All paper summaries read by Merve
Generate responses to your messages
Image and video tasks with moondream3.
Track and visualize project metrics
Visualize project metrics and media logs
Find matching keypoints between two images
Visualize patch similarity with DINOv3 feature maps.
Check if text and images are safe
Demo for ShieldGemma 2, multimodal safety model
Generate text from document images
PaliGemma2 LoRA finetuned on VQAv2
State-of-the-art open-vocabulary image segmentation ⚡️
Find keypoints in images
Generate answers by uploading images or videos
Generate descriptions and answers about images
Video captioning/tracking
Powerful foundation model for zero-shot object tracking
Try PaliGemma on document understanding tasks