openai/gpt-image-2.5-flare/edit

圖生圖

GPT Image 2.5 Flare Edit API by OpenAI

openai/gpt-image-2.5-flare/edit

Edit

GPT Image 2.5 Flare Edit applies natural-language instructions to up to 16 reference images, with an optional mask, arbitrary resolutions up to 3840x2160, five quality tiers including xhigh and max, and transparent-background output. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

GPT Image 2.5 Flare Edit 由 OpenAI 開發。Atlas Cloud（由 Atlas Cloud AI LLC 營運）僅提供接取服務，並不擁有該模型。所有商標均歸其各自所有者所有。

輸入

提示詞 *

圖片 *(0/16)

可拖曳檔案至此，或點擊上傳

MAX:16

Mask

品質

尺寸

1:1

長寬比已鎖定：修改一邊時另一邊會等比縮放。點擊鎖頭圖示可自由編輯。

Background

輸出格式

數量

輸出

閒置

生成的圖片將在這裡顯示

設定參數後點擊執行開始生成

每次執行將花費 ≈$0.005。$10 可執行約 2000 次。此模型按 token 計費：輸入文字、參考圖以及生成的圖片都按 token 計量。上方金額是依目前參數的預估值——尺寸越大、品質等級越高、參考圖越多，消耗的 token 越多，實際扣費也越高。

你可以繼續：

圖生影片圖生圖

參數

程式碼範例
import requests
import time

# Step 1: Start image generation
generate_url = "https://api.atlascloud.ai/api/v1/model/generateImage"
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer $ATLASCLOUD_API_KEY"
}
data = {
    "model": "openai/gpt-image-2.5-flare/edit",  # Required. Model name. options: openai/gpt-image-2.5-flare/edit
    "images": [
        "https://example.com/image1.jpg"
    ],  # Required. Up to 16 source images to edit
    "prompt": "Replace the background with a sunlit meadow, keep the subject unchanged.",  # Required. Text description of the desired image
    "quality": "medium",  # Rendering quality tier. options: auto | low | medium | high | xhigh | max
    "size": "1024x1024",  # optional string or auto or 1024x1024 or 1536x1024 or 5 moreThe size ofthe generated images
    "background": "auto",  # Background of the generated image. options: auto | opaque | transparent
    "output_format": "png",  # Output image format. options: png | jpeg | webp
    "moderation": "auto",  # Content-moderation strictness. options: auto | low
    "mask": "example_value",  # Optional mask marking the region to edit
    "n": 1,  # Number of images to generate, 1 to 10. (min: 1, max: 10)
}

generate_response = requests.post(generate_url, headers=headers, json=data)
generate_result = generate_response.json()
prediction_id = generate_result["data"]["id"]

# Step 2: Poll for result
poll_url = f"https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}"

def check_status():
    while True:
        response = requests.get(poll_url, headers={"Authorization": "Bearer $ATLASCLOUD_API_KEY"})
        result = response.json()

        if result["data"]["status"] == "completed":
            print("Generated image:", result["data"]["outputs"][0])
            return result["data"]["outputs"][0]
        elif result["data"]["status"] == "failed":
            raise Exception(result["data"]["error"] or "Generation failed")
        else:
            # Still processing, wait 2 seconds
            time.sleep(2)

image_url = check_status()

安裝

安裝所需的相依套件。

pip install requests

驗證

所有 API 請求都需要透過 API Key 進行認證。您可以在 Atlas Cloud 控制台取得 API Key。

export ATLASCLOUD_API_KEY="your-api-key-here"

HTTP 標頭

import os

API_KEY = os.environ.get("ATLASCLOUD_API_KEY")
headers = {
    "Content-Type": "application/json",
    "Authorization": f"Bearer {API_KEY}"
}

保護好您的 API Key

切勿在客戶端程式碼或公開儲存庫中暴露您的 API Key。請使用環境變數或後端代理。

提交請求

import requests

url = "https://api.atlascloud.ai/api/v1/model/generateImage"
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer $ATLASCLOUD_API_KEY"
}
data = {
    "model": "your-model",
    "prompt": "A beautiful landscape"
}

response = requests.post(url, headers=headers, json=data)
print(response.json())

