Image Tools - Background Removal, Upscaling & Face Restoration

Official4 tools

by fasuizu-br · Python

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

Remove backgrounds, upscale images 4x, and restore faces with GPU acceleration.

Topics

ai-agentsapi-exampleslanguage-learningmcppronunciationspeech-aispeech-to-texttext-to-speech

Captured live from the server via tools/list.

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

Parameters (2)

image_base64stringrequired
Base64-encoded image data. Supports PNG, JPEG, and WebP formats.
output_formatstring
Output image format: 'png' (default, with transparency) or 'webp'

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

Parameters (2)

image_base64stringrequired
Base64-encoded image data. Supports PNG, JPEG, and WebP formats.
scaleinteger
Upscale factor: 2 or 4 (default: 4)

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

Parameters (3)

image_base64stringrequired
Base64-encoded image data containing one or more faces.
upscaleinteger
Output upscale factor: 1-4 (default: 2)
enhance_backgroundboolean
Enhance background with Real-ESRGAN (default: true)

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

No parameters.

README.md7 KBView on GitHub

Brainiall AI APIs

Production AI APIs for speech, text, image, and LLM inference. Available as REST endpoints and MCP servers for AI agents.

Base URL: https://apim-ai-apis.azure-api.net Full API reference for LLMs: llms-full.txt | llms.txt

Products

Product	Endpoints	Latency	Notes
Pronunciation Assessment	`/v1/pronunciation/assess/base64`	<500ms	17MB ONNX, per-phoneme scoring (39 ARPAbet)
Text-to-Speech	`/v1/tts/synthesize`	<1s	12 voices (American + British), 24kHz WAV
Speech-to-Text	`/v1/stt/transcribe/base64`	<500ms	Compact 17MB model, English, word timestamps
Whisper Pro	`/v1/whisper/transcribe/base64`	<3s	99 languages, speaker diarization
NLP Suite	`/v1/nlp/{toxicity,sentiment,entities,pii,language}`	<50ms	CPU-only, ONNX, 5 endpoints
Image Processing	`/v1/image/{remove-background,upscale,restore-face}/base64`	<3s	GPU (A10), BiRefNet + ESRGAN + GFPGAN
LLM Gateway	`/v1/chat/completions`	varies	113+ models, OpenAI-compatible, streaming

Authentication

Include ONE of these headers in every request:

code

Ocp-Apim-Subscription-Key: YOUR_KEY
Authorization: Bearer YOUR_KEY
api-key: YOUR_KEY

Get API keys at the portal (GitHub sign-in, purchase credits, create key).

Quick Start

Python — LLM Gateway (OpenAI SDK)

python

from openai import OpenAI

client = OpenAI(
    base_url="https://apim-ai-apis.azure-api.net/v1",
    api_key="YOUR_KEY"
)

response = client.chat.completions.create(
    model="claude-sonnet",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

Python — Pronunciation Assessment

python

import requests, base64

audio_b64 = base64.b64encode(open("audio.wav", "rb").read()).decode()
r = requests.post(
    "https://apim-ai-apis.azure-api.net/v1/pronunciation/assess/base64",
    headers={"Ocp-Apim-Subscription-Key": "YOUR_KEY"},
    json={"audio": audio_b64, "text": "Hello world", "format": "wav"}
)
print(r.json()["overallScore"])  # 0-100

Python — NLP Pipeline

python

import requests

headers = {"Ocp-Apim-Subscription-Key": "YOUR_KEY"}
base = "https://apim-ai-apis.azure-api.net/v1/nlp"

# Sentiment
r = requests.post(f"{base}/sentiment", headers=headers, json={"text": "I love this!"})
print(r.json())  # {"label": "positive", "score": 0.9987}

# PII detection with redaction
r = requests.post(f"{base}/pii", headers=headers, json={"text": "Email john@acme.com", "redact": True})
print(r.json()["redacted_text"])  # "Email [EMAIL]"

