Teks-ke-gambar

• Model Experience Center: Klik tautan Coba secara online di atas (Singapura, Beijing) untuk membukanya. Anda dapat memilih model, mengatur resolusi output, mengaktifkan prompt rewriting, dan mengirimkan permintaan untuk menghasilkan gambar.

​

Kinerja model

​

Qwen-Image

Tata letak kompleks	Paragraf panjang	Portret realistis
Desain UI	PPT	Desain ilustrasi

​

Wanxiang

Fotografi potret	Fotografi fotorealistik	Gaya artistik
Rendering teks	Desain poster	Generasi set gambar

​

Pemilihan model

• qwen-image-3.0-pro: Model unggulan Qwen Image 3.0. Mendukung penulisan ulang prompt cerdas dan unggul dalam rendering teks yang menyatu alami dengan material fisik dalam bahasa Mandarin dan Inggris.
• wan2.7-image-pro: Menawarkan fitur paling lengkap, termasuk generasi multi-gambar, resolusi hingga 4096x4096, dan kontrol lebih baik atas fitur wajah, warna, dan rendering teks panjang.
• z-image-turbo: Memberikan generasi gambar cepat dan hemat biaya, unggul dalam potret dan gambar produk sangat realistis.

​

Opsi penggunaan

​

Memulai cepat

​

Prasyarat

​

Kode contoh

• Semua model teks-ke-gambar Qwen mendukung panggilan sinkron. Seri qwen-image-3.0, model qwen-image-plus dan qwen-image juga mendukung panggilan asinkron. Untuk informasi lebih lanjut, lihat Qwen - Generasi dan Pengeditan Gambar 3.0 dan Qwen - Teks-ke-Gambar.
• Semua model teks-ke-gambar Wan mendukung panggilan asinkron. Model wan2.7-image-pro, wan2.7-image, wan2.6-image, dan wan2.6-t2i juga mendukung panggilan sinkron. Untuk informasi lebih lanjut, lihat Wan - Generasi dan Pengeditan Gambar 2.7, Wan - Generasi dan Pengeditan Gambar 2.6, dan Wan - Teks-ke-Gambar V2.

import os
import dashscope
from dashscope import MultiModalConversation

dashscope.base_http_api_url = 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1'

response = MultiModalConversation.call(
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    model="qwen-image-3.0-pro",
    messages=[{
        "role": "user",
        "content": [
            {"text": "A vertical outdoor portrait photograph with a warm afternoon street atmosphere. Deep green vines and small orange flowers cascade from building eaves across the upper area. A dark blue sign reads 'Il Messaggero' in white Gothic lettering, partially obscured by foliage. Below, a newsstand displays newspapers behind black metal-framed glass, blurred by shallow depth of field. Strong backlight streams from the street's end. Center-right, a young woman in a black spaghetti-strap backless dress looks back at the camera with a warm smile. Her long, thick wavy black hair is outlined by golden rim light. She has fair skin, bright eyes, soft coral-red lips, and holds a large bouquet of orange, apricot, pink and peach roses contrasting with her black dress. The sunlit city street stretches into the blurred background. Warm film-like tones with fine grain, soft contrast and pronounced backlit edge glow create a romantic, bright, urban strolling atmosphere."}
        ]
    }],
    prompt_extend=True
)

print(response)
if response.status_code == 200:
    url = response.output.choices[0].message.content[0]["image"]
    print(f"Generated image URL: {url}")
else:
    print(f"Error: {response.code} - {response.message}")

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.utils.Constants;

public class ImageEditExample {
    public static void main(String[] args) {
        Constants.baseHttpApiUrl = "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1";

