P-Video Model - Pruna AI

New

image-to-video

Introducing P-Video

Introducing
P-Video

Fast. Affordable. Beautiful.
State-of-the-art AI Video in seconds.

Video

Audio

Get API access

See documentation

Documentation

p-video

p-video

p-video

p-video

Key Value Proposition

Ultra fast and controllable video generation.

Performance

High quality video generation in less than 10s.

Multi-modal

Text, image, and audio input
Up to 15s video w/ or w/o audio.

Aesthetic

Accurate and realistic video generations.

Control

Preview video generations in a couple of seconds.

Social ads

Product

Avatars

Music Videos

p-video

image-to-video

The woman in the photo moves naturally. She says: "Find the house that's perfect for you, and your family".

p-video

image-to-video

The camera pans from left to right. A heavy, deep male voice says: "Motorcycles! Faster than ever before!"

Social ads

Product

Avatars

Music Videos

p-video

image-to-video

The woman in the photo moves naturally. She says: "Find the house that's perfect for you, and your family".

p-video

image-to-video

The camera pans from left to right. A heavy, deep male voice says: "Motorcycles! Faster than ever before!"

p-video

image-to-video

The man say: "You! Join the fight!" and he points to the screen.

Social ads

Product

Avatars

Music Videos

p-video

image-to-video

The woman in the photo moves naturally. She says: "Find the house that's perfect for you, and your family".

p-video

image-to-video

The camera pans from left to right. A heavy, deep male voice says: "Motorcycles! Faster than ever before!"

Try it now

Prompting Guideline

Fundamental techniques for prompting P-video.

Fundamental techniques for prompting
P-video.

Basic

Image Ref

[Subject]

[Action]

[Scene]

[Camera]

[Lighting]

[Style]

[Audio]

Knitted purple prune character,

reading an open book,

sitting on warm wooden floor in cozy room,

static

camera,

warm natural light from window,

documentary-style realism,

character reading aloud:

“[Spoken Text]”

Basic

Image Ref

[Subject]

[Action]

[Scene]

[Camera]

[Lighting]

[Style]

[Audio]

Knitted purple prune character,

reading an open book,

sitting on warm wooden floor in cozy room,

static

camera,

warm natural light from window,

documentary-style realism,

character reading aloud:

“[Spoken Text]”

Advanced

Image Ref

[Subject]

[Action]

[Scene]

[Camera]

[Lighting]

[Style]

[Audio]

Knitted purple prune character with large white eyes,

a friendly moving mouth and green stem, reading a book,

and then look directly at the camera,

cozy room with wooden

floor and window,

the camera is slowly zooming in,

warm natural light from the window,

documentary-style

realism,

character reading aloud: “[Spoken Text]”

Advanced

Image Ref

[Subject]

[Action]

[Scene]

[Camera]

[Lighting]

[Style]

[Audio]

Knitted purple prune character with large white eyes,

a friendly moving mouth and green stem, reading a book,

and then look directly at the camera,

cozy room with wooden

floor and window,

the camera is slowly zooming in,

warm natural light from the window,

documentary-style

realism,

character reading aloud: “[Spoken Text]”

Basic

Image Ref

[Subject]

[Action]

[Scene]

[Camera]

[Lighting]

[Style]

[Audio]

Knitted purple prune character,

reading an open book,

sitting on warm wooden floor in cozy room,

static

camera,

warm natural light from window,

documentary-style realism,

character reading aloud:

“[Spoken Text]”

Advanced

Image Ref

[Subject]

[Action]

[Scene]

[Camera]

[Lighting]

[Style]

[Audio]

Knitted purple prune character with large white eyes,

a friendly moving mouth and green stem, reading a book,

and then look directly at the camera,

cozy room with wooden

floor and window,

the camera is slowly zooming in,

warm natural light from the window,

documentary-style

realism,

character reading aloud: “[Spoken Text]”

Performance Benchmark: Efficiency & Quality

P-Video is the most efficient model for high quality video generation.

Latency (s)

Price ($)

Latency (s)

Price ($)

Latency (s)

Price ($)

Our Inference Providers

Acknowledgments

Standing on the Shoulders of Giants

The launch of P-Video is a milestone for real-time, high-quality image generation.
But it is not a journey we took alone. We want to acknowledge the teams whose work defined the state-of-the-art for visual generation, introduced the proper techniques, and set the high bar for quality that we aimed to match including

Black Forest Labs for their work on the Flux series,
Alibaba for their work on Qwen Image, Qwen Image Edit, Z-Image, and Wan Video,
Lightricks for their work on LTX,
Hugging Face for their work on Diffusers and Transformers,
the Open source community the fantastic job on countless open models, open packages, and open research.