Explore 2 APIs and 6 AI models.
DeepLabV3+ is an advanced semantic image segmentation model developed by Google Research, offering improved boundary accuracy and multi-scale context understanding.
https://github.com/tensorflow/models/tree/master/research/deeplabPix2Pix is an open-source image-to-image translation model developed by researchers at UC Berkeley that converts sketches or images into realistic images using conditional GANs.
https://phillipi.github.io/pix2pix/Segment Anything Model (SAM) is an open-source image segmentation model developed by Meta AI that enables promptable segmentation with state-of-the-art accuracy.
https://segment-anything.com/Detectron2 is a powerful open-source computer vision library developed by Meta AI (Facebook AI Research). It excels in object detection, instance segmentation, and keypoint detection tasks.
https://github.com/facebookresearch/detectron2YOLOv5 is a high-performance, open-source object detection model created by Ultralytics. Built with PyTorch, it offers real-time image detection capabilities with high accuracy and speed.
https://docs.ultralytics.com/models/yolov5/Stable Diffusion is a cutting-edge open-source AI model that generates photorealistic images from textual descriptions.
https://stability.ai/blog/stable-diffusion-public-release