        MultiModalConversation conv = new MultiModalConversation();
        MultiModalMessage userMessage = MultiModalMessage.builder()
            .role(Role.USER.getValue())
            .content(Arrays.asList(
                Collections.singletonMap("text", "A vertical outdoor portrait photograph with a warm afternoon street atmosphere. Deep green vines and small orange flowers cascade from building eaves across the upper area. A dark blue sign reads 'Il Messaggero' in white Gothic lettering, partially obscured by foliage. Below, a newsstand displays newspapers behind black metal-framed glass, blurred by shallow depth of field. Strong backlight streams from the street's end. Center-right, a young woman in a black spaghetti-strap backless dress looks back at the camera with a warm smile. Her long, thick wavy black hair is outlined by golden rim light. She has fair skin, bright eyes, soft coral-red lips, and holds a large bouquet of orange, apricot, pink and peach roses contrasting with her black dress. The sunlit city street stretches into the blurred background. Warm film-like tones with fine grain, soft contrast and pronounced backlit edge glow create a romantic, bright, urban strolling atmosphere.")
            ))
            .build();
        MultiModalConversationParam param = MultiModalConversationParam.builder()
            .apiKey(System.getenv("DASHSCOPE_API_KEY"))
            .model("qwen-image-3.0-pro")
            .messages(Arrays.asList(userMessage))
            .parameter("prompt_extend", true)
            .build();
        try {
            MultiModalConversationResult result = conv.call(param);
            System.out.println(result);
        } catch (Exception e) {
            e.printStackTrace();
        }
    }
}

curl --location 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation' \
--header 'Content-Type: application/json' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--data '{
    "model": "qwen-image-3.0-pro",
    "input": {
        "messages": [
            {
                "role": "user",
                "content": [
                    {
                        "text": "A vertical outdoor portrait photograph with a warm afternoon street atmosphere. Deep green vines and small orange flowers cascade from building eaves across the upper area. A dark blue sign reads '\''Il Messaggero'\'' in white Gothic lettering, partially obscured by foliage. Below, a newsstand displays newspapers behind black metal-framed glass, blurred by shallow depth of field. Strong backlight streams from the street'\''s end. Center-right, a young woman in a black spaghetti-strap backless dress looks back at the camera with a warm smile. Her long, thick wavy black hair is outlined by golden rim light. She has fair skin, bright eyes, soft coral-red lips, and holds a large bouquet of orange, apricot, pink and peach roses contrasting with her black dress. The sunlit city street stretches into the blurred background. Warm film-like tones with fine grain, soft contrast and pronounced backlit edge glow create a romantic, bright, urban strolling atmosphere."
                    }
                ]
            }
        ]
    },
    "parameters": {
        "prompt_extend": true
    }
}'

{
    "output": {
        "choices": [
            {
                "finish_reason": "stop",
                "message": {
                    "content": [
                        {
                            "image": "https://dashscope-result-sz.oss-cn-shenzhen.aliyuncs.com/xxx.png?Expires=xxx"
                        }
                    ],
                    "role": "assistant"
                }
            }
        ]
    },
    "usage": {
        "output_height": 1024,
        "output_width": 1024,
        "input_image_count": 0,
        "input_image_type": "qima_input_1k",
        "output_image_count": 1,
        "output_image_type": "qima_output_1k"
    },
    "request_id": "571ae02f-5c9d-436c-83c2-f221e6df0xxx"
}

import os
import dashscope
from dashscope.aigc.image_generation import ImageGeneration
from dashscope.api_entities.dashscope_response import Message

# Ini adalah URL dasar untuk wilayah Singapura; URL dasar bersifat spesifik wilayah.
dashscope.base_http_api_url = 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1'

# Jika variabel lingkungan tidak diatur, ganti baris berikut dengan Kunci API Model Studio Anda: api_key="sk-xxx"
# Kunci API bervariasi berdasarkan wilayah. Untuk mendapatkan Kunci API, kunjungi: https://www.alibabacloud.com/help/en/model-studio/get-api-key
api_key = os.getenv("DASHSCOPE_API_KEY")

def main():
    message = Message(
        role="user",
        content=[
            {"text": "A young woman in a natural, casual selfie style. An ultra-high-definition, realistic lifestyle photo. She is wearing a yellow floral long-sleeved top, and her long, slightly wavy hair falls naturally. The background is an outdoor natural scene with green plants nearby and water and mountains in the distance. Soft, natural sunlight falls on her face and body, creating natural light and shadow effects. The camera angle is a medium shot from a selfie perspective, as if held by her. She is standing naturally, projecting a relaxed and comfortable state. The angle is natural, in the style of a casual snapshot—an unguarded moment."}
        ]
    )

    # Kirim tugas asinkron.
    print("Mengirim tugas asinkron...")
    response = ImageGeneration.async_call(
        model="wan2.7-image-pro",
        api_key=api_key,
        messages=[message],
        enable_sequential=False,
        n=1,
        size="2K"
    )

    if response.status_code == 200:
        print(f"Tugas berhasil dikirim. ID Tugas: {response.output.task_id}")

