FLORA Docs
FLORA Docs
  • Welcome to the Garden
  • Getting Started
    • Quickstart
    • FLORA Concepts
      • Manifesto
      • Our Product Philosophy
  • BLOCKS
    • Block Overview
    • Text Block
      • Text to Text
      • Image to Text
      • Video to Text
    • Image Block
      • Text to Image
      • Image to Image
    • Video Block
      • Text to Video
      • Image(s) to Video
  • Editor
    • Editor Overview
    • Canvas
    • Toolbar
    • Navigation
    • Collaboration & Share
  • HOW TO...
    • Styles
    • Unsplash
  • COMMUNITY
    • Community
Powered by GitBook
On this page
  • Summary
  • Models
  • Video to Text Model
  • Prompt
  1. BLOCKS
  2. Text Block

Video to Text

PreviousImage to TextNextImage Block

Last updated 3 months ago

Summary

Video to text can be performed by connecting a Video Block with a Text Block. Similar to Image to text, it can be used to extract information from any video inputs.

This combination of blocks can be used to Describe the video; Give a numbered list of frames with detailed description of visual content;

Models

Video to Text Model

Llava, a fine-tuned version of of the Qwen model.

Prompt

  • "Describe this video in a few sentence"

  • "Describe the composition and focal points of each frame, on how elements are arranged and how they guide the viewer's attention."

  • "Illustrate the atmosphere of each scene, focusing on sensory details such as lighting, visceral color sensation, and spatial depth."

  • "Describe how recurring motifs and visual patterns contribute to thematic development in the video."

  • "Give me a list of frame in this video and describe each visual composition."

Read more about Llava .

here