Node.js — LLM Gateway

javascript

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://apim-ai-apis.azure-api.net/v1",
  apiKey: "YOUR_KEY"
});

const res = await client.chat.completions.create({
  model: "claude-sonnet",
  messages: [{ role: "user", content: "Hello!" }]
});
console.log(res.choices[0].message.content);

curl — Image Background Removal

bash

curl -X POST https://apim-ai-apis.azure-api.net/v1/image/remove-background/base64 \
  -H "Ocp-Apim-Subscription-Key: YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d "{\"image\": \"$(base64 -i photo.jpg)\"}"

LLM Gateway — Popular Models

Model	Alias	Price ($/MTok in/out)
Claude Opus 4.6	`claude-opus`	$5 / $25
Claude Sonnet 4.6	`claude-sonnet`	$3 / $15
Claude Haiku 4.5	`claude-haiku`	$1 / $5
DeepSeek R1	`deepseek-r1`	$1.35 / $5.40
DeepSeek V3	`deepseek-v3`	$0.27 / $1.10
Llama 3.3 70B	`llama-3.3-70b`	$0.72 / $0.72
Amazon Nova Pro	`nova-pro`	$0.80 / $3.20
Amazon Nova Micro	`nova-micro`	$0.035 / $0.14
Mistral Large 3	`mistral-large-3`	$2 / $6
Qwen3 32B	`qwen3-32b`	$0.35 / $0.35

Full list: GET /v1/models (113+ models from 17 providers).

Supports: streaming SSE, tool calling, structured output (json_object/json_schema), extended thinking.

Works with: OpenAI SDK, LiteLLM, LangChain, Cline, Cursor, Aider, Continue, SillyTavern, Open WebUI.

MCP Servers (for AI Agents)

3 MCP servers with 20 tools total. Streamable HTTP transport.

Server	URL	Tools
Speech AI	`https://apim-ai-apis.azure-api.net/mcp/pronunciation/mcp`	10 tools + 8 resources + 3 prompts
NLP Tools	`https://apim-ai-apis.azure-api.net/mcp/nlp/mcp`	6 tools + 3 resources + 3 prompts
Image Tools	`https://apim-ai-apis.azure-api.net/mcp/image/mcp`	4 tools + 3 resources + 2 prompts

MCP Configuration (Claude Desktop / Cursor / Cline)

json

{
  "mcpServers": {
    "brainiall-speech": {
      "url": "https://apim-ai-apis.azure-api.net/mcp/pronunciation/mcp",
      "headers": { "Ocp-Apim-Subscription-Key": "YOUR_KEY" }
    },
    "brainiall-nlp": {
      "url": "https://apim-ai-apis.azure-api.net/mcp/nlp/mcp",
      "headers": { "Ocp-Apim-Subscription-Key": "YOUR_KEY" }
    },
    "brainiall-image": {
      "url": "https://apim-ai-apis.azure-api.net/mcp/image/mcp",
      "headers": { "Ocp-Apim-Subscription-Key": "YOUR_KEY" }
    }
  }
}

Also available on: Smithery (score 95/100) | MCPize | Apify ($0.02/call) | MCP Registry

Examples

File	Description
`python/basic_usage.py`	Speech APIs — assess, transcribe, synthesize
`python/pronunciation_tutor.py`	Interactive pronunciation tutor
`javascript/basic_usage.js`	Node.js examples for speech APIs
`curl/examples.sh`	curl commands for every endpoint
`mcp/claude-desktop-config.json`	MCP config for Claude Desktop
`mcp/cursor-config.json`	MCP config for Cursor IDE
`llms-full.txt`	Complete API reference for LLM consumption

Pricing

Product	Price	Unit
Pronunciation	$0.02	per call
TTS	$0.01-0.03	per 1K chars
STT (compact)	$0.01	per request
Whisper Pro	$0.02	per minute
NLP (any)	$0.001-0.002	per call
Image (any)	$0.003-0.005	per image
LLM Gateway	competitive pricing	per MTok

Credit packages: $5, $10, $25, $50, $100. Portal | Azure Marketplace (search "Brainiall").

License

MIT — Brainiall

Install

Tools (4)

remove_backgroundupscale_imagerestore_facecheck_image_service

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://apim-ai-apis.azure-api.net/mcp/image/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "image-tools": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://apim-ai-apis.azure-api.net/mcp/image/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.