提交請求

提交一個非同步生成請求。API 會傳回一個 prediction ID，您可以用它來檢查狀態與取得結果。

POST/api/v1/model/generateImage

請求主體

import requests

url = "https://api.atlascloud.ai/api/v1/model/generateImage"
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer $ATLASCLOUD_API_KEY"
}

data = {
    "model": "openai/gpt-image-2.5-flare/edit",
    "prompt": "A beautiful landscape with mountains and lake"
}

response = requests.post(url, headers=headers, json=data)
result = response.json()

print(f"Prediction ID: {result['data']['id']}")
print(f"Status: {result['data']['status']}")

回應

{
  "code": 200,
  "data": {
    "id": "pred_abc123",
    "status": "processing",
    "model": "model-name",
    "created_at": "2025-01-01T00:00:00Z"
  }
}

檢查狀態

輪詢 prediction 端點以檢查請求的當前狀態。

GET/api/v1/model/prediction/{prediction_id}

輪詢範例

import requests
import time

prediction_id = "pred_abc123"
url = f"https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}"
headers = { "Authorization": "Bearer $ATLASCLOUD_API_KEY" }

while True:
    response = requests.get(url, headers=headers)
    result = response.json()
    status = result["data"]["status"]
    print(f"Status: {status}")

    if status in ["completed", "succeeded"]:
        output_url = result["data"]["outputs"][0]
        print(f"Output URL: {output_url}")
        break
    elif status == "failed":
        print(f"Error: {result['data'].get('error', 'Unknown')}")
        break

    time.sleep(3)

狀態值

processing請求仍在處理中。

completed生成完成，輸出可用。

succeeded生成成功，輸出可用。

failed生成失敗，請檢查 error 欄位。

完成回應

{
  "data": {
    "id": "pred_abc123",
    "status": "completed",
    "outputs": [
      "https://storage.atlascloud.ai/outputs/result.png"
    ],
    "metrics": {
      "predict_time": 8.3
    },
    "created_at": "2025-01-01T00:00:00Z",
    "completed_at": "2025-01-01T00:00:10Z"
  }
}

上傳檔案

將檔案上傳到 Atlas Cloud 儲存空間，取得可在 API 請求中使用的 URL。使用 multipart/form-data 上傳。

POST/api/v1/model/uploadMedia

上傳範例

import requests

url = "https://api.atlascloud.ai/api/v1/model/uploadMedia"
headers = { "Authorization": "Bearer $ATLASCLOUD_API_KEY" }

with open("image.png", "rb") as f:
    files = {"file": ("image.png", f, "image/png")}
    response = requests.post(url, headers=headers, files=files)

result = response.json()
download_url = result["data"]["download_url"]
print(f"File URL: {download_url}")

回應

{
  "data": {
    "download_url": "https://storage.atlascloud.ai/uploads/abc123/image.png",
    "file_name": "image.png",
    "content_type": "image/png",
    "size": 1024000
  }
}

Input Schema

以下參數在請求主體中被接受。

總計: 10必填: 3選填: 7

modelstringrequired

Model name.

Default: "openai/gpt-image-2.5-flare/edit"

openai/gpt-image-2.5-flare/edit

imagesarray[string]required

Up to 16 source images to edit. Each entry is a URL, Base64 data, or an asset reference (asset://<ASSET_ID>).

Min items: 1Max items: 16

promptstringrequired

Text description of the desired image. Up to 32000 characters.

Default: "Replace the background with a sunlit meadow, keep the subject unchanged."

qualitystring

Rendering quality tier. gpt-image-2.5 adds xhigh and max on top of low/medium/high. Higher tiers cost more per image.

Default: "medium"

autolowmediumhighxhighmax

sizestring

optional string or auto or 1024x1024 or 1536x1024 or 5 moreThe size ofthe generated images.For gpt-image-2.5 is supported as WIDTHxHEIGHT strings,for example 1536x864 . Width and height mustboth be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1.Resolutions above2560x1440 are experimental, and the maximum supported resolution is 3840x2160 .The requesteosize must also satisfy the model's current pixel and edge limits.The standard sizes 1024x1024.1536x1024 ,and 1024x1536 are supported by the GPT image models; auto is supported for modelsthat allow automatic sizing.For dall-e-2,use oneof 256x256,512x512,or 1024x1024.Fordall-e-3,use oneof 1024x1024,1792x1024,or 1024x1792.

