全部產品
Search

搜尋本產品

    Vector Retrieval Service for Milvus：圖片編輯

    文件中心

    Vector Retrieval Service for Milvus：圖片編輯

    更新時間：Aug 04, 2026

    AI_IMAGE_EDIT 函數可根據一張或多張輸入圖片及提示詞產生編輯後的圖片 URL，可用於商品白底圖、背景替換、風格遷移和參考圖融合。

    命令格式

    REST 介面

    {
  "model_name": "wan2.7-image-pro",
  "texts": ["<image_url>"],
  "params": {"prompt": "<edit_instruction>", "n": 1}
}

    多圖輸入使用 image_inputs，每個內部數組代表一條編輯任務：

    {
  "model_name": "wan2.7-image-pro",
  "image_inputs": [["<base_image_url>", "<reference_image_url>"]],
  "params": {"prompt": "<edit_instruction>", "n": 2}
}

    Python

    schema = MilvusClient.create_schema(auto_id=True, enable_dynamic_field=False)
schema.add_field("id", DataType.INT64, is_primary=True)
schema.add_field("image_url", DataType.VARCHAR, max_length=4096)
schema.add_field("instruction", DataType.VARCHAR, max_length=512)
schema.add_field("edited_image", DataType.VARCHAR, max_length=8192)
schema.add_field("dummy_vector", DataType.FLOAT_VECTOR, dim=2)
schema.add_function(
    Function(
        name="edit_image",
        function_type=texttransform_function_type(),
        input_field_names=["image_url", "instruction"],
        output_field_names=["edited_image"],
        params={
            "provider": "aliyun_milvus",
            "model_name": "wan2.7-image-pro",
            "task": "ai_image_edit",
            "image_fields": "image_url",
            "prompt": "${instruction}",
            "n": "1",
            "size": "1024*1024",
            "watermark": "false",
            "timeout_sec": "180",
        },
    )
)

    參數說明

    參數

    說明

    model_name

    必填。使用 wan2.7-image-pro（推薦）或 wan2.7-image 等可同步返回圖片 URL 的模型。

    prompt

    必填。編輯目標描述；Schema 中可使用 ${field_name} 引用其他輸入欄位。

    texts

    單圖輸入的圖片數組，每個元素是一條任務；不能與 image_inputs 同時傳入。

    image_inputs

    多圖輸入的二維數組，內部數組是一條任務的圖片列表；同一請求中各任務的圖片數量必須一致。

    image_fields

    僅 Schema 可選。指定圖片欄位，預設第一個輸入欄位；可寫為 base_image,reference_image 或 JSON 字串數組。

    n

    可選，預設 1，範圍 1–6。n=1 返回一張圖片 URL，n>1 返回圖片 URL 列表。

    size / negative_prompt / seed / bbox_list / watermark

    可選，按模型能力透傳。

    timeout_sec / max_concurrency

    可選，分別控制單次逾時和批量並發數。

    provider / task

    僅 Collection Function 必填，固定為 aliyun_milvus 與 ai_image_edit。

    傳回值說明

    n=1 時，data.output.outputs 的元素為圖片 URL；n>1 時，每個元素為包含 images 數組的 JSON 字串。data.usage 可能包含 image_tokens 和 total_tokens。

    樣本一：單圖背景替換（單圖 texts，n=1）

    將一張人物與寵物合影的背景替換為乾淨白底，保留主體。預設素材是一張人物與狗的合影； Curl 樣本需要 jq。

    REST 介面

    #!/usr/bin/env bash
set -euo pipefail

MILVUS_REST_BASE_URL="http://c-xxxx.milvus.aliyuncs.com:19530"
MILVUS_AUTH_TOKEN="<yourUsername>:<yourPassword>"

post_json() {
  local path="$1"
  local body="$2"
  curl -X POST \
    "$MILVUS_REST_BASE_URL$path" \
    -H "Authorization: Bearer $MILVUS_AUTH_TOKEN" \
    -H "Content-Type: application/json" \
    -d "$body"
}

