Support Matrix#
Models#
Model Name |
Model ID |
Publisher |
|---|---|---|
AI Generated Image Detection |
hive/ai-generated-image-detection |
Hive |
Deepfake Image Detection |
hive/deepfake-image-detection |
Hive |
Supported Hardware#
AI Generated Image Detection#
NVIDIA supports the AI Generated Image Detection model on the following GPU models with the optimized TensorRT engine.
GPU |
GPU Memory (GB) |
Precision |
|---|---|---|
A100 |
40/80 |
FP32 |
H100 |
80 |
FP32 |
L40 |
48 |
FP32 |
A10G |
24 |
FP32 |
NVIDIA supports the AI Generated Image Detection model on any NVIDIA GPU with ONNX.
GPU |
GPU Memory (GB) |
Precision |
|---|---|---|
Any NVIDIA GPU with sufficient GPU memory |
4 |
FP32 |
Deepfake Image Detection#
NVIDIA supports the Deepfake Image Detection model on the following GPU models with the optimized TensorRT engine.
GPU |
GPU Memory (GB) |
Precision |
|---|---|---|
A100 |
40/80 |
FP32 |
H100 |
80 |
FP32 |
L40 |
48 |
FP32 |
A10G |
24 |
FP32 |
NVIDIA supports the Deepfake Image Detection on any NVIDIA GPU with ONNX.
GPU |
GPU Memory (GB) |
Precision |
|---|---|---|
Any NVIDIA GPU with sufficient GPU memory |
4 |
FP32 |
Software#
NVIDIA Driver#
NVIDIA NIM for Multimodal Safety uses Triton Inference Server Production Branch May 2024 (24.03). Refer to the Release Notes for the server to determine the driver requirements.
NVIDIA Container Toolkit#
Your Docker environment must support NVIDIA GPUs. Refer to Installing the NVIDIA Container Toolkit for more information.