GPU-optimized AI, Machine Learning, & HPC Software

NVIDIA

NVIDIA Audio2Face is a microservice for animating 3D character's facial characteristics to match any audio track, whether for a game, film, or real-time digital assistant.

Model

NVIDIA

Audio2Emotion Model

Audio2Emotion TRT Engine.

Model

NVIDIA

Mask Grounding DINO CC

Open vocabulary multi-modal instance segmentation model trained on commercial data.

Model

NVIDIA

RT-DETR 2D Warehouse

RT-DETR object detection model for 2D warehouse applications

Model

NVIDIA

ESS DNN Stereo Disparity

ESS is a DNN that estimates disparity for a stereo image pair and returns a continuous disparity map for the given left image.

Model

NVIDIA

Sparse4D (ResNet-101)

TAO Pretrained Sparse4D with ResNet-101 Backbone

Model

NVIDIA

Sparse4D (ResNet-50)

TAO Pretrained Sparse4D with ResNet-50 Backbone

Model

NVIDIA

Proteina - Complexa

Proteina-Complexa is a flow-matching generative model for fully atomistic protein binder design, jointly generating amino acid sequences and all-atom 3D coordinates from noise using a partially latent architecture derived from La-Proteina

Model

NVIDIA

CUDA Autocomplete

Fine-tuned Qwen2.5-Coder-7B for CUDA code completion in Nsight Copilot

Model

NVIDIA

NVOneFormer Commercial

OneFormer - a unified AI model for multiple image segmentation tasks - trained on commercial data.

Model

NVIDIA

Fast-FoundationStereo

Fast-FoundationStereo Model

Model

NVIDIA

Proteina Complexa Ligand

Proteina-Complexa is a flow-matching generative model for fully atomistic protein binder design, jointly generating amino acid sequences and all-atom 3D coordinates from noise using a partially latent architecture derived from La-Proteina.

Model

NVIDIA

Proteina - Complexa - AME

Proteina-Complexa is a flow-matching generative model for fully atomistic protein binder design, jointly generating amino acid sequences and all-atom 3D coordinates from noise using a partially latent architecture derived from La-Proteina.