# google/Gemini-Vision
#### NOTE
This is a [remotely-sourced model](../remote.md#model-zoo-remote) from the
[gemini-vision-plugin](../../plugins/plugins_ecosystem/gemini_vision_plugin.html) plugin, maintained by the community.
It is not part of FiftyOne core and may have special installation requirements.
Please review the plugin documentation and license before use.
Gemini Vision remote model for VQA via Google Gemini API.
**Details**
- Model name: `google/Gemini-Vision`
- Model source:
- Model author: Google
- Model license: Apache-2.0
- Exposes embeddings? no
- Tags: `gemini, vision, vqa, multimodal`
**Requirements**
- CPU support
- no
- GPU support
- no
**Example usage**
```python
import fiftyone as fo
import fiftyone.zoo as foz
foz.register_zoo_model_source("https://github.com/AdonaiVera/gemini-vision-plugin")
dataset = foz.load_zoo_dataset(
"coco-2017",
split="validation",
dataset_name=fo.get_default_dataset_name(),
max_samples=50,
shuffle=True,
)
model = foz.load_zoo_model("google/Gemini-Vision")
dataset.apply_model(model, label_field="predictions")
session = fo.launch_app(dataset)
```