Box — AI 图像生成工具中文文档

Requirements

• Android 16+
• ~4 GB of free storage for a typical quantised LLM
• `6 GB of Ram

Requirements

- Ubuntu (amd64) with a GTK4 / libadwaita desktop session - ~3–4 GB of free storage for a model - A webcam is optional (live vision mode) - CPU-only works fine; GPU acceleration is faster but not required. NPU/GPU paths are included but not all hardware is tested.

---

Install via Obtainium

1. Open Obtainium on your phone 2. Tap the + button 3. Paste this repo URL: https://github.com/jegly/Box 4. Tap Add

Recommended for most users: Main version

### Which version should I install? | Version | For | |---|---| | Main | Stock Android (Pixel, Samsung, etc.) | | Custom ROM | GrapheneOS, LineageOS, CalyxOS — no Google services | - The in-app updater is also available in Settings ### Setup steps 1. Tap the badge for your version above — this opens Obtainium with the repo pre-filled 2. Under APK filter regex, enter one of the following: - Main: Main - Custom ROM: custom-rom-support 3. Tap Add — Obtainium will find the latest release and install it 4. Future updates will be detected automatically > Note: The version number shown inside the app (1.0.13) reflects the > upstream Google AI Edge Gallery build number and is unrelated to the Box > release version. Box releases are tracked via GitHub tags (v1.0.5 etc). > Use Settings → Check for updates to see if a newer Box release is available.

Box is a security-hardened fork of Google AI Edge Gallery — with on-device image generation, voice mode (speech-to-speech AI chat), voice input, document analysis, vision AI, biometric lock, encrypted chat history, llama.cpp support, and GGUF model import.

[!IMPORTANT] ## Disclaimer

Box is an independent community fork of Google AI Edge Gallery and is not affiliated with or endorsed by Google LLC. Google branding has been replaced throughout. All credit for the underlying platform goes to Google and the original contributors — this fork simply builds on top of their work.

Getting Started

Build from source

git clone --recurse-submodules https://github.com/jegly/box
cd box/Android
./gradlew :app:assembleDebug

The --recurse-submodules flag is required to pull llama.cpp, stable-diffusion.cpp, and whisper.cpp submodules. The first build compiles all three native libraries from source — expect 15–25 minutes.

Open Android/ in Android Studio and run on a physical device for best performance.

Install

Download the latest .deb from the Releases page:

sudo apt install ./box_<version>_amd64.deb

The package pulls its system dependencies automatically. Then launch Box from your application menu, or run box from a terminal. On first run, Box offers to download a model (Gemma 4 E2B, ~2.59 GB) — models are downloaded once and then used entirely offline.

Screenshots

Home Overview	AI Chat	Chat Overview
Vision AI	Voice Input	Audio Scribe
Whisper STT	Voice Mode	Image Generation
Agent Skills	Prompt Lab	Model Config
Model Select	Settings	Gemini Nano

</div>

--- > [!NOTE] >## What Box adds on top of upstream

Box is a fork of Google AI Edge Gallery. The upstream project is excellent — Box just layers on additional capabilities:

Area	What Box adds
Inference engines	llama.cpp (GGUF LLMs), stable-diffusion.cpp (image gen), whisper.cpp (STT) alongside LiteRT
Model import	Import any local GGUF file — not limited to the curated download list
NPU / TPU	All Snapdragon / Tensor / MediaTek variants bundled in one APK (upstream ships per-SoC)
Voice mode / Vision mode	Free talk (continuous hands-free loop) and Vision talk (live camera + voice)
Image generation	On-device Stable Diffusion via GGUF
Speech-to-text	On-device Whisper STT
Document analysis	Attach text files (.txt, .md, .csv, .kt, etc.) directly in chat
Document Q&A	RAG pipeline: import PDFs, embed with MiniLM on-device, ask questions grounded in document content — answers cite their source passages
Gemini Nano	6 on-device ML Kit features (Summarize, Proofread, Rewrite, Chat, Describe, Speech) — NPU/TPU-accelerated on Pixel 9+, entirely on-device via AICore (main branch)
Background Removal	ML Kit Subject Segmentation — remove backgrounds from photos, output a transparency-preserving PNG (main branch)
Chat history	Persisted to a SQLCipher-encrypted Room database, resumable across sessions
Security	Biometric app lock, hard offline mode, prompt sanitisation, audit log, tap jacking protection, accessibility data sensitivity
Themes	Catppuccin (14 accents) and Dracula (7 accents) alongside Material You — three-way picker in Settings
Agent skills	20 built-in skills (upstream has 9)
Math rendering	LaTeX expressions rendered as Unicode in chat, including inside markdown table cells
App shortcut	Long-press icon → AI Chat for instant cold-start navigation
In-app updates	Settings → Check for updates — compares against latest GitHub release, downloads correct variant

---

Screenshots

Local Chat	Knowledge Base	Permission Prompts
Web & File Tools	Agent Mode	Persistent Memory
Vision & Camera	Voice & TTS	RAG Settings
Model Settings	Behaviour	Themes & Appearance

</div>

---

Knowledge Base — Document Q&A

Attach a PDF, Markdown file, source file, or plain text and Box chunks, embeds, and indexes it for retrieval — every answer is grounded in your documents, and a card on each reply shows exactly which passages the model used. Notebooks are named, reusable collections of documents that live independently of any chat: index a body of knowledge once and attach it to as many chats as you like, with an optional auto-attach for collections you always want. Retrieval unions a chat's private sources with every attached notebook.