import OpenAI

client = OpenAI(
    # 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"),
    base_url="https://dashscope.aliyuncs.com/compatible-mode/v1",
)
completion = client.chat.completions.create(
    model="qwen-vl-max-latest",
    messages=[{"role": "user","content": [
        {"type": "video","video": ["https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/xzsgiz/football1.jpg",
                           "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/tdescd/football2.jpg",
                           "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/zefdja/football3.jpg",
                           "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/aedbqh/football4.jpg"]},
        {"type": "text","text": "描述这个视频的具体过程"},
    ]}]
)
print(completion.choices[0].message.content)

返回结果

这个视频展示了一场足球比赛的瞬间。具体过程如下：

1. **背景**：视频是在一个大型体育场拍摄的，观众席上坐满了观众，灯光明亮，气氛热烈。
2. **球员**：场上有两队球员，一队穿着红色球衣，另一队穿着蓝色球衣。守门员穿着绿色球衣。
3. **动作**：一名穿着红色球衣的球员在禁区内准备射门。守门员试图扑救，但未能成功。
4. **进球**：红色球衣的球员成功将球踢入球门，球网被球击中，显示出进球的瞬间。

整个过程充满了紧张和激动，展示了足球比赛中的精彩瞬间。

Node.js

// 确保之前在 package.json 中指定了 "type": "module"
import OpenAI from "openai";

const openai = new OpenAI({
    // 若没有配置环境变量，请用百炼API Key将下行替换为：apiKey: "sk-xxx",
    apiKey: process.env.DASHSCOPE_API_KEY,
    baseURL: "https://dashscope.aliyuncs.com/compatible-mode/v1"
});

async function main() {
    const response = await openai.chat.completions.create({
        model: "qwen-vl-max-latest",
        messages: [{
            role: "user",
            content: [
                {
                    type: "video",
                    video: [
                        "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/xzsgiz/football1.jpg",
                        "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/tdescd/football2.jpg",
                        "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/zefdja/football3.jpg",
                        "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/aedbqh/football4.jpg"
                    ]
                },
                {
                    type: "text",
                    text: "描述这个视频的具体过程"
                }
            ]
        }]
    });
    console.log(response.choices[0].message.content);
}

main();

返回结果

这个视频展示了一场足球比赛的瞬间。具体过程如下：

1. **背景**：视频是在一个大型体育场拍摄的，观众席上坐满了观众，灯光明亮，气氛热烈。
2. **球员**：场上有两队球员，一队穿着红色球衣，另一队穿着蓝色球衣。守门员穿着绿色球衣。
3. **动作**：一名穿着红色球衣的球员在禁区内准备射门。他将球踢向球门。
4. **守门员**：守门员看到球飞来，迅速做出反应，向球的方向扑去，试图将球扑出。
5. **进球**：尽管守门员尽力扑救，但球还是飞进了球门，网子被球撞得晃动。

这个视频捕捉到了足球比赛中进球的精彩瞬间，展示了球员的技巧和守门员的反应。

curl

curl -X POST https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
    "model": "qwen-vl-max-latest",
    "messages": [{"role": "user",
                "content": [{"type": "video",
                "video": ["https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/xzsgiz/football1.jpg",
                           "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/tdescd/football2.jpg",
                           "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/zefdja/football3.jpg",
                           "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/aedbqh/football4.jpg"]},
                {"type": "text",
                "text": "描述这个视频的具体过程"}]}]
}'

返回结果

{
  "choices": [
    {
      "message": {
        "content": "这个视频展示了一场足球比赛的瞬间。具体过程如下：\n\n1. **背景**：视频是在一个大型体育场内拍摄的，观众席上坐满了观众，灯光明亮，气氛热烈。\n2. **球员**：场上有两支队伍，一支穿着红色球衣，另一支穿着蓝色球衣。守门员穿着绿色球衣。\n3. **动作**：一名身穿红色球衣的球员在禁区内接到传球，准备射门。守门员迅速反应，向球的方向扑去，试图阻止进球。\n4. **射门**：红色球衣的球员果断射门，球飞向球门。\n5. **扑救**：守门员尽力扑救，但球还是飞进了球门，球网被球撞得晃动。\n\n整个过程充满了紧张和刺激，展示了足球比赛中的精彩瞬间。",
        "role": "assistant"
      },
      "finish_reason": "stop",
      "index": 0,
      "logprobs": null
    }
  ],
  "object": "chat.completion",
  "usage": {
    "prompt_tokens": 1466,
    "completion_tokens": 181,
    "total_tokens": 1647
  },
  "created": 1728710375,
  "system_fingerprint": null,
  "model": "qwen-vl-max-latest",
  "id": "chatcmpl-73b2b130-b29a-99db-9eda-4cd45f27d4e0"
}

