ailia-ai / ailia-models

The collection of pre-trained, state-of-the-art AI models. About ailia SDK ailia SDK is a self-contained, cross-platform, high-speed inference SDK for AI. The ailia SDK provides a consistent C++ API across Windows, Mac, Linux, iOS, Android, Jetson, and Raspberry Pi platforms. It also supports Unity (C#), Python, Rust, Flutter(Dart) and JNI for efficient AI implementation. The ailia SDK makes extensive use of the GPU through Vulkan and Metal to enable accelerated computing. • Contact us • Mail How to use Try now on Google Colaboratory If you would like to try on your computer: ailia MODELS tutorial ailia MODELS tutorial 日本語版 Documentation ailia-models wiki Supported models 403 models as of March 12, 2026 Latest update • 2026.03.12 Add depth_anything_v3, depth_pro • 2026.03.06 Add depth_anything_v2 • 2026.03.04 Add gpt-sovits-v2-pro, bevformer, uniad • 2026.03.02 Add g2pw, gpt-sovits-v1, v2, v3 (chinese) • 2026.01.16 Add embeddinggemma • 2025.12.30 Add demucs, latentsync • 2025.12.26 Add sadtalker • 2025.12.25 Add samurai, cotracker3 (ailia SDK 1.6.1) • 2025.12.21 Add silerovad v5, v6, v6_2 • 2025.12.17 Add sensevoice, cosyvoice2 • 2025.12.01 Add glass, mobilevlm, donut • More information in our Wiki Action recognition | | Model | Reference | Exported From | Supported Ailia Version | Date | Blog | |:-----------|------------:|:------------:|:------------:|:------------:|:------------:|:------------:| | | va-cnn | View Adaptive Neural Networks (VA) for Skeleton-based Human Action Recognition | Pytorch | 1.2.7 and later | Mar 2017 || | | st-gcn | ST-GCN | Pytorch | 1.2.5 and later | Jan 2018 | EN JP | | | mars | MARS: Motion-Augmented RGB Stream for Action Recognition | Pytorch | 1.2.4 and later | Nov 2018 | EN JP | | | ax_action_recognition | Realtime-Action-Recognition | Pytorch | 1.2.7 and later | Mar 2019 | | | | driver-action-recognition-adas | driver-action-recognition-adas-0002 | OpenVINO | 1.2.5 and later | Mar 2019 | | | | action_clip | ActionCLIP | Pytorch | 1.2.7 and later | Sep 2021 | | Anomaly detection | | Model | Reference | Exported From | Supported Ailia Version | Date | Blog | |:-----------|------------:|:------------:|:------------:|:------------:|:------------:|:------------:| | | mahalanobisad | MahalanobisAD-pytorch | Pytorch | 1.2.9 and later | May 2020 | | | | spade-pytorch | Sub-Image Anomaly Detection with Deep Pyramid Correspondences | Pytorch | 1.2.6 and later | May 2020 | | | | padim | PaDiM-Anomaly-Detection-Localization-master | Pytorch | 1.2.6 and later | Nov 2020 | EN JP | | | patchcore | PatchCore_anomaly_detection | Pytorch | 1.2.6 and later | Jun 2021 | | | | glass | A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localization | Pytorch | 1.2.14 and later | Jul 2024 | | Audio Language Model | Model | Reference | Exported From | Supported Ailia Version | Date | Blog | |------------:|:------------:|:------------:|:------------:|:------------:|:------------:| |qwen_audio | Qwen-Audio | Pytorch | 1.5.0 and later | Nov 2023 | JP | Audio processing Audio classification | Model | Reference | Exported From | Supported Ailia Version | Date | Blog | |------------:|:------------:|:------------:|:------------:|:------------:|:------------:| | crnn_audio_classification | crnn-audio-classification | Pytorch | 1.2.5 and later | Mar 2019 | EN JP | | audioset_tagging_cnn | PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition | Pytorch | 1.2.9 and later | Dec 2019 | | | transformer-cnn-emotion-recognition | Combining Spatial and Temporal Feature Representions of Speech Emotion by Parallelizing CNNs and Transformer-Encoders | Pytorch | 1.2.5 and later | Oct 2020 | | | microsoft clap | CLAP | Pytorch | 1.2.11 and later | Jun 2022 | | | clap | CLAP | Pytorch | 1.2.6 and later | Nov 2022 | JP | Music enhancement | Model | Reference | Exported From | Supported Ailia Version | Date | Blog | |------------:|:------------:|:------------:|:------------:|:------------:|:------------:| | hifigan | HiFi-GAN | Pytorch | 1.2.9 and later | Oct 2020 | | | deep music enhancer | On Filter Generalization for Music Bandwidth Extension Using Deep Neural Networks | Pytorch | 1.2.6 and later | Nov 2020 | | Music generation | Model | Reference | Exported From | Supported Ailia Version | Date | Blog | |------------:|:------------:|:------------:|:------------:|:------------:|:------------:| | pytorch_wavenet | pytorch_wavenet | Pytorch | 1.2.14 and later | Sep 2016 | | Noise reduction | Model | Reference | Exported From | Supported Ailia Version | Date | Blog | |------------:|:------------:|:------------:|:------------:|:------------:|:------------:| | rnnoise | rnnoise | Keras | 1.2.15 and later | Sep 2017 | | | voicefilter | VoiceFilter | Pytorch | 1.2.7 and later | Oct 2018 | EN JP | | unet_source_separation | source_separation | Pytorch | 1.2.6 and later | Jul 2019 | EN JP | | demucs | Demucs | Pytorch | 1.4.0 and later | Sep 2019 | | | dtln | Dual-signal Transformation LSTM Network | Tensorflow | 1.3.0 and later | May 2020 | | | audiosep | AudioSep | Pytorch | 1.3.0 and later | Aug 2023 | | Phoneme alignment | Model | Reference | Exported From | Supported Ailia Version | Date | Blog | |------------:|:------------:|:------------:|:------------:|:------------:|:------------:| | narabas | narabas: Japanese phoneme forced alignment tool | Pytorch | 1.2.11 and later | Mar 2023 | | Pitch detection | Model | Reference | Exported From | Supported Ailia Version | Date | Blog | |------------:|:------------:|:------------:|:------------:|:------------:|:------------:| | crepe | torchcrepe | Pytorch | 1.2.10 and later | Feb 2018 | JP | Speaker diarization | Model | Reference | Exported From | Supported Ailia Version | Date | Blog | |------------:|:------------:|:------------:|:------------:|:------------:|:------------:| | pyannote-audio | Pyannote-audio | Pytorch | 1.2.15 and later | Nov 2019 | JP |…