Use code

for 30% off your first plan.

AI Models
Video generation

Veo 3.1

Veo 3.1 is PixPilot's premium Veo 3 video workflow for cinematic text-to-video, image animation, first and last frame transitions, and reference-guided clips with synchronized audio.

Curated examples

Output Details

Model type

Text, image, frames, and references to video

Resolution

720p / 1080p

Duration

4 / 6 / 8 seconds

Aspect ratio

16:9 / 9:16

Audio

Optional native audio

Reference images

Up to 3; 16:9 and 8 seconds

Estimated time

About 90-240 seconds

Credits

115-460 by duration and audio

Key Features

Native audio

Generate synchronized dialogue, sound effects, music, and ambience directly with the video.

Reference-guided video

Use up to three uploaded reference images to preserve subjects, styling, and visual direction.

Frame-to-frame control

Provide a start image and optional end image to guide a controlled video transition.

Flexible short clips

Choose 4, 6, or 8 seconds at 720p or 1080p in landscape or portrait.

Best Uses

Cinematic campaign films

Turn a detailed creative brief into polished motion with sound and visual direction.

Character consistency

Use reference images when a product, character, or visual style must stay recognizable.

Controlled transitions

Guide the beginning and ending of a clip with uploaded frames.

FAQ

What can Veo 3.1 generate?

Use a text prompt, one uploaded image, a start and end frame, or up to three reference images depending on the motion workflow you need.

When can I use reference images?

Reference mode uses one to three images and requires a 16:9, 8-second clip. It is designed for stronger subject and style consistency.

How are Veo 3.1 credits calculated?

Credits depend on duration and whether audio is enabled. An 8-second 1080p clip with audio uses 460 credits.

Related Models

Workflows using Veo 3.1

Ready to try Veo 3.1?

Open the workspace and start creating with Veo 3.1.