Repository Showcase
A curated collection of interesting GitHub repositories
deepseek-ai/Janus
unified multimodal model for both understanding and generating images and text
Related repos
- DeepSeek-VL2, a vision-language AI modelfor tasks like visual question answeringand OCR
- multimodal AI model for text, image, and video tasks
- text-to-image model for fast high-res AI image generation
- DeepSeek-R1 GitHub repo with model code and info
- An OCR model for visual text compression
- multimodal model for text-to-image, image editing, and in-context generation
- DeepClaude: Combines DeepSeek R1 and Claude 3.5 for AI reasoning and coding
- open large multimodal models for vision and language tasks
- 2K text-to-image AI model with multilingual support and high-res output
- DeepSeek-V3, a Mixture-of-Experts language model with 671B parameters and 37B active per token, focused on math and coding tasks