        # Tunggu hingga tugas selesai.
        status = ImageGeneration.wait(task=response, api_key=api_key)

        if status.output.task_status == "SUCCEEDED":
            print("Tugas selesai!")
            print(f"Hasil:")
            print(status)
        else:
            print(f"Tugas gagal. Status: {status.output.task_status}")
    else:
        print(f"Pembuatan tugas gagal: {response.code} - {response.message}")

if __name__ == "__main__":
    try:
        main()
    except Exception as e:
        print(f"Error: {e}")

{
    "status_code": 200,
    "request_id": "4fb3050f-de57-4a24-84ff-e37ee5xxxxxx",
    "code": "",
    "message": "",
    "output": {
        "text": null,
        "finish_reason": null,
        "choices": null,
        "audio": null,
        "task_id": "77093787-a217-4c29-9cd4-ca7b5ac86xxx",
        "task_status": "PENDING"
    },
    "usage": {
        "input_tokens": 0,
        "output_tokens": 0,
        "characters": 0
    }
}

{
    "status_code": 200,
    "request_id": "56e318fd-ed60-99e8-8ca1-cdef25ca4xxx",
    "code": "",
    "message": "",
    "output": {
        "text": null,
        "finish_reason": null,
        "choices": [
            {
                "finish_reason": "stop",
                "message": {
                    "role": "assistant",
                    "content": [
                        {
                            "image": "https://dashscope-result-bj.oss-cn-beijing.aliyuncs.com/xxxxxx.png?Expires=xxxxxx",
                            "type": "image"
                        }
                    ]
                }
            }
        ],
        "audio": null,
        "task_id": "77093787-a217-4c29-9cd4-ca7b5ac86xxx",
        "task_status": "SUCCEEDED",
        "submit_time": "2026-03-31 23:04:46.166",
        "scheduled_time": "2026-03-31 23:04:46.208",
        "end_time": "2026-03-31 23:05:11.664",
        "finished": true
    },
    "usage": {
        "input_tokens": 720,
        "output_tokens": 11,
        "characters": 0,
        "size": "2048*2048",
        "total_tokens": 731,
        "image_count": 1
    }
}

import com.alibaba.dashscope.aigc.imagegeneration.*;
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.util.Collections;

public class Main {

    // Ini adalah URL dasar untuk wilayah Singapura; URL dasar bersifat spesifik wilayah.
    static String baseUrl = "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1";

    // Jika variabel lingkungan tidak diatur, ganti baris berikut dengan Kunci API Model Studio Anda: apiKey="sk-xxx"
    // Kunci API bervariasi berdasarkan wilayah. Untuk mendapatkan Kunci API, kunjungi: https://www.alibabacloud.com/help/en/model-studio/get-api-key
    static String apiKey = System.getenv("DASHSCOPE_API_KEY");

    public static ImageGenerationResult waitTask(String taskId)
            throws ApiException, NoApiKeyException {
        ImageGeneration imageGeneration = new ImageGeneration(apiKey, baseUrl);
        return imageGeneration.wait(taskId, apiKey);
    }

    public static void asyncCall() throws ApiException, NoApiKeyException, UploadFileException {
        ImageGenerationMessage message = ImageGenerationMessage.builder()
                .role("user")
                .content(Collections.singletonList(
                        Collections.singletonMap("text", "A young woman in a natural, casual selfie style. An ultra-high-definition, realistic lifestyle photo. She is wearing a yellow floral long-sleeved top, and her long, slightly wavy hair falls naturally. The background is an outdoor natural scene with green plants nearby and water and mountains in the distance. Soft, natural sunlight falls on her face and body, creating natural light and shadow effects. The camera angle is a medium shot from a selfie perspective, as if held by her. She is standing naturally, projecting a relaxed and comfortable state. The angle is natural, in the style of a casual snapshot—an unguarded moment.")
                )).build();

        ImageGenerationParam param = ImageGenerationParam.builder()
                .apiKey(apiKey)
                .model("wan2.7-image-pro")
                .messages(Collections.singletonList(message))
                .enableSequential(false)
                .n(1)
                .size("2K")
                .build();

