Repolode
Submit
ailia-ai

ailia-ai/ailia-models

A collection of 419 pre-trained AI models covering vision, speech, NLP and LLMs, all runnable from a shared Python CLI via the ailia SDK.

View on GitHub
Stars
2,403
Forks
367
Open issues
329
Last commit
yesterday

What is it?

ailia-models is a large collection of pre-trained AI models organized by task, including object detection, pose estimation, face analysis, speech recognition and text-to-speech, image generation, super resolution, LLMs and vision-language models. Each model lives in its own folder with a Python script that can be run without arguments, and weights are downloaded automatically on first use.

The models run on the ailia SDK, a cross-platform inference engine. The repository states support for Windows, macOS, Linux, iOS, Android, Jetson and Raspberry Pi, with GPU acceleration via Vulkan and Metal, and bindings for C++, Python, Unity (C#), Kotlin, Rust and Flutter. Equivalent ports for several of these languages are maintained in separate repositories.

The project suits developers who want to try or prototype a specific model without assembling its original training code and dependencies, then move the same model into a production app on a range of devices.

Key features

  • 01Hundreds of models across vision, audio, NLP, and LLM/VLM tasks, grouped by category.
  • 02Uniform command-line usage: each model runs without arguments and downloads its weights automatically.
  • 03Built on the ailia SDK, with support for Windows, macOS, Linux, mobile and embedded boards.
  • 04Language bindings for C++, Python, Unity, Kotlin, Rust and Flutter.

Use cases

  • Quickly testing whether a pre-trained object detection, pose or segmentation model fits a project.
  • Prototyping speech recognition or text-to-speech pipelines in Python before productionizing.
  • Deploying the same vision or audio model to mobile, desktop or Raspberry Pi through the ailia SDK.

Quick start

  1. 1

    Install the ailia SDK from PyPI

    pip3 install ailia
  2. 2

    Clone the repository

    git clone https://github.com/ailia-ai/ailia-models
  3. 3

    Enter the folder and install the Python requirements

    pip3 install -r requirements.txt
  4. 4

    Run the YOLOX example from its model folder (cd object_detection/yolox first)

    python3 yolox.py

Things to know

  • The license is listed as NOASSERTION, so check each model's license terms before commercial use.
  • The README lists Python 3.9 to 3.12 as supported versions.

Topics

#deep-learning#pretrained-models#computer-vision#speech-recognition#llm#inference#object-detection#action-recognition#anomaly-detection#audio-processing

FAQ

What is ailia-models?
A collection of 419 pre-trained AI models covering vision, speech, NLP and LLMs, all runnable from a shared Python CLI via the ailia SDK. ailia-models is a large collection of pre-trained AI models organized by task, including object detection, pose estimation, face analysis, speech recognition and text-to-speech, image generation, super resolution, LLMs and vision-language models. Each model lives in its own folder with a Python script that can be run without arguments, and weights are downloaded automatically on first use.
Is ailia-models free to use? What license does it have?
ailia-models is open source under the Other license. Check the license terms before using it in commercial products.
Is ailia-models still maintained?
Actively maintained. The last commit to ailia-models was on Oct 19, 2026.
What can I use ailia-models for?
Quickly testing whether a pre-trained object detection, pose or segmentation model fits a project. Prototyping speech recognition or text-to-speech pipelines in Python before productionizing. Deploying the same vision or audio model to mobile, desktop or Raspberry Pi through the ailia SDK.
How do I install ailia-models?
Install the ailia SDK from PyPI: pip3 install ailia Clone the repository: git clone https://github.com/ailia-ai/ailia-models Enter the folder and install the Python requirements: pip3 install -r requirements.txt Run the YOLOX example from its model folder (cd object_detection/yolox first): python3 yolox.py
Where can I get ailia-models?
The source code and installation instructions are on GitHub: https://github.com/ailia-ai/ailia-models

Summary generated by AI from the project's README. GitHub stats refresh daily.

Related projects