Veo 3.1 Lite Image-to-Video Prompt Formula Card
Using Veo 3.1 Lite's image-to-video capability as the subject, create a visual guide in the style of a "prompt formula card": the static card image breaks down the structured writing approach (subject and action, camera language, lighting atmosphere, rhythm and duration), then this card image is used as the input image to generate a short dynamic video via the author's pipeline, letting the formula demonstrate itself on screen. The input structure corresponds to the schema: image_url is a 16:9 card image generated by the pipeline; the top-level prompt is submitted as the animation instruction, and base provides a duration of 6 seconds, 720p, 16:9, native audio enabled, default safety tolerance, and one negative_prompt. All media comes from generated assets; no external addresses are referenced. Use cases: developers quickly understanding the prompt structure of image-to-video; teams sharing prompt-writing paradigms internally; serving as a low-cost, high-throughput batch generation example reference. Veo 3.1 Lite supports text-to-video and image-to-video, 16:9 and 9:16 aspect ratios, 720p and 1080p resolutions, and 4s/6s/8s durations; output videos include audio, making it suitable for this kind of rapidly iterated example content.
Style Prompt Engineering · Developer Education · Image-to-Video
Model Veo 3.1 Lite
Reference inputs

Input image
Prompt
Turn the provided prompt formula card into a clean motion-graphics explainer video: the camera holds a fixed position with a slow push-in and subtle parallax; the four formula blocks (subject and action, camera language, lighting and atmosphere, rhythm and duration) light up in sequence, with thin connecting lines drawn between them; small icons ease into place with easing animations, the text stays crisp and legible, and a soft vignette gently pulses. Lighting is even, cool neutral studio white, with a warm accent light sweeping across the card. The mood is precise and instructional, the pacing calm and easy to follow, with no camera shake, no text distortion, and no flicker. 16:9, 720p, 6 seconds, native ambient audio of soft clicks and a low hum.
Copy the full prompt and adapt it for your own generation.
Tags