# Descripción general

Visión por computadora y modelos visión-idioma en GPU de CLORE.AI.

## Guías disponibles

| Modelo                                                                   | Caso de uso               |
| ------------------------------------------------------------------------ | ------------------------- |
| [LLaVA](/guides/guides_v2-es/modelos-de-vision/llava-vision-language.md) | Chat y preguntas visuales |
| [Florence-2](/guides/guides_v2-es/modelos-de-vision/florence2.md)        | Visión multitarea         |
| [SAM2](/guides/guides_v2-es/modelos-de-vision/sam2-video.md)             | Segmentación de video     |
| [GroundingDINO](/guides/guides_v2-es/modelos-de-vision/groundingdino.md) | Detección zero-shot       |

## Casos de uso

* **Comprensión de imágenes** - LLaVA, Florence-2
* **Detección de objetos** - GroundingDINO, YOLO
* **Segmentación** - SAM2, Segment Anything
* **Generación de descripciones** - Florence-2, LLaVA

## Requisitos de GPU

| Modelo        | VRAM mínima |
| ------------- | ----------- |
| LLaVA 7B      | 8GB         |
| Florence-2    | 8GB         |
| SAM2          | 8GB         |
| GroundingDINO | 6GB         |

## Guías relacionadas

* [Modelos de Lenguaje](/guides/guides_v2-es/modelos-de-lenguaje/language-models.md)
* [Visión por Computadora](/guides/guides_v2-es/vision-por-computadora/computer-vision.md)


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.clore.ai/guides/guides_v2-es/modelos-de-vision/vision-models.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.