Basic Capabilities
Documentation page
Basic Capabilities
⏳Reading time: 2mins
Cast your AI spells and discover your own ways to create.
Text Capabilities
- Text to Text: Generate ideas, scripts, and more.
- Text to Image: For example, type “give me a picture of a cat” to instantly get the image.
- Text to Video: For example, type “create a video of a woman drinking coffee” to instantly generate the video.
Image Capabilities
- Image to Text: Summarize or describe an image.
- Single Image Edit: Use our Image Editor or Toolbar to edit single image
- Image to Image (Multi-Image): Upload multiple images as references (e.g., style, scene) to generate new visuals from a text prompt.
- Image to Video (Single Frame): Use an uploaded image as the first frame to generate a video from text.
- Image to Video (Two Frames): Use two uploaded images as the start and end frames to generate a video that fills in the motion in between.
Video Capabilities
- Video to Text: Analyze and summarize video editing techniques.
- Video to Video: Extend or enhance videos with one click