📦 It all starts in Settings
Model downloads, scan controls, account, people, and remote channels all live in the app's Settings. Each step below points you to the right screen.
1Download required models
Tagging, face recognition, and semantic search all rely on on-device AI models. Go to Model Center → Required and download them all (7 models, ~1.5 GB). The Recommended models (local chat, matting, voice) are optional.
2Run a Pass 1 scan
Let the app learn the people and scenes in your gallery. Go to TAG Generation and start scanning (face detection + semantic encoding, ~1.5h / 10k photos). Remember to enable background activity when prompted, or it may be paused in the background.
3(Optional) Understand image content
Want searches like "beach", "night scene", or "family picnic" to be sharper? Run Image Understanding to generate scene, object, and activity tags for every photo. ~24h / 10k, best overnight while charging. Pause anytime — already-processed photos won't repeat.
4Sign up for quota
AI chat defaults to a remote model for the best experience. Sign in with email for a higher free quota (guests get less). When it runs out you'll see a notice, or switch to the local model to chat offline.
5Teach AI your people
After scanning, people are detected automatically. Name each person and set relationships (family / friends / colleagues…), then add facts in AI Memory — PoLang gets smarter in every conversation.
6(Optional) Remote control
Connect Feishu / Telegram to drive your gallery from IM (e.g. "send me yesterday's landscapes") — results come right back to the chat. Telegram uses long-polling, no public IP needed.
