Chart Extraction. This is a context aware chart element detection model that can detect 18 classes for chart basic elements, excluding plot elements.
Table Extraction. This is an open-source model from Baidu Research and receives an image as input, runs OCR on the image, and returns the text within the image and their bounding boxes.
Advanced AI model detects faces and identifies deep fake images.
Advanced Small Language Model supporting RAG, summarization, classification, code, and agentic AI
Highly efficient Mixture of Experts model for RAG, summarization, entity extraction, and classification
Shutterstock Generative 3D service for 360 HDRi generation. Trained on NVIDIA Edify using Shutterstock’s licensed creative libraries.
Cutting-edge vision-language model exceling in high-quality reasoning from images.
Cutting-edge vision-Language model exceling in high-quality reasoning from images.
Generates consistent characters across a series of images without requiring additional training.
Multi-modal vision-language model that understands text/img/video and creates informative responses
Robust image classification model for detecting and managing AI-generated content.
Cutting-edge open multimodal model exceling in high-quality reasoning from images.
NV-DINOv2 is a visual foundation model that generates vector embeddings for the input image.
An enterprise-grade text-to-image model trained on a compliant dataset produces high quality images.
Vision foundation model capable of performing diverse computer vision and vision language tasks.
AI-powered search for OpenUSD data, 3D models, images, and assets using text or image-based inputs.
Shutterstock Generative 3D service for 3D asset generation. Trained on NVIDIA Edify using Shutterstock’s licensed creative libraries
Getty Images’ API service for 4K image generation. Trained on NVIDIA Edify using Getty Images' commercially safe creative libraries.
MAISI is a pre-trained volumetric (3D) CT Latent Diffusion Generative Model.
NV-CLIP is a multimodal embeddings model for image and text.
Advanced text-to-image model for generating high quality images
OCDNet and OCRNet are pre-trained models designed for optical character detection and recognition respectively.
Visual Changenet detects pixel-level change maps between two images and outputs a semantic change segmentation mask
EfficientDet-based object detection network to detect 100 specific retail objects from an input video.
Cutting-edge open multimodal model exceling in high-quality reasoning from images.
Generate images and stunning visuals with realistic aesthetics.
One-shot visual language understanding model that translates images of plots into tables.
VISTA-3D is a specialized interactive foundation model for segmenting and anotating human anatomies.
Stable Video Diffusion (SVD) is a generative diffusion model that leverages a single image as a conditioning frame to synthesize video sequences.
A fast generative text-to-image model that can synthesize photorealistic images from a text prompt in a single network evaluation