        ImageGeneration imageGeneration = new ImageGeneration(apiKey, baseUrl);
        ImageGenerationResult taskResult = null;
        try {
            System.out.println("----async call, creating task----");
            taskResult = imageGeneration.asyncCall(param);
        } catch (ApiException | NoApiKeyException | UploadFileException e) {
            throw new RuntimeException(e.getMessage());
        }
        System.out.println("Task created: " + JsonUtils.toJson(taskResult));

        // Tunggu hingga tugas selesai.
        String taskId = taskResult.getOutput().getTaskId();
        ImageGenerationResult result = waitTask(taskId);
        System.out.println(JsonUtils.toJson(result));
    }

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

{
    "requestId": "7d026dc1-e8c9-9caa-84ac-e82e2da97xxx",
    "output": {
        "task_id": "2de18c56-c151-4b80-8105-1d164733exxx",
        "task_status": "PENDING"
    },
    "status_code": 200,
    "code": "",
    "message": ""
}

{
    "requestId": "daea7295-4ce0-928a-9a11-4d2bea058xxx",
    "usage": {
        "input_tokens": 720,
        "output_tokens": 11,
        "total_tokens": 731,
        "image_count": 1,
        "size": "2048*2048"
    },
    "output": {
        "choices": [
            {
                "finish_reason": "stop",
                "message": {
                    "role": "assistant",
                    "content": [
                        {
                            "image": "https://dashscope-result-bj.oss-cn-beijing.aliyuncs.com/xxxxxx.png?Expires=xxxxxx",
                            "type": "image"
                        }
                    ]
                }
            }
        ],
        "task_id": "2de18c56-c151-4b80-8105-1d164733exxx",
        "task_status": "SUCCEEDED",
        "finished": true,
        "submit_time": "2026-03-31 19:49:53.124",
        "scheduled_time": "2026-03-31 19:49:53.175",
        "end_time": "2026-03-31 19:50:53.160"
    },
    "status_code": 200,
    "code": "",
    "message": ""
}

curl --location 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/image-generation/generation' \
    --header 'Content-Type: application/json' \
    --header "Authorization: Bearer $DASHSCOPE_API_KEY" \
    --header "X-DashScope-Async: enable" \
    --data '{
        "model": "wan2.7-image-pro",
        "input": {
            "messages": [
                {
                    "role": "user",
                    "content": [
                        {"text": "A flower shop with exquisite windows, a beautiful wooden door, and flowers on display"}
                    ]
                }
            ]
        },
        "parameters": {
            "size": "2K",
            "n": 1,
            "watermark": false,
            "thinking_mode": true
        }
    }'

curl -X GET https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/tasks/{task_id} \
--header "Authorization: Bearer $DASHSCOPE_API_KEY"

​

Kemampuan utama

​

1. Mengikuti Arahan

• prompt: Menggambarkan konten yang diinginkan untuk gambar, termasuk subjek, adegan, gaya, pencahayaan, dan komposisi. Ini adalah parameter inti untuk mengontrol generasi teks-ke-gambar.
• negative prompt: Menggambarkan apa yang harus dikecualikan dari gambar, seperti "blurry" atau "extra fingers." Parameter ini membantu menyempurnakan kualitas output.

Parameter negative_prompt tidak didukung oleh wan2.7-image-pro dan wan2.7-image. Untuk mengecualikan elemen yang tidak diinginkan, gambarkan dalam prompt (misalnya, "do not include xxx").

​

2. Aktifkan penulisan ulang prompt

• Aktifkan fitur ini untuk prompt singkat atau umum guna meningkatkan kualitas gambar secara signifikan.
• Nonaktifkan fitur ini jika Anda memerlukan kontrol tepat atas detail gambar, telah memberikan prompt komprehensif, atau jika latensi respons menjadi perhatian. Untuk menonaktifkannya, atur parameter prompt_extend ke false.

Parameter prompt_extend tidak didukung oleh wan2.7-image-pro dan wan2.7-image. Untuk meningkatkan kualitas gambar pada model ini, aktifkan thinking_mode sebagai gantinya. Model qwen-image-3.0-pro dan qwen-image-3.0 mendukung parameter prompt_extend (diaktifkan secara default).

• direct: Direct Prompt Enhancement (DPE), cocok untuk sebagian besar skenario. Didukung untuk teks-ke-gambar (T2I) dan gambar-ke-gambar/pengeditan (I2I).
• agent: Agent Prompt Enhancement (APE), memberikan penulisan ulang lebih halus. Hanya didukung untuk teks-ke-gambar (T2I). Mengirimkan agent untuk gambar-ke-gambar/pengeditan (I2I) mengembalikan error 400.

