You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Count the number of occurrences of various objects in single or multiple images, leveraging the capabilities of GroundingDINO. This extension enhances GroundingDINO's usability by incorporating object counting functionality, providing a total count of detected items.
Explore the cutting edge of computer vision with this comprehensive repository, showcasing a spectrum from classical machine learning to state-of-the-art transformer models.
This project explores the intersection of NLP and CV, showcasing the potential of leveraging three powerful models – SAM, Stable Diffusion, and Grounding DINO – to edit manipulate images through textual commands.
A project to combine Grounding-DINO with Meta AI's Segment Anything Model (SAM) and Stable Diffusion for image manipulation using prompts. The plan is to integrate these techniques and deploy the model on Hugging Face with a Gradio interface for users to detect, segment regions and inpaint them in images.