nvidia/nemotron-3-nano-omni/vision

Vision reasoning variant of NVIDIA's Nemotron 3 Nano Omni. 30B A3B hybrid Transformer-Mamba MoE - accepts an image plus a prompt and returns text.

Learn more about Nemotron

Inference

Commercial use

Schema

LLMs

Playground API Examples

Prompt examples

Examples are generated using the Nemotron 3 Nano Omni. You can customize them by clicking on the "Playground" button.

text

This is a highly stylized, close-up portrait of a person featuring elaborate and surreal body art.

**Face and Makeup:**
The person's face is the central focus, covered in intricate, colorful patterns that resemble a mix of tribal art, paisley, and organic textures.
*   **Colors:** The

describe the image

Playground