​

3. Atur resolusi output gambar

Model wan2.7-image-pro mendukung resolusi 4K dan resolusi kustom hingga 40964096, tetapi hanya untuk tugas teks-ke-gambar (tanpa input gambar dan generasi set gambar dinonaktifkan). Semua skenario lain dibatasi hingga resolusi 2K (20482048).

• 1664*928 (default): 16:9
• 1472*1104: 4:3
• 1328*1328: 1:1
• 1104*1472: 3:4
• 928*1664: 9:16

​

4. Generasi set gambar

• Jumlah gambar: Dikontrol oleh parameter n. Saat mode ini diaktifkan, nilai ini dapat berkisar 1 hingga 12, dengan default 12. Model menentukan jumlah aktual gambar yang dihasilkan, yang tidak akan melebihi n.
• Catatan: Saat generasi set gambar diaktifkan, parameter thinking_mode dan color_palette tidak tersedia.

​

5. Mode berpikir

Hanya tersedia saat generasi set gambar dinonaktifkan (enable_sequential=false).

​

6. Palet warna kustom

Hanya tersedia saat generasi set gambar dinonaktifkan (enable_sequential=false).

"color_palette": [
    {
        "hex": "#C2D1E6",
        "ratio": "23.51%"
    },
    {
        "hex": "#CDD8E9",
        "ratio": "20.13%"
    },
    {
        "hex": "#B5C8DB",
        "ratio": "15.88%"
    },
    {
        "hex": "#C0B5B4",
        "ratio": "13.27%"
    },
    {
        "hex": "#DAE0EC",
        "ratio": "10.11%"
    },
    {
        "hex": "#636574",
        "ratio": "8.93%"
    },
    {
        "hex": "#CACAD2",
        "ratio": "5.55%"
    },
    {
        "hex": "#CBD4E4",
        "ratio": "2.62%"
    }
]

​

Penerapan produksi

• Toleransi kesalahan
  • Menangani pembatasan laju: Saat API mengembalikan kode kesalahan Throttling atau kode status HTTP 429, pembatasan laju telah dipicu. Untuk menangani pembatasan laju, lihat Pembatasan Laju.
  • Polling untuk tugas asinkron: Saat melakukan polling untuk hasil tugas asinkron, terapkan strategi polling yang masuk akal untuk menghindari pemicuan pembatasan laju. Misalnya, polling setiap 3 detik selama 30 detik pertama, lalu tingkatkan interval polling. Tetapkan timeout akhir untuk tugas (misalnya, 2 menit). Jika tugas timeout, tandai sebagai gagal.
• Pencegahan risiko
  • Persistensi hasil: URL gambar API berlaku selama 24 jam. Sistem produksi Anda harus segera mengunduh gambar setelah menerima URL dan memindahkannya ke layanan penyimpanan persisten Anda sendiri, seperti Alibaba Cloud Object Storage Service (OSS).
  • Moderasi konten: Semua input prompt dan negative_prompt dikenai moderasi konten. Jika input tidak sesuai, permintaan diblokir dan dikembalikan kesalahan DataInspectionFailed.
  • Risiko hak cipta dan kepatuhan konten yang dihasilkan: Pastikan prompt Anda mematuhi semua hukum dan peraturan yang berlaku. Menghasilkan konten yang mencakup merek dagang, kemiripan selebriti, atau kekayaan intelektual berhak cipta (IP) dapat menimbulkan risiko pelanggaran. Anda bertanggung jawab untuk mengevaluasi dan menanggung semua risiko terkait.

​

Referensi API

• Qwen - Generasi dan Pengeditan Gambar 3.0
• Qwen-Image
• Wan2.7 - generasi dan pengeditan gambar
• Wan2.6 - generasi dan pengeditan gambar
• Wan - teks-ke-gambar v2
• Z-Image - teks-ke-gambar

​

Penagihan dan pembatasan laju

• Untuk kuota gratis dan harga, lihat harga model.
• Untuk batas laju, lihat Generasi gambar.
• Anda hanya dikenai biaya untuk gambar yang berhasil dihasilkan. Permintaan gagal dan kesalahan pemrosesan tidak dikenai biaya atau mengurangi kuota gratis untuk pengguna baru.

​

Kode kesalahan

​

FAQ