EVERY QUESTION.
UNCOMPROMISING ANSWERS.

In WebGPU Mode and API Mode: ABSOLUTELY NOT. All image decoding, RT-DETR bubble detection, PaddleOCR text extraction, and canvas inpainting run 100% locally on your machine in an isolated browser offscreen document.

In API Mode, only extracted text strings (no pixel data) are transmitted to your configured endpoint (such as your local Ollama or LM Studio instance). In Gemini Mode, the annotated manga page is sent directly from your browser to Google AI Studio using your personal API key — with zero proxy server or middleman in between.

Data sharing is strictly opt-in and disabled by default. When enabled in Settings, LMT sends telemetry only when you manually correct or refine a bounding box.

The payload contains only the series name, chapter ID, page number, corrected bounding box coordinates (x1, y1, x2, y2), and image URL. No personal identifiers, IP logs, user accounts, or full page bitmaps are collected.

Yes. Once you select WebGPU Mode and allow the initial model download (Qwen3 4B or 8B, RT-DETR bubble detector ONNX weights, and PaddleOCR models) to complete, all weights are cached permanently in browser Cache Storage and IndexedDB.

You can disconnect your network, enable airplane mode, and translate chapters offline without contacting any server.

API Mode works offline too when you point it at an OpenAI-compatible / LM Studio server on the same machine (e.g. Ollama at http://127.0.0.1:11434/v1 or LM Studio at http://127.0.0.1:1234/api/v1) — localhost traffic never needs the internet after setup. Remote LAN / VPS / cloud hosts still need connectivity.

WebGPU mode requires a Chromium browser (Chrome 113+, Edge 113+, Brave) or Firefox Nightly with dom.webgpu.enabled set to true in about:config.

• Qwen3-4B-q4f16_1-MLC (Balanced): Requires ~3.4 GB available VRAM / unified memory. Recommended for most modern laptops and desktop GPUs.
• Qwen3-8B-q4f16_1-MLC (Powerful): Requires ~5.7 GB available VRAM. Delivers richer literary nuance and idioms.

If your machine lacks a dedicated GPU or has insufficient VRAM, WebGPU mode will notify you and recommend switching to API Mode or Gemini Mode.

Ollama provides an OpenAI-compatible endpoint at port 11434. Follow these steps:

# 1. Pull the recommended translation model
ollama pull qwen3.5:4b

# 2. Start the Ollama server
ollama serve

Then open LMT Settings › Backend and set:

• Backend Kind: API Mode
• Host URL: http://127.0.0.1:11434/v1
• Schema: OpenAI
• Model Name: qwen3.5:4b

Click Test Connection to verify communication.

In LM Studio, navigate to the Developer / Local Server tab, select your preferred model (e.g. tiny-aya-global), and click Start Server on port 1234.

In LMT Settings › Backend:

• Host URL: http://127.0.0.1:1234/api/v1
• Schema: LM Studio (Experimental)
• Model Name: Match the exact model identifier loaded in LM Studio

The experimental schema uses native prompt arrays (input + system_prompt) and parses JSON responses directly without forcing OpenAI-style wrapper envelopes.

For API Mode we recommend a model that was built for translation rather than general chat: Tiny Aya Global for general multilingual translation, or Tiny Aya Fire when your reading is CJK-focused (Chinese / Japanese / Korean). Because they are purpose-trained for translation, they tend to produce cleaner, more consistent manga dialogue than a general-purpose model of the same size. Both are distributed as GGUF, so you can load either one in Ollama, LM Studio or llama.cpp and point LMT at your local host URL as usual.

Google provides free tier API keys through Google AI Studio.

1. Sign in with your Google account at aistudio.google.com.
2. Click Get API key and copy your key.
3. In LMT, open Settings › Backend, select Gemini Mode, and paste the key.

Gemini 2.5 Flash, 3.1 Flash and 3.5 Flash handles both OCR and translation in a single pass with high speed. Your key is stored in browser local storage and never leaves your device except to authenticate directly with Google's API endpoints.

Manga is traditionally read from right to left, top to bottom. LMT builds deterministic regions (refineDetections: centre-in-box merge, speckle drop, overlap merge) then applies agglomerative horizontal band clustering (applyBboxesSort):

1. Calculates vertical centers for all bounding boxes and sorts strictly top-to-bottom.
2. Groups dialogue into horizontal panel bands using a gutter threshold (80% of average bubble height).
3. Sorts bubbles within each panel band using Japanese manga diagonal flow (Right-to-Left).

In the bubble editor overlay, you can manually reorder or refine any box before translation.

Yes. On the results view, click the Edit button in the toolbar. This opens a modal displaying the raw OCR source text alongside the translated output for each numbered bubble.

