Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.heyoz.com/llms.txt

Use this file to discover all available pages before exploring further.

The Text/Image to Video models in HeyOz’s Generative AI Models let you create stunning, AI-generated videos from simple text prompts or uploaded images giving you total creative freedom and brand control in every frame. Perfect for marketing campaigns, product showcases, and storytelling videos, this format combines the power of your ideas with the precision of AI.
Here’s how it works:
  1. Select a Model – From the Generative AI Models section, choose a model tagged Text/Image to Video that matches your creative needs and preferred visual style.
  2. Add Your Assets – Upload your own image or select one from your Media Library, including brand assets, product visuals, or any reference image you want the AI to use as inspiration.
  3. Write Your Prompt – Describe the concept, mood, or motion you want in the video — the AI will interpret it to build visuals and scenes that align with your vision.
  4. Choose Video Settings – Before generating, customize key parameters such as format (landscape, portrait, or square), duration, and resolution. Available options vary based on the selected model’s capabilities.
  5. Generate with One Click – HeyOz’s AI then transforms your text and visuals into a complete, high-quality video built around your brand’s tone and style.
Once the video is generated, it opens in the HeyOz Video Editor, where you can:
  • Adjust duration, transitions, or effects
  • Update visuals, overlays, and captions
  • Add soundtracks or voiceovers
  • Export, download, or post directly to your connected social platforms
The Text/Image to Video Format is ideal for brands and creators who want to turn their ideas and visuals into dynamic, on-brand videos quickly, effortlessly, and powered by AI precision.