Termux-Vision
안드로이드 Termux를 위한 제로 디펜던시 온디바이스 컴퓨터 비전 & VLM 멀티모달 추론 엔진
Zero-Dependency On-Device Computer Vision & Multimodal VLM Inference Engine for Android Termux
Architecture & Overview
- 초고속 C/C++ CPU 비전 커널: 8-방향 2차원 BFS Hysteresis Canny 에지 검출, Sobel 3x3, 적분 영상 필터링을 스레드 로컬 0-Allocation 스크래치 버퍼로 1ms 내에 완료.
- AMEVA Vulkan Runtime 완전 통합: 기기 드라이버 및 칩셋 버그(Quirks)를 자동 패치하고
--device auto -ngl 99로 모바일 GPU 가속 완전 위임. - 스마트 4단계 해상도 프리셋:
fast(384px),optimal(768px),high(1280px),original로 모바일 메모리 한계 내에서 VLM 추론 최적화. - 듀얼 엔진 지원: Python (
pip) 및 Node.js (npm) 양대 언어에서 100% 동일한 비전 파이프라인 제공.
Installation & Quickstart
One-Touch Installer (Recommended)
curl -sL https://raw.githubusercontent.com/uno-km/termux-vision/main/install.sh | bash
Python (PyPI)
pip install termux-vision && termux-llama install
import termux_vision as tv
# 1. Classical CV Filters (Sub-millisecond C/C++ Engine)
img = tv.io.load_image("photo.jpg")
edges = tv.cv.canny(tv.transforms.to_grayscale(img), 40, 120)
# 2. On-Device VLM Multimodal Inference
with tv.vlm.load("smolvlm-500m-q4", quality="optimal") as engine:
res = engine.describe("photo.jpg", prompt="Describe this scene in detail.")
print(f"[{res.metrics.backend.upper()}] {res.text}")
Node.js / TypeScript (npm)
npm install -g termux-vision && pkg install termux-llamacpp
import tv from 'termux-vision';
// 1. Diagnostics & Hardware Probe
const doc = tv.doctor(true);
console.log(`Vulkan GPU: ${doc.vulkan.status} | Cores: ${doc.hardware.cpuCores}`);
// 2. Multimodal VLM Inference
const engine = await tv.load({ modelId: 'smolvlm-500m-q4' });
const result = await engine.describe('photo.jpg', { prompt: 'What is inside this image?' });
console.log(`[${result.metrics.backend.toUpperCase()}] ${result.text}`);
engine.close();
Official Documentation & Benchmarks
- Official Architecture & API Reference
- Ecosystem Metrics & Registry Stats
- AMEVA Open-Source Foundation Portal
License
Licensed under the Apache-2.0 License. Copyright (c) 2026 Eunho Kim (@uno-km).
1 maintainer
Metadata
1 maintainer
Release files for termux-vision 1.1.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| termux_vision-1.1.1.tar.gz | 77.6 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| termux_vision-1.1.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 157.6 kB
Release files / termux_vision-1.1.1.tar.gz
| Download URL | termux_vision-1.1.1.tar.gz |
|---|---|
| Size | 77.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
759230e2fed53adfd83bce2ee324238cb93bfbc556be7d125b47fb981ffc3a8e
|
|
BLAKE2b-256 checksum How to use checksums |
266529a857cf09dfca0d3c2a1fa98f225c46294f6048813f06acaa1b8072e556
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.12.0
|
Release files / termux_vision-1.1.1-py3-none-any.whl
| Download URL | termux_vision-1.1.1-py3-none-any.whl |
|---|---|
| Size | 80.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
0300b9a131ba454d40f111f9a5c21d393b8f31c66e68b4babd3b47a18a53d390
|
|
BLAKE2b-256 checksum How to use checksums |
28db07987801dfcffcb046ab2621da999f11c3e25daba837f35ff0d221d30160
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.12.0
|
