蒙版 gpt-image-1.5

POST /v1/images/edits

MethodPOST
Path/v1/images/edits
Typehttp
Status1
Module2102810
Folder55735707

说明

给定一个提示，该模型将返回一个或多个预测的完成，并且还可以返回每个位置的替代标记的概率。

为提供的提示和参数创建完成

官方文档：https://platform.openai.com/docs/api-reference/images/createEdit

概览

MethodPOST
Path/v1/images/edits
Typehttp
Status1
Module2102810
Folder55735707

参数

{
  "query": [],
  "path": [],
  "cookie": [],
  "header": [
    {
      "id": "qb8tEQbCty",
      "name": "Accept",
      "required": true,
      "description": "",
      "type": "string",
      "enable": true,
      "sampleValue": "application/json"
    },
    {
      "required": false,
      "description": "",
      "type": "string",
      "id": "gBxcCbXhsa",
      "enable": true,
      "name": "Authorization",
      "sampleValue": "Bearer {{YOUR_API_KEY}}"
    }
  ]
}

请求体

{
  "type": "multipart/form-data",
  "parameters": [
    {
      "required": true,
      "description": "要编辑的图片。必须是受支持的图片文件或图片数组。对于 gpt-image-1，每张图片应为小于 25MB 的 png、webp 或 jpg 文件。对于 dall-e-2，您只能提供一张图片，并且该图片应为小于 4MB 的方形 png 文件。\n",
      "type": "file",
      "id": "b3jXL90sE5",
      "enable": true,
      "name": "image",
      "schema": {
        "format": "binary",
        "type": "string"
      },
      "sampleValue": "file://C:\\Users\\Administrator\\Desktop\\sunlit_lounge.png"
    },
    {
      "required": true,
      "description": "所需图像的文本描述。dall-e-2 的最大长度为 1000 个字符，gpt-image-1 的最大长度为 32000 个字符。\n",
      "type": "string",
      "id": "TeGM3GrLP9",
      "enable": true,
      "name": "prompt",
      "sampleValue": "A sunlit indoor lounge area with a pool containing a flamingo"
    },
    {
      "required": false,
      "description": "一张附加图片，其完全透明区域（例如，alpha 值为零）指示应编辑 image 位置。如果提供了多张图片，则遮罩将应用于第一张图片。必须是有效的 PNG 文件，小于 4MB，且尺寸与 image 相同。\n",
      "type": "file",
      "id": "i7NJKm41S6",
      "enable": true,
      "name": "mask",
      "schema": {
        "format": "binary",
        "type": "string"
      },
      "sampleValue": "file://C:\\Users\\Administrator\\Desktop\\mask.png"
    },
    {
      "required": false,
      "description": "用于生成图像的模型。仅 gpt-image-1, gpt-image-1-all  , flux-kontext-pro  , flux-kontext-max。\n",
      "type": "string",
      "id": "9puBSlhkv8",
      "enable": true,
      "name": "model",
      "sampleValue": "gpt-image-1.5"
    },
    {
      "required": false,
      "description": "要生成的图像数量。必须介于 1 到 10 之间。\n",
      "type": "string",
      "id": "UwcVbSRbom",
      "enable": true,
      "name": "n",
      "sampleValue": "1"
    },
    {
      "required": false,
      "description": "生成图像的质量。只有 gpt-image-1 支持 high、medium 和 low 质量。dall-e-2 仅支持 standard 质量。默认为 auto。\n",
      "type": "string",
      "id": "NnJEH3V1Lk",
      "enable": false,
      "name": "quality",
      "sampleValue": ""
    },
    {
      "required": false,
      "description": "返回生成图像的格式。必须是 url 或 b64_json 之一。URL 在图像生成后 60 分钟内有效。此参数仅适用于 dall-e-2，因为 gpt-image-1 始终返回 base64 编码的图像，请不要使用这个参数。\n",
      "type": "string",
      "id": "zSKhx4jKxt",
      "enable": false,
      "name": "response_format",
      "sampleValue": "b64_json"
    },
    {
      "required": false,
      "description": "生成图像的尺寸。对于 GPT 图像模型，必须是 1024x1024 、 1536x1024 （横版）、 1024x1536 （竖版）或 auto （默认值）之一，对于 dall-e-2 必须是 256x256 、 512x512 或 1024x1024 之一，对于 dall-e-3 必须是 1024x1024 、 1792x1024 或 1024x1792 之一。\n\n",
      "type": "string",
      "id": "cBVZfsBqpM",
      "enable": true,
      "name": "size",
      "sampleValue": "1024x1024"
    },
    {
      "required": false,
      "description": "允许为生成的图像的背景设置透明度。此参数仅在 gpt-image-1 中受支持。其值必须为 “透明（transparent）”、“不透明（opaque）” 或 “自动（auto）”（默认值）之一。当使用 “自动（auto）” 时，模型将自动为图像确定最佳背景。\n",
      "type": "string",
      "id": "eWjSCaxckX",
      "enable": false,
      "name": "background",
      "sampleValue": "transparent"
    },
    {
      "required": false,
      "description": "控制由 gpt-image-1 生成的图像的内容审核级别。可以设置为 “low” 以进行限制较少的过滤，也可以设置为 “auto”（默认值）。\n",
      "type": "string",
      "id": "R3LlLzVkmp",
      "enable": false,
      "name": "moderation",
      "sampleValue": "low"
    }
  ],
  "jsonSchema": {
    "type": "object",
    "properties": {
      "image": {
        "description": "要编辑的图片。必须是受支持的图片文件或图片数组。对于 gpt-image-1，每张图片应为小于 25MB 的 png、webp 或 jpg 文件。对于 dall-e-2，您只能提供一张图片，并且该图片应为小于 4MB 的方形 png 文件。",
        "type": "string"
      },
      "prompt": {
        "description": "所需图像的文本描述。dall-e-2 的最大长度为 1000 个字符，gpt-image-1 的最大长度为 32000 个字符。",
        "type": "string"
      },
      "mask": {
        "description": "一张附加图片，其完全透明区域（例如，alpha 值为零）指示应编辑 image 位置。如果提供了多张图片，则遮罩将应用于第一张图片。必须是有效的 PNG 文件，小于 4MB，且尺寸与 image 相同。",
        "type": "string"
      },
      "model": {
        "description": "用于生成图像的模型。仅支持 dall-e-2 和 gpt-image-1。除非使用特定于 gpt-image-1 参数，否则默认为 dall-e-2。",
        "type": "string"
      },
      "n": {
        "description": "要生成的图像数量。必须介于 1 到 10 之间。",
        "type": "integer"
      },
      "quality": {
        "description": "生成图像的质量。只有 gpt-image-1 支持 high、medium 和 low 质量。dall-e-2 仅支持 standard 质量。默认为 auto。",
        "type": "string"
      },
      "response_format": {
        "description": "返回生成图像的格式。必须是 url 或 b64_json 之一。URL 在图像生成后 60 分钟内有效。此参数仅适用于 dall-e-2，因为 gpt-image-1 始终返回 base64 编码的图像。",
        "type": "string"
      },
      "size": {
        "description": "生成图像的尺寸。对于 gpt-image-1，必须为 1024x1024、1536x1024（横向）、1024x1536（纵向）或 auto（默认值）之一；对于 dall-e-2，必须为 256x256、512x512 或 1024x1024 之一。",
        "type": "string"
      }
    },
    "required": [
      "image",
      "prompt",
      "mask",
      "model",
      "n",
      "quality",
      "response_format",
      "size"
    ],
    "x-apifox-orders": [
      "image",
      "prompt",
      "mask",
      "model",
      "n",
      "quality",
      "response_format",
      "size"
    ]
  },
  "required": false,
  "mediaType": "",
  "examples": [
    {
      "value": "{\n    \"size\": \"1024x1024\",\n    \"prompt\": \"一直可爱的小猪\",\n    \"model\": \"gpt-image-1\",\n    \"n\": 1\n}",
      "mediaType": "application/json"
    },
    {
      "value": "{\n    \"size\": \"1024x1024\",\n    \"prompt\": \"一直可爱的小猪\",\n    \"model\": \"gpt-image-1\",\n    \"n\": 1\n}",
      "mediaType": "multipart/form-data",
      "description": ""
    }
  ],
  "oasExtensions": ""
}