BODY=$(cat <<JSON
{
  "model_name": "wan2.7-image-pro",
  "texts": ["https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"],
  "params": {
    "prompt": "Keep the main subject and replace the background with a clean white background.",
    "n": 1,
    "size": "1024*1024",
    "watermark": false,
    "timeout_sec": 180
  }
}
JSON
)
RESPONSE_BODY="$(post_json "/v2/vectordb/ai/image_edit" "$BODY")"
if command -v jq >/dev/null 2>&1; then
  echo "$RESPONSE_BODY" | jq .
  [ "$(echo "$RESPONSE_BODY" | jq -r '.code // -1')" = "0" ] || exit 1
else
  echo "$RESPONSE_BODY"
fi

    Python

    from __future__ import annotations

from typing import Any

from pymilvus import DataType, Function, FunctionType, MilvusClient

MILVUS_URI = "http://c-xxxx.milvus.aliyuncs.com:19530"
MILVUS_TOKEN = "<yourUsername>:<yourPassword>"

DUMMY_VECTOR_DIM = 2
TEXTTRANSFORM_FUNCTION_TYPE = 9

def texttransform_function_type() -> Any:
    for type_name in ("TEXTTRANSFORM", "TEXT_TRANSFORM", "TextTransform"):
        function_type = getattr(FunctionType, type_name, None)
        if function_type is not None:
            return function_type
    # 阿里雲 Milvus 將 TEXTTRANSFORM 作為託管擴充(函數類型值 9)提供;
    # 部分 pymilvus 版本尚未內建該枚舉成員,而 Function(...) 通過 FunctionType(...) 校正。
    existing = getattr(FunctionType, "_value2member_map_", {}).get(TEXTTRANSFORM_FUNCTION_TYPE)
    if existing is not None:
        return existing
    extension = int.__new__(FunctionType, TEXTTRANSFORM_FUNCTION_TYPE)
    extension._name_ = "TEXTTRANSFORM"
    extension._value_ = TEXTTRANSFORM_FUNCTION_TYPE
    FunctionType._value2member_map_[TEXTTRANSFORM_FUNCTION_TYPE] = extension
    FunctionType._member_map_["TEXTTRANSFORM"] = extension
    return extension

def add_id(schema: Any) -> None:
    schema.add_field("id", DataType.INT64, is_primary=True)

def add_dummy_vector(schema: Any) -> None:
    schema.add_field("dummy_vector", DataType.FLOAT_VECTOR, dim=DUMMY_VECTOR_DIM)

def run_texttransform_example(*, client, collection_name, input_fields, output_field, function_name, function_params, rows) -> None:
    if client.has_collection(collection_name):
        client.drop_collection(collection_name)
    schema = MilvusClient.create_schema(auto_id=True, enable_dynamic_field=False)
    add_id(schema)
    for name, data_type, max_length in input_fields:
        field_params = {"max_length": max_length} if max_length is not None else {}
        schema.add_field(name, data_type, **field_params)
    output_name, output_data_type, output_max_length = output_field
    output_params = {"max_length": output_max_length} if output_max_length is not None else {}
    schema.add_field(output_name, output_data_type, **output_params)
    add_dummy_vector(schema)
    schema.add_function(
        Function(
            name=function_name,
            function_type=texttransform_function_type(),
            input_field_names=[name for name, _, _ in input_fields],
            output_field_names=[output_name],
            params=function_params,
        )
    )
    index_params = client.prepare_index_params()
    index_params.add_index(field_name="dummy_vector", index_type="AUTOINDEX", metric_type="COSINE")
    client.create_collection(collection_name=collection_name, schema=schema, index_params=index_params)
    client.insert(collection_name, rows)
    client.flush(collection_name)
    fields = [name for name, _, _ in input_fields] + [output_name]
    for row in client.query(collection_name, filter="", output_fields=fields, limit=len(rows)):
        print(row)

