Screenshots
At a Glance
A quick look
Zero photo uploads — your privacy stays on-device. Search your local gallery and edit photos, all in natural language.
A smart gallery that speaks your language
Manage your gallery by chatting: "Find last summer's photos" or "Make this one warmer." PoLang understands and does it.
On-device semantic search & search-by-image: auto-tags every photo (scene / people / objects / activity), so even vague descriptions hit the right shots.
GPU-accelerated pro tools: smooth skin, brighten, slim face, enlarge eyes, lip color, blush. One-tap AI enhancement.
Leica (classic / vivid / mono), film (gold / Fuji / vintage), real-time GPU effects, with batch support.
Face detection, beauty, and tagging run on-device. Your photos are never uploaded, and we collect no data.
Browse, search, and edit your gallery from Feishu or Telegram — results land right back in the chat.
A quick look
Make the AI truly get you
Tagging, face recognition, and semantic search all rely on on-device AI models. Download them in "Model Center → Required" — 7 models, ~1.5 GB.
Open "TAG Generation" and scan so PoLang learns the people and scenes in your gallery (faces + semantics), about 1.5h / 10k photos. Remember to keep background activity on.
Want "beach" or "night scene" searches to be sharper? Run image understanding to tag scenes, objects, and activities — about 24h / 10k photos, best overnight while charging.
AI chat runs on a cloud-based model by default. Sign in with email for a higher free quota (guests get less). A network connection is all you need.
Name people and set relationships (family / friends…), then add facts in "AI Memory" — PoLang gets to know you better over time.
Connect Feishu / Telegram to drive your gallery from IM in natural language — results come right back to the chat. Telegram uses long-polling, no public IP needed.
"Find last summer's beach photos" — matches show up, grouped smartly. All search, face, and scene recognition happens on-device; photos are never uploaded.
Drive your gallery with natural language
"Find last summer's beach photos"
🗂️ 12 matches, grouped smartly by time
"Make this one warmer"
🎨 Warm filter applied — what you see is what you get
"Smooth skin 50, brighten 30"
✨ Beauty params applied
"What's in this photo?"
🤖 Beach, sunset, two people (recognized on-device)
Fully open on GitHub. "Photos never uploaded" isn't a slogan — you can verify every network request yourself.
View source →No. Face detection, beauty, and tagging run on your device. Your photos never leave your phone.
Smart search relies on on-device models and a one-time gallery scan. First download the required models in "Model Center" and run a scan — see the Getting Started guide.
The required face + semantic scan takes about 1.5h per 10k photos; the more accurate image-understanding pass takes about 24h per 10k — best run overnight while charging. Already-processed photos won't repeat.
Chat runs on a cloud-based model with a free quota; sign in for a higher quota. A network connection is required.
Yes. No ads, no subscriptions, no in-app purchases — every feature is free.
On-device capabilities like tagging, face recognition, and scene detection work fully offline. Cloud AI chat requires a network connection.
Android 7.0 (API 24) and above; beauty and on-device inference run best on arm64 devices. An iOS version is in development — coming soon.
No. We collect no user data. See the Privacy Policy.
Same on-device, offline, open-source promise — plus a full editor and an AI assistant
| Capability | PoLang | Queryable / PicQuery | Google Photos |
|---|---|---|---|
| On-device semantic search (CLIP / MobileCLIP) | ✅ hybrid recall | ✅ | ☁️ cloud |
| Search by image | ✅ | ✅ | ✅ |
| People naming & relations ("my daughter's photos") | ✅ | ❌ | ☁️ cloud |
| Conversational gallery management & editing | ✅ | ❌ | ❌ |
| Cutout / ID photo / beauty editor | ✅ | ❌ | partial |
| Open source / price | MIT · free | MIT · Queryable $4.99 one-time | ❌ · free (cloud) |
Free · No ads · Photos never uploaded