JSON Prompting For AI Image & Video
How to make incredibly detailed and structured prompts for AI image and video generators using the JSON prompting method.
JSON prompting for AI image and video generators involves structuring detailed scene descriptions, camera directions, character actions, and style preferences in a machine-readable JSON format to guide the AI in generating precise visual outputs. Each key-value pair in the JSON defines specific aspects - such as environment, lighting, motion, duration, or objects - to reduce ambiguity and improve consistency across outputs. This format allows for more granular control compared to plain text prompts, making it ideal for generating complex scenes, animations, or multi-step sequences with accurate timing and transitions.
The method
Watch the video to see how simple it is to have ChatGPT or other LLM create detailed JSON prompts. You can do this with just a simple description, or add more details as to what you want to see in your output. You can then copy and paste into any image or video generator. In the example, we're using Google Veo 3.
The prompts
You must make me a JSON prompt for an AI video generator. The JSON will help the video generator produce a video that more accurately represents what I am looking for. The whole video should be around 10 seconds long. Here is what I want to see in the video: ["A man covers his face with mustard"]
