PrunaAI/p-video
Real-time AI video generation from text, images, and audio. Supports up to 1080p at 48 FPS with built-in audio generation, draft mode for 4x faster previews, and prompt upsampling.
Try the model with a sample request using the same API shape shown in the reference page.
Generate a lower-quality draft at reduced cost. 720p draft is $0.005/s vs $0.02/s; 1080p draft is $0.01/s vs $0.04/s.
Whether to preserve audio from the input when doing image-to-video generation.
Whether to automatically enhance the prompt for better results.
Duration of the generated video in seconds (1-10). Ignored when audio is provided. (Default: empty, 1 ≤ duration ≤ 10)
URL of an audio file to condition the video on. When provided, the duration parameter is ignored.. (Default: empty)
Frames per second of the generated video.
Aspect ratio of the generated video.
URL of an input image to use as the first frame for image-to-video generation.. (Default: empty)
Resolution of the generated video. Defaults to 720p.
Text prompt describing the image
Random seed for reproducible generation. (Default: empty)
Adjust settings and run the demo to see the model output generated here in real-time.
