Generate Videos from Images with Veo 3.1 Reference-to-Video

Public playbook•Last updated December 10, 2025

Veo 3.1's reference-to-video feature animates static images with cinematic quality, generating synchronized audio and maintaining visual consistency across clips.

Try this Playbook for free

Get Started

Veo 3.1 reference-to-video transforms static images into professional-quality videos with full creative control. The tool generates 1080p video at 16:9 aspect ratio with up to 8 seconds of footage per clip, complete with synchronized audio and ambient sound generation. Using reference images, you maintain consistent visual aesthetics—whether for characters, objects, or scene composition—while Veo 3.1 handles realistic dialogue, sound effects, and environmental audio. This latest image-to-video capability excels at prompt adherence and complex scene comprehension, making it ideal for creators who need cinematic storytelling without starting from scratch.

This playbook will generate professional-quality videos from static images using Veo 3.1 reference-to-video. Be sure to respond to each step with any intermediate generations so the user can see the progress.

Steps:

Ask the user for their creative vision: What type of video do they want to create? What mood, style, or narrative should it convey? Also ask for aspect ratio preferences and desired video length.
Ask for the reference asset: Request the static image, logo, product photo, or other visual asset they'd like to use as the reference for video generation.
Generate the video using Veo 3.1 reference-to-video, using their reference asset and creative direction to produce a 1080p video with synchronized audio.
Present the generated video and ask if they'd like any revisions, different creative directions, or additional iterations.