ControlNet API Overview

Generate images guided by edge maps, depth maps, poses, and other control signals using ControlNet via the Stable Diffusion API.

What is ControlNet?

ControlNet is a neural network architecture that adds spatial conditioning to Stable Diffusion. Instead of generating from prompt alone, ControlNet uses an additional image (edge map, depth, pose, scribble) to guide composition.

Supported control types

Canny — edge detection
Depth — depth-aware composition
Pose — human pose preservation
Scribble — sketch-to-image
Segmentation — semantic guidance
Lineart — anime lineart
MLSD — straight-line detection (architecture)
Normal — surface normals

Endpoints

ControlNet Main — primary generation endpoint
ControlNet Inpaint — guided inpainting

Quickstart

curl -X POST 'https://stablediffusionapi.com/api/v5/controlnet' \
  -H 'Content-Type: application/json' \
  -d '{
    "key": "YOUR_API_KEY",
    "controlnet_model": "canny",
    "init_image": "https://example.com/edge.png",
    "prompt": "a futuristic city, neon lights"
  }'