Default: "1024x1024"

auto1024x768768x10241024x15361536x10242048x20482048x11521152x20482560x10881088x25602880x21602160x28803840x21602160x3840

backgroundstring

Background of the generated image. When using transparent, set the output format to png or webp.

Default: "auto"

autoopaquetransparent

output_formatstring

Output image format.

Default: "png"

pngjpegwebp

moderationstring

Content-moderation strictness. low applies less restrictive filtering.

Default: "auto"

autolow

maskstring

Optional mask marking the region to edit. A URL, Base64 data, or an asset reference (asset://<ASSET_ID>). Transparent pixels mark the area the model should replace; it must match the first source image's dimensions.

ninteger

Number of images to generate, 1 to 10. Each image is billed separately.

Default: 1Min: 1Max: 10

範例請求主體

{
  "model": "openai/gpt-image-2.5-flare/edit",
  "images": [
    "https://example.com/file.jpg"
  ],
  "prompt": "Replace the background with a sunlit meadow, keep the subject unchanged.",
  "quality": "medium",
  "size": "1024x1024",
  "background": "auto",
  "output_format": "png",
  "moderation": "auto",
  "n": 1
}

Output Schema

API 傳回包含生成輸出 URL 的 prediction 回應。

idstring

Unique identifier for the prediction.

modelstring

Model ID used for the prediction.

statusstring

Status of the task: created, processing, completed, or failed.

outputsarray

Array of URLs to the generated images. Empty when status is not completed.

created_atstring

ISO timestamp of when the request was created.

範例回應

{
  "id": "pred_abc123",
  "status": "completed",
  "model": "model-name",
  "outputs": [
    "https://storage.atlascloud.ai/outputs/result.png"
  ],
  "metrics": {
    "predict_time": 8.3
  },
  "created_at": "2025-01-01T00:00:00Z",
  "completed_at": "2025-01-01T00:00:10Z"
}

Atlas Cloud Skills

Atlas Cloud Skills 將 400+ AI 模型直接整合到您的 AI 程式碼助手中。一條命令安裝，即可用自然語言生成圖片、影片，以及與 LLM 對話。

支援的客戶端

Claude Code

OpenAI Codex

Gemini CLI

Cursor

Windsurf

VS Code

Trae

GitHub Copilot

Cline

Roo Code

Amp

Goose

Replit

40+ 支援的客戶端

安裝

npx skills add AtlasCloudAI/atlas-cloud-skills

設定 API Key

從 Atlas Cloud 控制台取得 API Key，並將其設定為環境變數。

export ATLASCLOUD_API_KEY="your-api-key-here"

功能

安裝完成後，您可以在 AI 助手中使用自然語言存取所有 Atlas Cloud 模型。

圖片生成使用 Nano Banana 2、Z-Image 等模型生成圖片。

影片創作使用 Kling、Vidu、Veo 等從文字或圖片創建影片。

LLM 對話與 Qwen、DeepSeek 及其他大型語言模型對話。

媒體上傳上傳本機檔案用於圖片編輯和圖生影片工作流程。

MCP Server

Atlas Cloud MCP Server 透過 Model Context Protocol 將您的 IDE 與 400+ AI 模型連接。支援任何相容 MCP 的客戶端。

支援的客戶端

Cursor

VS Code

Windsurf

Claude Code

OpenAI Codex

Gemini CLI

Cline

Roo Code

100+ 支援的客戶端

安裝

npx -y atlascloud-mcp

設定

將以下設定新增到您的 IDE 的 MCP 設定檔中。

{
  "mcpServers": {
    "atlascloud": {
      "command": "npx",
      "args": [
        "-y",
        "atlascloud-mcp"
      ],
      "env": {
        "ATLASCLOUD_API_KEY": "your-api-key-here"
      }
    }
  }
}

