P-Video-2 Model - Pruna AI

New

text-to-video

Introducing
P-Video-2

Generate your video. Fast. Multimodal.
Premium video generation from text, images, and audio.

Get API access

See documentation

Documentation

p-video

p-video

p-video-2

p-video

p-video

p-video-2

Two Generation Modes

Generate videos from text, images, or audio in 720p or 1080p, with Draft for fast previews and Standard for final-quality output.

P-Video-2 Draft

From $0.015/s

Fast, lower-cost previews for testing prompts and creative directions.

P-Video-2 Standard

From $0.025/s

Higher-quality generation for final videos and production use.

P-Video-2 Draft

From $0.015/s

Fast, lower-cost previews for testing prompts and creative directions.

P-Video-2 Standard

From $0.025/s

Higher-quality generation for final videos and production use.

Retail

Media

p-video-2

text-to-video

Slow macro push-in, pendant catches moving light reflections, velvet texture stable, static tripod, luxury boutique atmosphere. Audio: subtle ambient piano, very quiet.

p-video-2

text-to-video

Subtle fashion editorial movement, slight playful movements, model maintains confident presence, natural breathing motion, gentle shoulder shift, soft micro head movement, static camera, premium ecommerce showcase, controlled minimal motion. Audio: minimal pop groove, no vocals.

Performance Benchmark: Efficiency & Quality

Pruna AI Optimizing Image &
Video generation models

P-Video-2 delivers quality on par with SoTA model.

To find more benchmarks check out P-Bench.

Price ($)

Latency (s)

Price ($)

Latency (s)

Price ($)

Latency (s)

Our Inference Providers

Acknowledgments

Standing on the Shoulders of Giants

The launch of P-Video is a milestone for real-time, high-quality video 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.