VEO 3.1 I2V

Veo 3.1 image to video is Google DeepMind's animation mode, transforming a single still image or a pair of start and end frames into a short cinematic clip. The system preserves subject identity, style, and environment from the input image while introducing motion, camera transitions, lighting shifts, and synchronized audio that can include ambience, music, and dialogue. Output lands at native 1080p with stereo audio at 48 kHz and 192 kbps AAC encoding. Aspect ratios include 16:9 and 9:16, and creative controls support Ingredients to Video for multi image guidance and Frames to Video for morphing between two key frames. It is optimized for prompt accuracy and tight visual and audio coherence across the full clip.

October 15, 2025

Google

Image to Video (I2V)