可用工具

atlas_generate_image根據文字提示生成圖片。

atlas_generate_video從文字或圖片創建影片。

atlas_chat與大型語言模型對話。

atlas_list_models瀏覽 400+ 可用 AI 模型。

atlas_quick_generate一步式內容創建，自動選擇最佳模型。

atlas_upload_media上傳本機檔案用於 API 工作流程。

了解更多

github.com/AtlasCloudAI/mcp-server

API Schema

{
  "info": {
    "title": "AtlasCloud API",
    "version": "1.0.0",
    "description": "GPT Image 2.5 Flare image editing (OpenAI Images API)."
  },
  "openapi": "3.0.0",
  "servers": [
    {
      "url": "https://api.atlascloud.ai"
    }
  ],
  "paths": {
    "/api/v1/model/generateImage": {
      "post": {
        "requestBody": {
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/Input"
              }
            }
          },
          "required": true
        },
        "responses": {
          "200": {
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/PredictionResponse"
                }
              }
            },
            "description": "The request status."
          }
        }
      },
      "x-api-name": "model_run"
    },
    "/api/v1/model/prediction/{request_id}": {
      "get": {
        "parameters": [
          {
            "in": "path",
            "name": "request_id",
            "required": true,
            "schema": {
              "description": "Request ID",
              "type": "string"
            }
          }
        ],
        "responses": {
          "200": {
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/PredictionResponse"
                }
              }
            },
            "description": "Result of the request."
          }
        }
      },
      "x-api-name": "model_result"
    }
  },
  "components": {
    "schemas": {
      "Input": {
        "type": "object",
        "required": [
          "model",
          "prompt",
          "images"
        ],
        "properties": {
          "model": {
            "type": "string",
            "description": "Model name.",
            "default": "openai/gpt-image-2.5-flare/edit",
            "enum": [
              "openai/gpt-image-2.5-flare/edit"
            ]
          },
          "images": {
            "type": "array",
            "minItems": 1,
            "maxItems": 16,
            "items": {
              "type": "string"
            },
            "description": "Up to 16 source images to edit. Each entry is a URL, Base64 data, or an asset reference (asset://<ASSET_ID>)."
          },
          "prompt": {
            "type": "string",
            "maxLength": 32000,
            "default": "Replace the background with a sunlit meadow, keep the subject unchanged.",
            "description": "Text description of the desired image. Up to 32000 characters."
          },
          "quality": {
            "type": "string",
            "default": "medium",
            "enum": [
              "auto",
              "low",
              "medium",
              "high",
              "xhigh",
              "max"
            ],
            "description": "Rendering quality tier. gpt-image-2.5 adds xhigh and max on top of low/medium/high. Higher tiers cost more per image.",
            "x-ui-component": "select"
          },
          "size": {
            "default": "1024x1024",
            "description": "optional string or auto or 1024x1024 or 1536x1024 or 5 moreThe size ofthe generated images.For gpt-image-2.5 is supported as WIDTHxHEIGHT strings,for example 1536x864 . Width and height mustboth be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1.Resolutions above2560x1440 are experimental, and the maximum supported resolution is 3840x2160 .The requesteosize must also satisfy the model's current pixel and edge limits.The standard sizes 1024x1024.1536x1024 ,and 1024x1536 are supported by the GPT image models; auto is supported for modelsthat allow automatic sizing.For dall-e-2,use oneof 256x256,512x512,or 1024x1024.Fordall-e-3,use oneof 1024x1024,1792x1024,or 1024x1792.",
            "enum": [
              "auto",
              "1024x768",
              "768x1024",
              "1024x1536",
              "1536x1024",
              "2048x2048",
              "2048x1152",
              "1152x2048",
              "2560x1088",
              "1088x2560",
              "2880x2160",
              "2160x2880",
              "3840x2160",
              "2160x3840"
            ],
            "type": "string"
          },
          "background": {
            "type": "string",
            "default": "auto",
            "enum": [
              "auto",
              "opaque",
              "transparent"
            ],
            "description": "Background of the generated image. When using transparent, set the output format to png or webp.",
            "x-ui-component": "select"
          },
          "output_format": {
            "type": "string",
            "default": "png",
            "enum": [
              "png",
              "jpeg",
              "webp"
            ],
            "description": "Output image format.",
            "x-ui-component": "select"
          },
          "moderation": {
            "type": "string",
            "default": "auto",
            "enum": [
              "auto",
              "low"
            ],
            "description": "Content-moderation strictness. low applies less restrictive filtering.",
            "x-ui-component": "select"
          },
          "mask": {
            "type": "string",
            "description": "Optional mask marking the region to edit. A URL, Base64 data, or an asset reference (asset://<ASSET_ID>). Transparent pixels mark the area the model should replace; it must match the first source image's dimensions."
          },
          "n": {
            "type": "integer",
            "minimum": 1,
            "maximum": 10,
            "default": 1,
            "description": "Number of images to generate, 1 to 10. Each image is billed separately."
          }
        },
        "x-order-properties": [
          "model",
          "images",
          "mask",
          "prompt",
          "quality",
          "size",
          "background",
          "output_format",
          "n"
        ],
        "allOf": [
          {
            "if": {
              "properties": {
                "background": {
                  "const": "transparent"
                }
              },
              "required": [
                "background"
              ]
            },
            "then": {
              "properties": {
                "output_format": {
                  "enum": [
                    "png",
                    "webp"
                  ]
                }
              }
            }
          }
        ]
      },
      "PredictionResponse": {
        "type": "object",
        "properties": {
          "id": {
            "type": "string",
            "description": "Unique identifier for the prediction."
          },
          "urls": {
            "type": "object",
            "description": "Object containing related API endpoints."
          },
          "model": {
            "type": "string",
            "description": "Model ID used for the prediction."
          },
          "status": {
            "type": "string",
            "description": "Status of the task: created, processing, completed, or failed."
          },
          "outputs": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "description": "Array of URLs to the generated images. Empty when status is not completed."
          },
          "created_at": {
            "type": "string",
            "format": "date-time",
            "description": "ISO timestamp of when the request was created."
          }
        }
      }
    }
  }
}

