Text-to-Image
Generating an image directly from a written description. You type a prompt, the model (usually a diffusion model) turns it into pixels in seconds. It is the foundational GenAI skill: subject, style, lighting, and composition all come from your words, so prompt quality directly controls output quality. Modern models like Imagen 3 and NanoBanana handle long, detailed prompts and even render readable text inside images. Example: 'product photo of a matte black water bottle on wet slate, soft studio lighting, 4k' produces a usable e-commerce shot on the first try.