Try NVIDIA NIM APIs

nvidia streampetr

StreamPETR offers efficient 3D object detection for autonomous driving by propagating sparse object queries temporally.

autonomous vehicles bev AV Stack automotive

nvidia parakeet-ctc-0.6b-zh-cn

Record-setting accuracy and performance for Mandarin English transcriptions.

ASR Streaming Speech-to-Text Mandarin NVIDIA NIM

nvidia sparsedrive

End-to-end autonomous driving stack integrating perception, prediction, and planning with sparse scene representations for efficiency and safety.

autonomous vehicles bev av stack automotive

nvidia nv-embedcode-7b-v1

The NV-EmbedCode model is a 7B Mistral-based embedding model optimized for code retrieval, supporting text, code, and hybrid queries.

nemo retriever Embedding Retrieval Augmented Generation

nvidia llama-3.2-nv-embedqa-1b-v2

Multilingual and cross-lingual text question-answering retrieval with long context support and optimized data storage efficiency.

nemo retriever embedding Retrieval Augmented Generation Text-to-Embedding

nvidia llama-3.2-nv-rerankqa-1b-v2

Fine-tuned reranking model for multilingual, cross-lingual text question-answering retrieval, with long context support.

nemo retriever Retrieval Augmented Generation reranking

nvidia nv-yolox-page-elements-v1

Model for object detection, fine-tuned to detect charts, tables, and titles in documents.

Object Detection Data ingestion Chart Detection nemo retriever Table Detection run-on-rtx extraction

nvidia nv-dinov2

NV-DINOv2 is a visual foundation model that generates vector embeddings for the input image.

Image-to-Embedding computer vision deepstream NVIDIA NIM object Classification

nvidia nv-grounding-dino

Grounding dino is an open vocabulary zero-shot object detection model.

Object Detection computer vision deepstream NVIDIA NIM

nvidia nv-embedqa-e5-v5

English text embedding model for question-answering retrieval.

Embedding run-on-rtx Retrieval Augmented Generation Nemo retriever Text-to-Embedding

nvidia maisi

MAISI is a pre-trained volumetric (3D) CT Latent Diffusion Generative Model.

Image Generation Medical Imaging NVIDIA NIM

nvidia nvclip

NV-CLIP is a multimodal embeddings model for image and text.

Computer vision multimodal embeddings text and image Run-on-rtx

nvidia ocdrnet

OCDNet and OCRNet are pre-trained models designed for optical character detection and recognition respectively.

Optical Character Recognition image Optical Character Detection cv vlm computer vision TAO Toolkit video

nvidia nv-embed-v1

Generates high-quality numerical embeddings from text inputs.

Non-Commercial Use Only Retrieval Augmented Generation Text-to-Embedding

nvidia visual-changenet

Visual Changenet detects pixel-level change maps between two images and outputs a semantic change segmentation mask

image Image Generation cv Image Segmentation vlm computer vision TAO Toolkit video NVIDIA NIM

nvidia retail-object-detection

EfficientDet-based object detection network to detect 100 specific retail objects from an input video.

Object Detection image cv vlm computer vision TAO Toolkit video NVIDIA NIM

google paligemma

Vision language model adept at comprehending text and visual inputs to produce informative responses

image cv Vision Assistant vlm Visual Question Answering computer vision Language Generation Image-to-Text video