LLM 友善的提示詞範本

# openai/gpt-image-2.5-flare/edit

> GPT Image 2.5 Flare Edit applies natural-language instructions to up to 16 reference images, with an optional mask, arbitrary resolutions up to 3840x2160, five quality tiers including xhigh and max, and transparent-background output. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.


## Overview

- **Submit endpoint (POST)**: `https://api.atlascloud.ai/api/v1/model/generateImage` — start an async generation; returns a `prediction_id`
- **Poll endpoint (GET)**: `https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}` — poll this until the prediction finishes
- **Model ID**: `openai/gpt-image-2.5-flare/edit`


## API Information

This model can be used via our HTTP API or more conveniently via our client libraries.
See the input and output schema below, as well as the usage examples.


### Input Schema

The API accepts the following input parameters:

- **`model`** (`string`, _required_):
  Model name.
  - Default: `"openai/gpt-image-2.5-flare/edit"`
  - Options: "openai/gpt-image-2.5-flare/edit"

- **`images`** (`array[string]`, _required_):
  Up to 16 source images to edit. Each entry is a URL, Base64 data, or an asset reference (asset://<ASSET_ID>).
  - Min items: 1
  - Max items: 16

- **`mask`** (`string`, _optional_):
  Optional mask marking the region to edit. A URL, Base64 data, or an asset reference (asset://<ASSET_ID>). Transparent pixels mark the area the model should replace; it must match the first source image's dimensions.

- **`prompt`** (`string`, _required_):
  Text description of the desired image. Up to 32000 characters.
  - Default: `"Replace the background with a sunlit meadow, keep the subject unchanged."`

- **`quality`** (`string`, _optional_):
  Rendering quality tier. gpt-image-2.5 adds xhigh and max on top of low/medium/high. Higher tiers cost more per image.
  - Default: `"medium"`
  - Options: "auto", "low", "medium", "high", "xhigh", "max"

- **`size`** (`string`, _optional_):
  optional string or auto or 1024x1024 or 1536x1024 or 5 moreThe size ofthe generated images.For gpt-image-2.5 is supported as WIDTHxHEIGHT strings,for example 1536x864 . Width and height mustboth be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1.Resolutions above2560x1440 are experimental, and the maximum supported resolution is 3840x2160 .The requesteosize must also satisfy the model's current pixel and edge limits.The standard sizes 1024x1024.1536x1024 ,and 1024x1536 are supported by the GPT image models; auto is supported for modelsthat allow automatic sizing.For dall-e-2,use oneof 256x256,512x512,or 1024x1024.Fordall-e-3,use oneof 1024x1024,1792x1024,or 1024x1792.
  - Default: `"1024x1024"`
  - Options: "auto", "1024x768", "768x1024", "1024x1536", "1536x1024", "2048x2048", "2048x1152", "1152x2048", "2560x1088", "1088x2560", "2880x2160", "2160x2880", "3840x2160", "2160x3840"

