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

说明与用途

Screenshot Sloth 使用 Florence‑2 模型对截图进行 OCR，并自动重命名、分类和标记文件，所有操作均在本地完成，无需上传数据。

问题

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

结果

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.

工作流

• 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

证据

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

来源

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

来源

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

来源