Google · video
Veo 3.1 Reference
Veo 3.1 from up to 3 reference images: 8-second shots with native dialogue and sound, up to 4K.
- Length
- 8 s
- Resolution
- 720p, 1080p, 4K
- Aspect ratio
- 16:9, 9:16
- References
- Up to 3 image files
About Veo 3.1 Reference
Veo 3.1 Reference is the reference mode of Google's Veo 3.1, priced at $4.00 per generation. Instead of a start frame it takes up to 3 images of a subject and keeps that subject's appearance consistent in a new shot, with dialogue and sound generated together with the picture.
The length is fixed at 8 seconds. You choose the resolution (720p, 1080p and 4K), the shape (16:9 and 9:16) and whether audio is on; switching audio off lowers the price, $4.00 instead of $8.00 at 720p. A typical generation takes about 2 min.
Good for
- Keeping a person, product or character looking the same, from up to 3 pictures of it
- Dialogue shots where the speaker has to match your photos
Getting good results
- Upload pictures of the subject, not of the scene: the images set how the subject looks, the prompt sets what happens.
- Every clip lasts 8 seconds, so only resolution and audio move the price, from $4.00 up to $12.00 at 4K with sound.
Veo 3.1 Reference questions
How is Veo 3.1 Reference different from Veo 3.1?
Veo 3.1 uses your image as the first frame, or a start and an end image, with a length you choose. Veo 3.1 Reference takes up to 3 images as references for the subject's appearance and always makes 8 seconds. Both are charged at the same per-second rates.
How much does a Veo 3.1 Reference clip cost?
The length is fixed, so the price is per clip: $8.00 at 720p with audio, $4.00 without it, and $12.00 at 4K with audio.