marker vs pdf-craft
PDF conversion tools compared
marker and pdf-craft are Python projects for turning PDFs into more usable digital formats. marker handles PDFs and several other document types with structured outputs, while pdf-craft focuses on OCR workflows for scanned PDFs, including EPUB creation and translation.

marker: Convert Documents into Structured Text
Marker converts PDFs and other documents into Markdown, JSON, HTML, or chunks, preserving structure such as tables, equations, and images. It suits developers building document-processing workflows who can run its local models and inference backend.

pdf-craft: Convert Scanned PDFs with DeepSeek OCR
PDF Craft is a Python library and online service for turning scanned books, research papers, and technical documents into editable Markdown or reader-friendly EPUB. Built around DeepSeek OCR, it also supports translation and translated PDF output.
| marker | pdf-craft | |
|---|---|---|
| Language | Python | Python |
| License | Apache-2.0 | MIT |
| Stars | 40.2k | 6.4k |
| Forks | 2.9k | 466 |
| Last analyzed | Oct 3, 2026 | Oct 18, 2026 |
Key differences
- marker supports PDFs and, with additional dependencies, formats such as DOCX, XLSX, HTML, and EPUB; pdf-craft focuses on scanned PDFs.
- marker outputs Markdown, JSON, HTML, or chunks and targets structured extraction; pdf-craft creates Markdown or EPUBs and offers translation workflows.
- marker uses text-layer extraction, layout detection, OCR, and selective vision-language model use; pdf-craft combines OCR with conversion and optional translation.
- marker describes local inference options including GPU and CPU setups; pdf-craft supports remote OCR by default, while local OCR requires suitable NVIDIA GPU hardware and configuration.
- marker is licensed under Apache-2.0, with model weights under separate terms; pdf-craft is licensed under MIT.
- The supplied project figures list marker at 40.2k stars and 2.9k forks, and pdf-craft at 6.3k stars and 460 forks.
Choose marker if you…
- need structured outputs such as JSON, HTML, or chunks for downstream processing.
- want to process a range of document formats or customize conversion with processors and renderers.
- need a self-hosted workflow and can configure its local inference backend.
Choose pdf-craft if you…
- want to turn scanned books or documents into Markdown or EPUB.
- need translation options, such as bilingual EPUB output or translated text written onto PDF pages.
- want synchronous or asynchronous Python APIs and reusable extraction results.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.