FLUX.2 Pro 图像编辑

curl --request POST \
  --url https://api.vidgo.ai/api/generate/submit \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data @- <<EOF
{
  "model": "blackforestlabs/flux-2-pro/edit",
  "input": {
    "prompt": "Using image 1 (the grandmother) and image 2 (the boy) as identity references and image 3 as the location, create one warm documentary photograph of the grandmother teaching the boy to fold jiaozi dumplings at the flour-dusted wooden table in the kitchen from image 3. Keep both people exactly recognisable: the grandmother's pinned silver hair with black clip, smile lines, maroon knitted cardigan, white collar and jade earrings; the boy's bowl haircut, missing front tooth, mustard corduroy overalls and striped shirt. The grandmother stands beside and slightly behind the boy, guiding his small hands as he pinches a dumpling closed; a tray of neat finished dumplings and a few lopsided ones sits in front of him, with a rolling pin and a bowl of pork-and-chive filling nearby. Preserve the brick stove, iron wok, bamboo steamer, frosted window with red paper-cuts, and hanging garlic and chillies from image 3. Soft afternoon window light, a little flour in the air, natural skin texture, believable hands, 35mm lens. No text, no watermark.",
    "image_urls": [
      "https://cdn.vidgo.ai/apis/models/blackforestlabs/flux-2-pro/edit/v1/01/input-01.png",
      "https://cdn.vidgo.ai/apis/models/blackforestlabs/flux-2-pro/edit/v1/01/input-02.png",
      "https://cdn.vidgo.ai/apis/models/blackforestlabs/flux-2-pro/edit/v1/01/input-03.png"
    ],
    "size": "3:2",
    "resolution": "1K"
  }
}
EOF

{
  "code": 200,
  "data": {
    "task_id": "G4SI8DYZSIKS9UV5",
    "status": "running",
    "created_time": "2026-09-26T10:37:28"
  }
}

{
  "detail": "<string>"
}

{
  "detail": "<string>"
}

{
  "detail": "<string>"
}

{
  "detail": "<string>"
}

Request timeout

{
  "detail": "<string>"
}

{
  "detail": "<string>"
}

{
  "detail": "<string>"
}

{
  "detail": "<string>"
}

{
  "detail": "<string>"
}

POST

api

generate

submit

curl --request POST \
  --url https://api.vidgo.ai/api/generate/submit \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data @- <<EOF
{
  "model": "blackforestlabs/flux-2-pro/edit",
  "input": {
    "prompt": "Using image 1 (the grandmother) and image 2 (the boy) as identity references and image 3 as the location, create one warm documentary photograph of the grandmother teaching the boy to fold jiaozi dumplings at the flour-dusted wooden table in the kitchen from image 3. Keep both people exactly recognisable: the grandmother's pinned silver hair with black clip, smile lines, maroon knitted cardigan, white collar and jade earrings; the boy's bowl haircut, missing front tooth, mustard corduroy overalls and striped shirt. The grandmother stands beside and slightly behind the boy, guiding his small hands as he pinches a dumpling closed; a tray of neat finished dumplings and a few lopsided ones sits in front of him, with a rolling pin and a bowl of pork-and-chive filling nearby. Preserve the brick stove, iron wok, bamboo steamer, frosted window with red paper-cuts, and hanging garlic and chillies from image 3. Soft afternoon window light, a little flour in the air, natural skin texture, believable hands, 35mm lens. No text, no watermark.",
    "image_urls": [
      "https://cdn.vidgo.ai/apis/models/blackforestlabs/flux-2-pro/edit/v1/01/input-01.png",
      "https://cdn.vidgo.ai/apis/models/blackforestlabs/flux-2-pro/edit/v1/01/input-02.png",
      "https://cdn.vidgo.ai/apis/models/blackforestlabs/flux-2-pro/edit/v1/01/input-03.png"
    ],
    "size": "3:2",
    "resolution": "1K"
  }
}
EOF

{
  "code": 200,
  "data": {
    "task_id": "G4SI8DYZSIKS9UV5",
    "status": "running",
    "created_time": "2026-09-26T10:37:28"
  }
}

{
  "detail": "<string>"
}

{
  "detail": "<string>"
}

{
  "detail": "<string>"
}

{
  "detail": "<string>"
}

Request timeout

{
  "detail": "<string>"
}

{
  "detail": "<string>"
}

{
  "detail": "<string>"
}

{
  "detail": "<string>"
}

{
  "detail": "<string>"
}

提交后会返回 task_id。如果提供了 callback_url，当任务状态变为 finished 或 failed 时，系统会向 callback_url 发送 POST 请求。
无论是否提供 callback_url，都可以通过统一的查询任务状态接口获取结果。

在 FLUX.2 Pro 中将视觉参考与文字指令结合，编辑场景、迁移风格并保留可辨识的主体。

模型

blackforestlabs/flux-2-pro/edit - 使用提示词和参考图编辑图像。

功能

使用提示词和参考图编辑图像。
image_urls 接受 1-8 张图像。
可选 1K、2K 输出分辨率。

输出选项

图像尺寸

size：必填。可选值：1:1、4:3、3:4、16:9、9:16、3:2、2:3、auto。auto 使用 image_urls 中第一张图像的宽高比。

分辨率

resolution：必填。可选值：1K、2K。

高级参数

model 和可选的 callback_url 放在请求根级。所有工作流参数（包括输出选项）都放在 input 内。发送本页列出的 input 字段。每个输入 URL 都是公开的 HTTP(S) URL。

提示词

prompt：必填。描述要做的修改。长度：3-5,000 个字符。

图像 URL

image_urls：必填。提供公开可访问的图像 URL。1-8 项。每项都必须是 HTTP(S) URL。

已验证示例

此示例通过 Vidgo API 生成，也是 Playground 中的默认示例。源图和结果图托管在 Vidgo CDN 上。参考图 1

{
  "code": 200,
  "data": {
    "task_id": "G4SI8DYZSIKS9UV5",
    "status": "finished",
    "files": [
      {
        "file_type": "image",
        "file_url": "https://cdn.vidgo.ai/apis/models/blackforestlabs/flux-2-pro/edit/v1/01/output.jpg"
      }
    ],
    "created_time": "2026-09-26T10:37:28",
    "error_message": null,
    "progress": 100
  }
}

授权

Authorization

string

header

必填

使用 VIDGO_API_KEY。

请求体

application/json

model 和 callback_url 放在根级。工作流参数放在 input 内。

model

string

必填

示例:

"blackforestlabs/flux-2-pro/edit"

input

object

必填

Show child attributes

callback_url

string | null

可选的公开 HTTP(S) 接口，用于接收任务完成通知。建议使用 HTTPS。省略、设为 null 或空字符串即关闭回调。

响应

任务已提交

code

enum<integer>

必填

可用选项:

200

data

object

必填

Show child attributes

​模型

​功能

​输出选项

​图像尺寸

​分辨率

​高级参数

​提示词

​图像 URL

​已验证示例

授权

请求体

响应

模型

功能

输出选项

图像尺寸

分辨率

高级参数

提示词

图像 URL

已验证示例