Text-to-image generation. This technique uses natural language prompts to generate images from scratch using AI models like Stable Diffusion or DALL·E.

Image-to-image transformation. This technique modifies an existing image based on a prompt or style, preserving composition while changing content or quality.

AI-based image editing. It allows the user to erase or mask parts of an image and regenerate them using a prompt, often used for fixing or modifying specific regions.

A structured process of using multiple AI tools or steps (e.g., txt2img → img2img → upscaling) to refine and generate images systematically.

Video-to-video synthesis. This technique transforms an existing video into a new one, often stylizing or altering it using AI.

Text-to-video generation. It generates video clips from text prompts using models like Sora or Runway.

Image-to-video animation. It takes still images and animates them into moving content, often with inferred motion or transitions based on context.

A powerful extension for AI models that allows control over image generation using poses, depth maps, edges, etc., to ensure structural accuracy and consistency.