AI creators tools

Vidu Q2 Reference-to-Video video model

Name: Vidu
Version: Q2
Variant: Reference-to-Video
Also Known As: Vidu Q2R2V
Creator: Vidu

Vidu Q2 Reference-to-Video was released on October the 22nd 2025. You can add sound effects, lip-synced voices, and tones that match the video (currently in Beta).

Vidu Q2 Models let you pick any length between 2 to 8 seconds.

They run faster, about 50% more speed, with better understanding of meaning and cheaper rates.

1080p videos can be extended more than once. You can also pick a final frame image to keep things steady.

Vidu Q2 Reference-to-Video Examples

Test with 2 images and speech/sound in text prompt. Resemblance is there, text on t-shirt and fabric quality - all preserved. But refuses to speak the full sentence, this is the 2nd attempt and same result. Generated on October 22, 2025
for link to original.
Multi-character dialogue + lip sync + prompt following is still very challenging. Used a single image as reference. Generated on October 22, 2025
for link to original.
Compare Models

Where To Find Vidu Q2 Reference-to-Video

If you'd like to access this model, you can explore the following possibilities:

Other Models by Vidu