Grounding DINO combines a DINO-based detector with grounded pre-training to detect arbitrary objects described in natural language, enabling open-vocabulary object detection.
Grounding DINO — Open-Set Object Detection with Text Prompts
Grounding DINO combines a DINO-based detector with grounded pre-training to detect arbitrary objects described in natural language, enabling open-vocabulary object detection.
Ready-to-run agent install
This asset can be installed after the agent chooses its runtime, checks the plan, and runs the matching command.
npx -y tokrepo@latest install c61831c4-54cb-11f1-9bc6-00163e2b0d79 --target codexRun after dry-run confirms the install plan.
Discussion
Related Assets
Open-Sora — Open-Source Text-to-Video Generation
Open-source alternative to Sora by HPC-AI Tech. Generate videos from text prompts with an 11B parameter model. Apache 2.0 licensed. 28,800+ stars.
Huh — Build Terminal Forms and Prompts in Go
A Go library for building interactive terminal forms with inputs, selects, confirms, and file pickers, powered by the Bubble Tea TUI framework.
CogVLM — Open Visual Language Model with Deep Visual Understanding
A multimodal pretrained model that excels at image captioning, visual question answering, and visual grounding with strong benchmark performance.
OpenSSF Scorecard — Security Health Metrics for Open Source
OpenSSF Scorecard automatically assesses open source projects against a set of security best practices, producing a score that helps maintainers and consumers understand supply chain risk.