controlnet-aux
Auxillary models for controlnet
Decision gist · record as of 2026-08-14
Yes, if you are building ControlNet-based image generation pipelines or need a convenient way to extract structural annotations from images. The package has low install friction, permissive licensing, and no known vulnerabilities. Caveat: maintenance is aging (no release in 463 days), so verify that model checkpoints and detector implementations match your use case before production deployment.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires torch and torchvision; model checkpoints are downloaded from Hugging Face Hub on first use (requires internet access and disk space).
- Low install friction with a pure Python wheel.
- Maintenance status is aging—last commit was 2025-05-08 with no release in 463 days—but the package remains in Production/Stable status with archived=false.
License · maintenance · safety
Apache (permissive) — Licensed under Apache (permissive), so you can use it freely in commercial and private projects without copyleft obligations.
last release 2025-05-08 (463 days) · last repo commit 2025-05-08 · 497 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 292,957 downloads/mo, #7,959 on PyPI
Alternatives
Verify before relying
pip install controlnet-aux
from controlnet_aux.processor import Processor
processor = Processor('openpose')
processed = processor(img, to_pil=True)- Whether model checkpoints are cached locally or re-downloaded on each instantiation
- Memory footprint and GPU VRAM requirements for concurrent detector instances
- Performance characteristics (inference speed) for each detector type
What it is and what it does
controlnet-aux wraps a collection of computer vision annotation models from lllyasviel's ControlNet repository and connects them to the Hugging Face Hub for model checkpoint hosting. It provides detector classes for edge detection, pose estimation, depth mapping, segmentation, and other tasks, each loadable via a unified Processor interface or individually. Models are downloaded on first use from the Hub and can be instantiated with optional device specification.
The package depends on torch, torchvision, scipy, numpy, opencv-python-headless, scikit-image, Pillow, einops, timm, filelock, and importlib_metadata. It is designed for image-to-image generation pipelines where you need to extract structural information from input images to guide model conditioning. Each detector accepts images and returns processed outputs.
Use it for
- Extract pose skeletons from photos to guide pose-conditioned image generation
- Detect edges in images for edge-guided image synthesis or artistic processing
- Generate depth maps from single images for 3D-aware image editing
- Segment objects in images for object-aware inpainting or layout-guided generation
- Preprocess images for ControlNet-based diffusion models requiring structural annotations
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you are building ControlNet-based image generation pipelines or need a convenient way to extract structural annotations from images.
The package has low install friction, permissive licensing, and no known vulnerabilities. Caveat: maintenance is aging (no release in 463 days), so verify that model checkpoints and detector implementations match your use case before production deployment.
Install
controlnet-aux on PyPI
Before you install
Low install friction with a pure Python wheel. Maintenance status is aging—last commit was 2025-05-08 with no release in 463 days—but the package remains in Production/Stable status with archived=false.
Requires torch and torchvision; model checkpoints are downloaded from Hugging Face Hub on first use (requires internet access and disk space).
License in practice
Licensed under Apache (permissive), so you can use it freely in commercial and private projects without copyleft obligations.
Quickstart
pip install controlnet-aux
from controlnet_aux.processor import Processor
processor = Processor('openpose')
processed = processor(img, to_pil=True)Verify before relying
- Whether model checkpoints are cached locally or re-downloaded on each instantiation
- Memory footprint and GPU VRAM requirements for concurrent detector instances
- Performance characteristics (inference speed) for each detector type
Package facts
| License | Apache permissive |
| Python support | Supports the current Python release >=3.7.0 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 12 packagestorchimportlib_metadatahuggingface_hubscipyopencv-python-headlessfilelocknumpyPilloweinopstorchvisiontimmscikit-image |
| Maintenance | Aging 463 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 292,957 / month, #7,959 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 5 - Production/StableIntended Audience :: DevelopersIntended Audience :: EducationIntended Audience :: Science/ResearchLicense :: OSI Approved :: Apache Software LicenseOperating System :: OS IndependentProgramming Language :: Python :: 3Programming Language :: Python :: 3.7Programming Language :: Python :: 3.8Programming Language :: Python :: 3.9Topic :: Scientific/Engineering :: Artificial Intelligence |
Evidence: controlnet_aux-0.0.10-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “controlnet annotators”
- controlnet-auxProvides computer vision annotation and detection models (edge…
- runwareClient library for the Runware inference API, enabling image…
- dtlpymetricsCalculates and generates quality scores for annotations in image and…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also inference-models · supervision · face-alignment · ultralytics · albumentations · pytorchcv · mmcv · mmdet · norfair