Image Tools - Background Removal, Upscaling & Face Restoration

io.github.fasuizu-br由 GitHub 帳號 fasuizu-br 發布v1.1.0更新於 Oct 24, 2026

Background removal, 4x upscaling, and face restoration via GPU

已驗證Streamable HTTP可網頁執行媒體與設計

概覽

AI 產生的概覽

遠端 MCP 伺服器，提供 GPU 影像處理：去背、2x/4x 放大與人臉修復，輸入為 base64 圖片。

可以做什麼
  • 移除圖片背景，回傳透明 PNG 或白底 WebP
  • 以 Real-ESRGAN 將圖片放大 2 倍或 4 倍，輸出最大 8192x8192
  • 以 GFPGAN 偵測並修復人臉，可選擇同時強化背景
  • 查詢影像服務與已載入模型的健康狀態
適用情境
適合需要清理商品圖、為設計或網頁準備圖片，或在沒有本機 GPU 的情況下修復低品質人像的情境。
執行需求
需要遠端 streamable HTTP 端點，圖片以 base64 資料傳入。清單未宣告驗證、環境變數或標頭。README 稱其列出的閘道已停用，且目前 API 使用 Authorization Bearer 金鑰，使用前應先確認可用端點與金鑰需求。
安裝前請注意
圖片會上傳到第三方服務，避免傳送敏感或私人照片。README 將該閘道標為舊版且已停用，並明確表示不要使用這些 URL，所列端點可能無法運作。清單未宣告驗證，但 README 說明目前 API 需要 Bearer 金鑰；切勿提交真實金鑰。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Image Tools - Background Removal, Upscaling & Face Restoration，將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/io.github.fasuizu-br%2Fimage-tools/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "image-tools-background-removal-upscaling": {
      "type": "http",
      "url": "https://apim-ai-apis.azure-api.net/mcp/image/mcp"
    }
  }
}

README

Brainiall Speech AI examples — migration notice

[Current TTS health] [Current TTS repository]

This repository is legacy. The former apim-ai-apis.azure-api.net gateway and the old Speech AI MCP URLs documented in earlier revisions have been retired. Do not use those URLs. The other files in this repository are retained only as historical source and may no longer run.

Current supported surfaces

NeedCurrent surface
Text-to-speech MCP serverhttps://api.brainiall.com/mcp/tts/mcp
Text-to-speech REST endpointPOST https://api.brainiall.com/v1/tts/synthesize
TTS health checkhttps://api.brainiall.com/mcp/tts/health
TTS setup, OpenAPI and maintained examplesfasuizu-br/brainiall-tts-mcp
Brazilian Portuguese transcriptionTranscreve BR
Speech-to-text API overviewBrainiall Speech-to-Text
Account and API keyBrainiall app
Offline contract compatibility checkscompatibility-pack/

Authentication for the current API uses an Authorization: Bearer YOUR_BRAINIALL_API_KEY header. Never commit a real key.

For TTS examples for Claude, Cursor, VS Code, n8n, Postman and raw REST clients, use the maintained TTS repository linked above. It is the canonical source for current voices, prices and request schemas.

The small compatibility pack is different from the historical examples. It is an offline-only contract test for buffered TTS, generic diarized-STT review artifacts, a synthetic diarization canary and local-by-default usage planning. It performs no API call during tests, contains no key, copies no third-party source, and does not claim streaming, cancellation, OpenAI drop-in compatibility, completed third-party integration or billing. Read its kill gates before reusing it.

Why this notice exists

External directories and search engines may still link to this repository. This notice prevents an old listing from sending developers to endpoints that no longer work and points them to the maintained production surfaces.

License

MIT — Brainiall

C112 — hosted STT contract fixture

The Whisper-WebUI OpenAI-compatible fixture is a provider-neutral, synthetic request/response example for maintainers evaluating an external speech-to-text path. It does not claim that Whisper-WebUI has adopted the contract, and it never includes a key or private audio.

來源：README.md，提交 eab44aa

工具

4

remove_background

Remove Background

Remove the background from an image. Uses BiRefNet segmentation to precisely separate foreground from background. Returns a base64-encoded image with transparent background (PNG) or white background (WebP). Sub-500ms latency on GPU. Args: image_base64: Base64-encoded image data (PNG, JPEG, or WebP). output_format: Output format -- 'png' (with transparency) or 'webp'. Returns: dict with keys: - image_base64 (str): Base64-encoded result image - format (str): Output image format - original_size (dict): Original width and height - processing_ms (int): Processing time in milliseconds

輸入參數image_base64必填output_format

upscale_image

Upscale Image

Upscale image resolution using Real-ESRGAN. Enhances image resolution by 2x or 4x using GPU-accelerated Real-ESRGAN super-resolution. Processes in tiles (256x256) to manage VRAM. Maximum output dimension: 8192x8192. Args: image_base64: Base64-encoded image data (PNG, JPEG, or WebP). scale: Upscale factor -- 2 or 4 (default: 4). Returns: dict with keys: - image (str): Base64-encoded upscaled image - format (str): Output image format - width (int): Output width - height (int): Output height - scale (int): Scale factor applied - processing_time_ms (float): Processing time in milliseconds

輸入參數scaleimage_base64必填

restore_face

Restore Face

Restore and enhance faces in an image using GFPGAN. Detects all faces via RetinaFace, restores quality (fixes blur, noise, compression artifacts), and pastes them back. Optionally enhances the background using Real-ESRGAN. GPU-accelerated, sub-3s latency. Args: image_base64: Base64-encoded image data containing faces (PNG, JPEG, WebP). upscale: Output upscale factor -- 1 to 4 (default: 2). enhance_background: Whether to enhance background with Real-ESRGAN (default: true). Returns: dict with keys: - image (str): Base64-encoded restored image - format (str): Output image format - width (int): Output width - height (int): Output height - upscale (int): Scale factor applied - processing_time_ms (float): Processing time in milliseconds

輸入參數upscaleimage_base64必填enhance_background

check_image_service

Check Image Service

Check health status of Image API services and loaded models. Returns: dict with keys: - status (str): 'healthy' or error state - models (dict): Loaded model status per capability - version (str): API version

無需輸入參數。

版本歷史

1
  1. v1.1.0最新Sep 16, 2026

評分

已滿足適用檢查項的 100%

該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分