Fast text-to-video generation with 1-20 second durations, 720p and 1080p output, optional audio, and common aspect ratios.
Added May 12, 2026
Approx. Price
$0.100 per video
Model Type
text-to-video
Settings
Generation controls available for this model.
Output Format
Default Duration
5
20 duration options
Aspect Ratio
Default
16:9
Options (7)
Landscape (16:9), Portrait (9:16), Classic (4:3), Portrait Classic (3:4) +3 more
Output aspect ratio
Duration
Default
5
Options (20)
1 seconds, 2 seconds, 3 seconds, 4 seconds +16 more
Video duration in seconds
Resolution
Default
720p
Options (2)
720p, 1080p
Output video resolution
Save Audio
Default
Yes
Save the generated video with audio
Seed
Default
-1
Control reproducibility (-1 for random)
Benchmarks
Benchmarks
Human preference benchmarks sourced from Artificial Analysis.
Text to Video
#52 / 78
ELO
1062.0
Appearances
6,508
95% CI
-8/8
Image to Video
#58 / 72
ELO
1123.0
Appearances
6,032
95% CI
-10/10
Release Date 2026-02 · Matched as P-Video
Artificial Analysis APIExamples
Loading examples…
Related video models
Compare P-Video with similar models from the same provider or model family.
P-Video Animate
pruna-ai/p-video/animateMotion-control video generation that animates a reference image using movement from a source video, with optional prompt guidance, audio preservation, frame-rate control, and 720p or 1080p output.
P-Video Avatar
pruna-ai/p-video/avatarImage-and-audio avatar video generation for speech-driven talking-head clips, with 720p and 1080p output.
P-Video Image-to-Video
pruna-ai/p-video/image-to-videoFast image-to-video generation with 1-20 second durations, 720p and 1080p output, and optional audio.
Gemini Omni Flash 1.1
google/gemini-omni-flash/v1.1Google’s multimodal video model for text-to-video, image animation with optional end frames, multimodal reference generation, and instruction-based video editing. Generates synchronized native audio at resolutions from 360p through 4K.
MiniMax H3 Max
minimax/h3-maxMiniMax H3 Max generates 5–15 second videos at 480p or 768p from a text prompt or a first-frame image, with optional first/last-frame transitions.
Wan 3.0 Prime
alibaba/wan-3.0-primeAccelerated Wan 3.0 video generation in one model. Automatically routes text, first/last-frame images, or multimodal image, video, and audio references to the matching Prime endpoint.