llava

Answer visual questions and caption images using vision-language models.

Updated Jun 25, 2026

Search Tags:#multimodal #computer vision #conversational ai #vision-language #vqa #llava

Ready to run

npx skills add https://github.com/Rheasilvia/hermes-desktop --skill llava-rheasilvia

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: llava
Source: https://github.com/Rheasilvia/hermes-desktop/tree/main/optional-skills/mlops/llava
Command: npx skills add https://github.com/Rheasilvia/hermes-desktop --skill llava-rheasilvia

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires transformers, torch, pillow, and includes references (resource) components.

What problem does it solve?

This skill bridges the gap between visual perception and natural language, allowing users to interact with images through conversational queries rather than manual analysis.

Core Features & Use Cases

Visual Question Answering: Ask specific questions about the content, objects, or text within an image.
Image Captioning & Description: Generate detailed, context-aware descriptions of visual scenes.
Use Case: Use this skill to analyze a set of product photos to automatically generate descriptive alt-text or to query a document image for specific data points.

Quick Start

Use the llava skill to analyze the provided image and describe the objects present in the scene.

Frequently Asked Questions about llava

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I perform visual question answering on an image using a vision-language model?▼

Visual question answering uses vision-language models to analyze image content and respond to conversational queries. This skill enables multimodal interaction, allowing you to ask specific questions about objects, text, or scenes within an image using torch and transformers.

Can I automatically generate image captions and descriptions for product photos?▼

Yes, you can automatically generate image captions for product photos. The skill leverages vision-language models to produce detailed, context-aware descriptions of visual scenes, bridging visual perception with natural language for automated alt-text generation.

Does visual question answering require GPU-accelerated hardware and specific Python dependencies?▼

Yes, high-performance visual question answering requires GPU-accelerated hardware. The skill depends on torch, transformers, and pillow to execute inference, requiring this specific environment setup to process images and generate conversational responses effectively.

What is the best way to extract specific data points from a document image?▼

The best way to extract data points from a document image is using multimodal conversational interaction. By leveraging vision-language models, you can query the document image directly with natural language questions to identify and retrieve specific textual or visual data.

How do I identify objects within a scene using conversational AI?▼

You identify objects within a scene by providing the image to a vision-language model and asking conversational queries. This skill performs scene analysis and object identification by bridging visual perception with natural language processing through transformers.