#2525th of 70 in Open models
ailia-models
427 pre-trained vision, audio and NLP models with runnable ailia scripts
- Stars
- 2.4k
- License
- custom license
- Last commit
- Nov 2026
- Language
- Python
2,321 on 21 Apr 20262,404 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
A repository of per-model sample scripts for 427 pre-trained models covering detection, segmentation, depth estimation, speech recognition, text to speech, diffusion, embeddings and more. Each script downloads its weights automatically and runs through the ailia inference SDK installed from PyPI. It targets Python 3.9 to 3.12 on Windows, macOS, Linux, iOS, Android, Jetson and Raspberry Pi.
Who it is for: Engineers trying pre-trained models on desktop or edge devices via ailia
Strengths
- Every model runs the same way: no arguments, weights download automatically
- Wide coverage across vision, audio, diffusion, NLP and embeddings in one repo
- Lists mobile and edge targets such as Jetson and Raspberry Pi
- Includes recent models such as Qwen3-TTS, SAM 3.1 and Depth Anything v3
Weaknesses
- Requires the ailia SDK, a separate runtime from the sample scripts
- License is reported as NOASSERTION, so terms are unclear from repo metadata
- No release tags, so versions are tied to commits
- Standalone per-model scripts, not a served API or unified library
What it needs
- Needs ailia (PyPI), Python 3.9-3.12
Quick answers
Is ailia-models open source?
Its code is public on GitHub under its own license terms; read them before you use it at work.
Also in Open models
See all 70| Rank | Project | Score |
|---|---|---|
| 1 | ruviewWiFi CSI sensing on ESP32 for presence, breathing, heart rate and pose | 94 out of 100 |
| 2 | layaSingle-pass multilingual classifier for typed choice, score and yes/no decisions | 88 out of 100 |
| 3 | rf-detrReal-time transformer models for object detection, segmentation and keypoints | 79 out of 100 |
| #4 | timesfmPretrained time-series foundation model for zero-shot forecasting from Google Research | 78 out of 100 |
| #5 | yolov5PyTorch YOLOv5 object detection, segmentation and classification models with training code | 76 out of 100 |