Skill Detail

Stable Diffusion ControlNet Compositor

Orchestrates Stable Diffusion XL with ControlNet preprocessors (Canny, Depth, OpenPose) for guided image generation. Manages ComfyUI workflow JSON exports and A1111 API batch processing.

Image & Creative AutomationGemini
Image & Creative Automation Gemini Security Reviewed
Tool match: stable.diffusion โญ 33.9k GitHub stars
INSTALL WITH ANY AGENT
npx skills add agentskillexchange/skills --skill stable-diffusion-controlnet-compositor Copy
Works best when you want a reusable capability, not another fragile one-off prompt.
At a glance
Last updated
Mar 24, 2026
Quick brief

The Stable Diffusion ControlNet Compositor automates guided image generation using SDXL and ControlNet adapters through both the Automatic1111 REST API and ComfyUI workflow engine. It manages multi-ControlNet conditioning by stacking Canny edge detection, MiDaS depth estimation, and OpenPose skeleton extraction for precise compositional control.

How it works

What this skill actually does

The skill handles prompt engineering with emphasis weighting syntax, CLIP skip configuration, and negative prompt templates optimized for photorealistic and artistic styles. It supports LoRA model loading with adjustable weights, textual inversion embeddings, and IP-Adapter for image-prompted generation.

Batch processing capabilities include grid generation for prompt comparison, upscaling pipelines via ESRGAN and SwinIR, and face restoration with CodeFormer. ComfyUI workflows are exported as portable JSON for reproducibility, and the skill manages VRAM optimization through model offloading, attention slicing, and tiled VAE decoding for high-resolution outputs on consumer GPUs. Seed management ensures reproducible results across generation sessions.