When you tweak the wording and click Apply, LMT repaints the typography directly on top of the cached inpainted canvas. Inpainting is skipped entirely, delivering an instantaneous re-render.

Traditional extensions run heavy blur or Fast Marching across the entire bounding box, leaving ugly rectangular gray patches and halo artifacts over screentones.

LMT solves this with a multi-stage engine ladder using text-shaped contour masks:

• Rung 0 (Planar Fill): For flat white or uniform speech bubbles, samples the paper border and executes a smooth gradient fill. Zero noise.
• Rung 1 (Bilateral Denoise): For grainy or JPEG-compressed scans, applies edge-preserving bilateral filtering to prevent ringing.
• Rung 2 (LaMa Redraw, opt-in): For complex screentone, halftone and art behind text. One-time ~207 MB download, ~500 MB RAM/VRAM, ~1–2s per complex region (512² tiles, 128px overlap).
• Rung 3 (Pure-JS Telea Fast-Marching): Real rebuilds where fill/denoise fail. MV3-safe, no unsafe-eval.

Every stage is evaluated against an image quality metric; if a rung degrades the page, it escalates to the next engine. Pick Auto (recommended), Telea (legacy full-region) or Fast (edge-blend) under Appearance › Inpainting.

LMT ships with 3 bundled font families: Noto Sans, Bangers, and Comic Neue.

To use your own font:

1. Open extension Settings › Typography.
2. Drag-and-drop any .ttf, .otf, or .woff file into the dropzone.
3. Select your font from the active dropdown.

The font is parsed into browser font storage and dynamically rendered with automatic bubble fit scaling and high-contrast text outlines.

LMT extracts the series title, chapter number, and page index using regex site rules:

• AI Rule Generator: Open the manga chapter in your browser, click the LMT icon › Settings › Site Rules, and click Generate with AI. The active LLM will analyze the page title and URL structure to propose a working rule.
• Submit a Pull Request: Copy src/lib/adapters/_example.ts to src/lib/adapters/<domain>.ts, fill in the 3 regex fields, and submit a PR on GitHub. It bundles into the next release automatically.

Beta5 ships four selectable on-device detectors (Settings › Detection, Min Confidence 0.5, Auto-Update on):

• YOLO26-Nano (default, 2.4 MB, MIT): Fast enough for interactive use; handles most manga.
• YOLO26-Small (9.5 MB, MIT): More accurate on dense / small-text pages; roughly 2.5× slower than Nano.
• Comic Bubble Detector RT-DETR-v2 (11.1 MB, Apache-2.0): Good at bubbles and free-floating text (bubble, text_bubble, text_free).
• Comic Text Detector (94.7 MB, GPL-3.0): Text boxes plus a per-pixel segmentation mask ([1, 1, 1024, 1024]) that seeds fitMask() directly — best for dense vertical Japanese. Never bundled; downloads to your local browser cache only when you select it.

Pick in Settings › Text Recognition (OCR). PaddleOCR (~80 MB, default) is the fast multilingual generalist. Manga-OCR (~460 MB, opt-in) is the Japanese manga specialist (ViT encoder + BERT decoder) for vertical text and stylized lettering.

OCR Min Confidence defaults to 0.7 with a retry pass at 0.7× on failed crops; single characters demand ≥ max(minConfidence, 0.75) to suppress noise. Held-back regions keep their recognized text so you can still view and edit it.

Enable LaMa Redraw for complex screentone, halftone and artwork behind text — where pure-JS fill / denoise / Telea would leave flat patches or smudges. One-time ~207 MB download, ~500 MB RAM/VRAM, ~1–2s per complex region (512² tiled inference, 128px overlap).

It plugs into the Auto ladder as rung 2 (planar → denoise → LaMa → Telea). Per-region provenance ({method, deviation, thickness, ms}) and per-rung counts surface in the debug panel.

Settings › Model Storage lists every downloaded weight with its size, plus per-model delete and full cache clear. Onboarding includes a multi-model downloader with storage progress, and background prefetch (PREFETCH_MODEL) warms the cache.

Translation results are keyed by series + chapter + resolved page index (resolveImagePageIndex) + image hash (quickHash), so re-opening a translated chapter is instant.

Run llama.cpp directly as your local server. Both Ollama and LM Studio build on llama.cpp under the hood — going straight to the source drops the extra GUI layers while staying fully OpenAI-compatible for LMT's API Mode.

Start it with llama-server -m <model>.gguf, then in LMT Settings › Backend set Host to http://127.0.0.1:8080/v1, Schema to OpenAI, and click Test Connection as usual.

The payoff is freshness: new model architectures and GGUF quant releases land in llama.cpp first, so same-day model drops work without waiting for the wrappers to catch up.