响应

[
  {
    "id": 706724265,
    "name": "OK",
    "code": 200,
    "contentType": "json",
    "jsonSchema": {
      "type": "object",
      "properties": {
        "id": {
          "type": "string"
        },
        "object": {
          "type": "string"
        },
        "created": {
          "type": "integer"
        },
        "choices": {
          "type": "array",
          "items": {
            "type": "object",
            "properties": {
              "index": {
                "type": "integer"
              },
              "message": {
                "type": "object",
                "properties": {
                  "role": {
                    "type": "string"
                  },
                  "content": {
                    "type": "string"
                  }
                },
                "required": [
                  "role",
                  "content"
                ],
                "x-apifox-orders": [
                  "role",
                  "content"
                ]
              },
              "finish_reason": {
                "type": "string"
              }
            },
            "x-apifox-orders": [
              "index",
              "message",
              "finish_reason"
            ]
          }
        },
        "usage": {
          "type": "object",
          "properties": {
            "prompt_tokens": {
              "type": "integer"
            },
            "completion_tokens": {
              "type": "integer"
            },
            "total_tokens": {
              "type": "integer"
            }
          },
          "required": [
            "prompt_tokens",
            "completion_tokens",
            "total_tokens"
          ],
          "x-apifox-orders": [
            "prompt_tokens",
            "completion_tokens",
            "total_tokens"
          ]
        }
      },
      "required": [
        "id",
        "object",
        "created",
        "choices",
        "usage"
      ],
      "x-apifox-orders": [
        "id",
        "object",
        "created",
        "choices",
        "usage"
      ]
    },
    "itemSchema": {},
    "description": "",
    "mediaType": "",
    "headers": [],
    "oasExtensions": ""
  }
]

响应示例

[
  {
    "name": "OK",
    "responseId": 706724265,
    "data": "{\n    \"id\": \"chatcmpl-123\",\n    \"object\": \"chat.completion\",\n    \"created\": 1677652288,\n    \"choices\": [\n        {\n            \"index\": 0,\n            \"message\": {\n                \"role\": \"assistant\",\n                \"content\": \"\\n\\nHello there, how may I assist you today?\"\n            },\n            \"finish_reason\": \"stop\"\n        }\n    ],\n    \"usage\": {\n        \"prompt_tokens\": 9,\n        \"completion_tokens\": 12,\n        \"total_tokens\": 21\n    }\n}",
    "description": "",
    "oasKey": "",
    "oasExtensions": "",
    "id": 612471432
  }
]