deepseek-ai/DeepSeek-OCR
An OCR model for visual text compression
View on index · View in 3D Map
Related repos
- DeepSeek-VL2, a vision-language AI modelfor tasks like visual question answeringand OCR
- Offline OCR using DeepSeek-OCR AI
- OCR app with PDF processing and document conversion
- unified multimodal model for both understanding and generating images and text
- Reproduces DeepSeek-OCR using VILA codebase
- Desktop GUI for real-time OCR with GPU acceleration
- Rust implementation of DeepSeek-OCR inference stack
- Generates synthetic text images for OCR training
- OCR utility for copying text from images or videos
- 7B text-to-image model for text rendering
