I lay down. A 0.23B open model sorted my screenshots folder.

Описание и применение

Screenshot Sloth использует модель Florence‑2 для распознавания текста в скриншотах и автоматически переименовывает, сортирует и помечает файлы, сохраняя данные локально без загрузки в облако.

Задача

Users have large folders of screenshots with generic names, making it hard to locate specific items such as receipts, OTPs, or tickets.

Результат

On a 12‑image demo set, Screenshot Sloth processed all images in 1 min 21 s, while manual sorting would take ~2 min. The tool provides a safe, offline workflow with undo capability.

Рабочий процесс

• Select folder via File System Access API
• Model downloads (≈350 MB) and runs in WebGPU/WebWorker
• OCR each image and extract text with bounding boxes
• Apply rules to determine filename, folder, and flags
• Show proposed plan to user
• User reviews and edits plan
• Apply changes: rename, move, flag, duplicate handling
• Log all moves to .screenshot‑sloth‑undo.json
• Provide Undo option

Доказательства

Screenshot Sloth reads every screenshot in a folder with an open‑source vision model, inside your browser tab, and proposes a plan:

Источник

The first run downloads the model once (about 350 MB, then cached). After that the demo goes like this:

Источник

Machine time: 1 min 21 s to read all 12 (after the one‑time model download)

Источник