- **`background`** (`string`, _optional_):
  Background of the generated image. When using transparent, set the output format to png or webp.
  - Default: `"auto"`
  - Options: "auto", "opaque", "transparent"

- **`output_format`** (`string`, _optional_):
  Output image format.
  - Default: `"png"`
  - Options: "png", "jpeg", "webp"

- **`n`** (`integer`, _optional_):
  Number of images to generate, 1 to 10. Each image is billed separately.
  - Default: `1`
  - Min: 1
  - Max: 10



**Required Parameters Example**:

```json
{
  "model": "openai/gpt-image-2.5-flare/edit",
  "prompt": "Replace the background with a sunlit meadow, keep the subject unchanged.",
  "images": [
    ""
  ]
}
```


**Full Example**:

```json
{
  "model": "openai/gpt-image-2.5-flare/edit",
  "images": [
    ""
  ],
  "mask": "",
  "prompt": "Replace the background with a sunlit meadow, keep the subject unchanged.",
  "quality": "medium",
  "size": "1024x1024",
  "background": "auto",
  "output_format": "png",
  "n": 1
}
```


### Output Schema

The API returns the following output format:


- **`id`** (`string`, _optional_):
  Unique identifier for the prediction.

- **`urls`** (`object`, _optional_):
  Object containing related API endpoints.

- **`model`** (`string`, _optional_):
  Model ID used for the prediction.

- **`status`** (`string`, _optional_):
  Status of the task: created, processing, completed, or failed.

- **`outputs`** (`array[string]`, _optional_):
  Array of URLs to the generated images. Empty when status is not completed.

- **`created_at`** (`string`, _optional_):
  ISO timestamp of when the request was created.



**Example Response**:

```json
{
  "id": "",
  "urls": {},
  "model": "",
  "status": "",
  "outputs": [
    ""
  ],
  "created_at": ""
}
```


## Usage Examples

### cURL

```bash
# Step 1: Start generation (async)
curl -X POST "https://api.atlascloud.ai/api/v1/model/generateImage" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "openai/gpt-image-2.5-flare/edit",
  "images": [
    ""
  ],
  "mask": "",
  "prompt": "Replace the background with a sunlit meadow, keep the subject unchanged.",
  "quality": "medium",
  "size": "1024x1024",
  "background": "auto",
  "output_format": "png",
  "n": 1
}'

# Response will contain: {"code": 200, "data": {"id": "prediction_id", "status": "processing"}}

# Step 2: Poll for result (replace {prediction_id} with the id returned above)
curl -X GET "https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY"

# Keep polling until status is "completed", "succeeded" or "failed"
# When completed, outputs will contain the generated content URL(s)
```

## Additional Resources

### Documentation

- [Model Playground](https://www.atlascloud.ai/models/openai/gpt-image-2.5-flare/edit)

Two friends taking a casual selfie together at home, standing close with their arms naturally wrapped around each other, genuine smiles and relaxed expressions, spontaneous candid moment, warm and intimate friendship atmosphere. Shot with a vintage CCD digital camera, nostalgic early-2000s aesthetic, subtle flash, slightly overexposed highlights, soft skin tones, natural indoor lighting, authentic digital noise, subtle chromatic aberration, low-resolution CCD texture, slightly imperfect focus, realistic skin details, cozy home interior, everyday lifestyle photography, unposed composition, snapshot photography, cinematic color grading, nostalgic and youthful mood, highly natural and photorealistic. A spontaneous CCD snapshot of two close friends taking a selfie together at home, arms around each other's shoulders, faces naturally close to the camera, genuine laughter and imperfect smiles, slightly awkward framing as if captured spontaneously by a friend. Direct on-camera flash, harsh but nostalgic highlights, soft shadows, slight motion blur, subtle lens distortion, visible CCD noise, muted colors, low dynamic range, slight overexposure, imperfect white balance, authentic early-2000s compact digital camera look, cozy lived-in home background, intimate friendship, raw and unpolished, realistic everyday photography.

載入中...