MODEL_NAME = "wan2.7-image-pro"
client = MilvusClient(uri=MILVUS_URI, token=MILVUS_TOKEN)

run_texttransform_example(
    client=client,
    collection_name="simple_ai_image_edit_schema",
    input_fields=[("image_url", DataType.VARCHAR, 4096), ("instruction", DataType.VARCHAR, 512)],
    output_field=("edited_image", DataType.VARCHAR, 8192),
    function_name="edit_image",
    function_params={"provider": "aliyun_milvus", "model_name": MODEL_NAME, "task": "ai_image_edit", "image_fields": "image_url", "prompt": "${instruction}", "n": "1", "size": "1024*1024", "watermark": "false", "timeout_sec": "180"},
    rows=[{"image_url": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg", "instruction": "Keep the main subject and replace the background with a clean white background.", "dummy_vector": [0.1, 0.2]}],
)

    預期結果：data.output.outputs[0] 是非空的編輯後圖片 URL，可寫入會員紀念素材的 edited_image 欄位（VARCHAR）。產生圖的具體布景具有非確定性，不應按某一固定畫面斷言成功。

    樣本二：人寵合影與服裝參考圖產生品牌概念圖

    以人物與寵物合影作為主體參考，以服裝素材作為色彩和質感參考，一次產生兩張社交媒體概念圖供人工選片。

    REST 介面

    #!/usr/bin/env bash
set -euo pipefail

MILVUS_REST_BASE_URL="http://c-xxxx.milvus.aliyuncs.com:19530"
MILVUS_AUTH_TOKEN="<yourUsername>:<yourPassword>"

post_json() {
  local path="$1"
  local body="$2"
  curl -X POST \
    "$MILVUS_REST_BASE_URL$path" \
    -H "Authorization: Bearer $MILVUS_AUTH_TOKEN" \
    -H "Content-Type: application/json" \
    -d "$body"
}

BODY=$(cat <<JSON
{
  "model_name": "wan2.7-image-pro",
  "image_inputs": [["https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg", "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260415/hynnff/wan-video-edit-clothes.webp"]],
  "params": {
    "prompt": "Keep the person, dog, and seaside composition from the first image. Use the second image only as clothing color and texture reference. Generate brand-safe social media concept images.",
    "n": 2,
    "size": "1024*1024",
    "watermark": false,
    "timeout_sec": 180
  }
}
JSON
)
RESPONSE_BODY="$(post_json "/v2/vectordb/ai/image_edit" "$BODY")"
if command -v jq >/dev/null 2>&1; then
  echo "$RESPONSE_BODY" | jq .
  [ "$(echo "$RESPONSE_BODY" | jq -r '.code // -1')" = "0" ] || exit 1
else
  echo "$RESPONSE_BODY"
fi

    Python

    from __future__ import annotations

from typing import Any

from pymilvus import DataType, Function, FunctionType, MilvusClient

MILVUS_URI = "http://c-xxxx.milvus.aliyuncs.com:19530"
MILVUS_TOKEN = "<yourUsername>:<yourPassword>"

DUMMY_VECTOR_DIM = 2
TEXTTRANSFORM_FUNCTION_TYPE = 9

def texttransform_function_type() -> Any:
    for type_name in ("TEXTTRANSFORM", "TEXT_TRANSFORM", "TextTransform"):
        function_type = getattr(FunctionType, type_name, None)
        if function_type is not None:
            return function_type
    # 阿里雲 Milvus 將 TEXTTRANSFORM 作為託管擴充(函數類型值 9)提供;
    # 部分 pymilvus 版本尚未內建該枚舉成員,而 Function(...) 通過 FunctionType(...) 校正。
    existing = getattr(FunctionType, "_value2member_map_", {}).get(TEXTTRANSFORM_FUNCTION_TYPE)
    if existing is not None:
        return existing
    extension = int.__new__(FunctionType, TEXTTRANSFORM_FUNCTION_TYPE)
    extension._name_ = "TEXTTRANSFORM"
    extension._value_ = TEXTTRANSFORM_FUNCTION_TYPE
    FunctionType._value2member_map_[TEXTTRANSFORM_FUNCTION_TYPE] = extension
    FunctionType._member_map_["TEXTTRANSFORM"] = extension
    return extension

