Back to directory

ailia-models

A collection of 419 pretrained AI models covering object detection, speech recognition, image generation, large language models and more, each runnable from the same simple command-line interface using the ailia SDK.

ailia-models

ailia-models is a collection of 419 pretrained, state-of-the-art AI models for the ailia SDK, spanning categories such as action recognition, anomaly detection, audio classification, speech-to-text and text-to-speech, background removal, autonomous driving, crowd counting, fashion detection, depth estimation and image and video diffusion, among others.

Every model works the same way: after installing the ailia package and the repository's requirements, running a model's script with no arguments downloads its weights automatically and produces a result, so different models can be tried without separate setup for each one.

More in Models

See all 405
  • mini-AGI

    github.com

    A continual learning language model that trains from scratch on a single 8 GB VRAM GPU, assembling its own architecture and adapting its size to the hardware and data available rather than shipping as a fixed pretrained model.

  • An open-source contrastive-embedding pipeline that maps technical CVE vulnerability descriptions to formal cybersecurity compliance controls in NIST SP 800-53 and CMMC, published with its model generation, fine-tuning and evaluation code.

  • peekaboolean

    github.com

    A small vision-language model, fine-tuned with LoRA on a 500-million-parameter backbone, that answers typed multiple-choice, ordinal-score and yes/no questions about an image with calibrated probabilities, in about 400 milliseconds on a laptop.