Glossary · Getting Started
Quick answer
A prompt is the text instruction you give an AI model to tell it what to create. In AI video and image generation, the prompt describes the subject, action, setting, style, and camera work you want — for example, "handheld close-up of a barista pouring latte art, warm morning light, shallow depth of field." More specific prompts produce more predictable results.
Prompts are the primary creative control in generative AI. The model interprets your words against everything it learned in training, so word choice matters: "cinematic drone shot" and "shaky phone video" steer the same scene toward very different outputs.
A useful mental model is to write a prompt like a shot description in a film script: who or what is in frame, what they are doing, where, in what light, and how the camera moves.
VdoBloom’s template gallery is a fast way to learn prompting — every template publishes its full prompt text, so you can study what works and adapt it.
VdoBloom starts you with 10 free credits — enough to put this into practice with no card required.
Open Text to Video tool