def add_id(schema: Any) -> None:
    schema.add_field("id", DataType.INT64, is_primary=True)

def add_dummy_vector(schema: Any) -> None:
    schema.add_field("dummy_vector", DataType.FLOAT_VECTOR, dim=DUMMY_VECTOR_DIM)

def run_texttransform_example(*, client, collection_name, input_fields, output_field, function_name, function_params, rows) -> None:
    if client.has_collection(collection_name):
        client.drop_collection(collection_name)
    schema = MilvusClient.create_schema(auto_id=True, enable_dynamic_field=False)
    add_id(schema)
    for name, data_type, max_length in input_fields:
        field_params = {"max_length": max_length} if max_length is not None else {}
        schema.add_field(name, data_type, **field_params)
    output_name, output_data_type, output_max_length = output_field
    output_params = {"max_length": output_max_length} if output_max_length is not None else {}
    schema.add_field(output_name, output_data_type, **output_params)
    add_dummy_vector(schema)
    schema.add_function(
        Function(
            name=function_name,
            function_type=texttransform_function_type(),
            input_field_names=[name for name, _, _ in input_fields],
            output_field_names=[output_name],
            params=function_params,
        )
    )
    index_params = client.prepare_index_params()
    index_params.add_index(field_name="dummy_vector", index_type="AUTOINDEX", metric_type="COSINE")
    client.create_collection(collection_name=collection_name, schema=schema, index_params=index_params)
    client.insert(collection_name, rows)
    client.flush(collection_name)
    fields = [name for name, _, _ in input_fields] + [output_name]
    for row in client.query(collection_name, filter="", output_fields=fields, limit=len(rows)):
        print(row)

MODEL_NAME = "wan2.7-image-pro"
client = MilvusClient(uri=MILVUS_URI, token=MILVUS_TOKEN)

# 每項 image_inputs 包含基礎圖和參考圖;n=2 返回兩個候選結果。
# 注意:ai_image_edit 在 n > 1 時,輸出欄位必須為 DataType.JSON(不能用 VARCHAR)。
run_texttransform_example(
    client=client,
    collection_name="simple_ai_image_edit_multi_schema",
    input_fields=[
        ("base_image_url", DataType.VARCHAR, 4096),
        ("reference_image_url", DataType.VARCHAR, 4096),
        ("instruction", DataType.VARCHAR, 1024),
    ],
    output_field=("edited_images", DataType.JSON, None),
    function_name="edit_images_with_reference",
    function_params={
        "provider": "aliyun_milvus",
        "model_name": MODEL_NAME,
        "task": "ai_image_edit",
        "image_fields": '["base_image_url","reference_image_url"]',
        "prompt": "${instruction}",
        "n": "2",
        "size": "1024*1024",
        "watermark": "false",
        "timeout_sec": "180",
    },
    rows=[
        {
            "base_image_url": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg",
            "reference_image_url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260415/hynnff/wan-video-edit-clothes.webp",
            "instruction": "Keep the person, dog, and seaside composition from the base image. Use the reference image only as clothing color and texture guidance. Generate brand-safe social media concept images.",
            "dummy_vector": [0.1, 0.2],
        }
    ],
)

    預期結果：因為 n=2，data.output.outputs[0] 是含 images 數組（2 個非空圖片 URL）的 JSON 字串。

    注意：ai_image_edit 在 n>1 時，Collection 的輸出欄位必須為 JSON（不能用 VARCHAR），否則建立集合會報 output field must be a JSON field for task [ai_image_edit] when n > 1。