FLUX 3 Max Text-to-Video Prompt Formula Card

In the form of a "prompt formula card," this turns the structured approach to FLUX 3 Max text-to-video prompting into a visual guide that can be played straight through. The visuals use infographic-style cards stacked layer by layer: subject and action, shot size and camera position, camera movement, lighting and color, rhythm and mood—each layer corresponds to a line of short text on a card, ultimately composing a complete reusable prompt. The entire video is generated by the author's own FLUX 3 Max text-to-video, with inputs limited to the schema-declared fields prompt, duration, resolution, aspect_ratio, generate_audio, and reasoning_level, and no reference images or reference videos, so it serves as an end-to-end example of pure text to finished footage. It is suitable for developers and creators to quickly understand how text-to-video prompts are organized, and also works as material for showing a team "how structured prompts influence visual rhythm and camera movement." Family documentation indicates that this model has been post-trained for prompt adherence and optimized for low-latency inference, making it well suited for iterating on short clips like this that require clear cinematic language and visual hierarchy.