Python

import os
# dashscope版本需要不低于1.20.10
import dashscope

messages = [{"role": "user",
             "content": [
                 {"video":["https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/xzsgiz/football1.jpg",
                           "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/tdescd/football2.jpg",
                           "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/zefdja/football3.jpg",
                           "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/aedbqh/football4.jpg"]},
                 {"text": "描述这个视频的具体过程"}]}]
response = dashscope.MultiModalConversation.call(
    # 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"),
    model='qwen-vl-max-latest',
    messages=messages
)
print(response["output"]["choices"][0]["message"].content[0]["text"])

返回结果

这个视频展示了一场足球比赛的瞬间。具体过程如下：

1. **背景**：视频是在一个大型体育场内拍摄的，观众席上坐满了观众，灯光明亮，气氛热烈。
2. **球员**：场上有两支队伍，一支穿着红色球衣，另一支穿着蓝色球衣。守门员穿着绿色球衣。
3. **动作**：一名身穿红色球衣的球员在禁区内准备射门。他将球踢向球门。
4. **守门员**：守门员看到球飞来，迅速做出反应，向球的方向扑去，试图将球扑出。
5. **进球**：尽管守门员尽力扑救，但球还是飞进了球门，网子被球撞得晃动。

这个视频捕捉到了足球比赛中进球的精彩瞬间，展示了球员的技巧和守门员的反应。

Java

// DashScope SDK版本需要不低于2.16.7
import java.util.Arrays;
import java.util.Collections;
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;

public class Main {
    private static final String MODEL_NAME = "qwen-vl-max-latest";
    public static void videoImageListSample() throws ApiException, NoApiKeyException, UploadFileException {
        MultiModalConversation conv = new MultiModalConversation();
        MultiModalMessage systemMessage = MultiModalMessage.builder()
                .role(Role.SYSTEM.getValue())
                .content(Arrays.asList(Collections.singletonMap("text", "You are a helpful assistant.")))
                .build();
        MultiModalMessage userMessage = MultiModalMessage.builder()
                .role(Role.USER.getValue())
                .content(Arrays.asList(Collections.singletonMap("video", Arrays.asList("https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/xzsgiz/football1.jpg",
                                "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/tdescd/football2.jpg",
                                "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/zefdja/football3.jpg",
                                "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/aedbqh/football4.jpg")),
                        Collections.singletonMap("text", "描述这个视频的具体过程")))
                .build();
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                .model(MODEL_NAME).message(systemMessage)
                .message(userMessage).build();
        MultiModalConversationResult result = conv.call(param);
        System.out.print(result.getOutput().getChoices().get(0).getMessage().getContent().get(0).get("text"));
    }
    public static void main(String[] args) {
        try {
            videoImageListSample();
        } catch (ApiException | NoApiKeyException | UploadFileException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}

返回结果

这个视频展示了一场足球比赛的瞬间。具体过程如下：

1. **背景**：视频是在一个大型体育场内拍摄的，观众席上坐满了观众，灯光明亮，气氛热烈。
2. **球员**：场上有两队球员，一队穿着红色球衣，另一队穿着蓝色球衣。守门员穿着绿色球衣。
3. **动作**：一名身穿红色球衣的球员在禁区内准备射门。他将球踢向球门。
4. **守门员**：守门员看到球飞来，迅速做出反应，向球的方向扑去，试图将球扑出。
5. **进球**：尽管守门员尽力扑救，但球还是飞进了球门，网子被球撞得晃动。

这个视频捕捉到了足球比赛中进球的精彩瞬间，展示了球员的技巧和守门员的反应。

curl

curl -X POST https://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
  "model": "qwen-vl-max-latest",
  "input": {
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "video": [
              "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/xzsgiz/football1.jpg",
              "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/tdescd/football2.jpg",
              "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/zefdja/football3.jpg",
              "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/aedbqh/football4.jpg"
            ]
                 
          },
          {
            "text": "描述这个视频的具体过程"
          }
        ]
      }
    ]
  }
}'

返回结果

{
  "output": {
    "choices": [
      {
        "finish_reason": "stop",
        "message": {
          "role": "assistant",
          "content": [
            {
              "text": "这个视频展示了一场足球比赛的瞬间。具体过程如下：\n\n1. **背景**：视频是在一个大型体育场拍摄的，观众席上坐满了观众，灯光明亮，气氛热烈。\n2. **球员**：场上有两队球员，一队穿着红色球衣，另一队穿着蓝色球衣。守门员穿着绿色球衣。\n3. **动作**：一名穿着红色球衣的球员在禁区内接到了队友的传球，准备射门。\n4. **射门**：红色球员用右脚大力射门，球飞向球门。\n5. **扑救**：守门员迅速反应，向球的方向扑去，试图将球扑出。\n6. **进球**：尽管守门员尽力扑救，但球还是飞进了球门，守门员未能阻止进球。\n\n整个过程充满了紧张和激动，展示了足球比赛中的精彩瞬间。"
            }
          ]
        }
      }
    ]
  },
  "usage": {
    "output_tokens": 191,
    "video_tokens": 1440,
    "input_tokens": 1466
  },
  "request_id": "c728d1e0-79ad-9076-8589-7f072e96bccf"
}