Pruna AI family
# P Video High-performance generative video for creative marketing ## Overview P Video is a versatile, high-speed AI model designed to bridge the gap between rapid creative iteration and high-quality video production. By integrating text-to-video, image-to-video, and audio-to-video capabilities into a single, unified endpoint, P Video allows marketing teams to generate professional-grade assets without the overhead of traditional rendering pipelines. What makes P Video distinct is its native support for a 'draft mode,' which facilitates lightning-fast previews for storyboarding and concept testing. Whether you are looking to animate static brand assets or generate cinematic sequences from descriptive prompts, P Video provides the control necessary to maintain visual consistency across campaigns. Its architecture is optimized for both creative flexibility and analytical precision, making it an essential tool for modern ad agencies. ## Use Cases * **Social Media Ad Variations:** Rapidly generate multiple aspect ratio versions of a video campaign for Instagram Reels, TikTok, and YouTube Shorts. * **Static-to-Motion Conversion:** Animate product photography or brand key visuals to create engaging, high-conversion display ads. * **Audio-Driven Storytelling:** Sync video generation to brand voiceovers or background music tracks for immersive video content. * **Rapid Storyboarding:** Use the draft mode to quickly visualize campaign concepts for client approval before committing to high-resolution final renders. * **Dynamic B-Roll Creation:** Generate custom, high-quality background footage that aligns perfectly with specific brand color palettes and themes. * **Last-Frame Continuity:** Use the last-frame reference feature to create seamless, continuous video loops for long-form brand storytelling. ## Parameters P Video offers a robust set of configuration options to fine-tune your output. Please refer to the Input Parameters section in the Pixloop dashboard to manage settings such as frame rate, resolution, aspect ratio, and safety filter toggles. ## Tips for Best Results * **Leverage Draft Mode:** Always start with `draft: true` to validate your prompt and composition before committing to a full-resolution render. * **Use Prompt Upsampling:** Keep `prompt_upsampling` enabled to allow the model to interpret and expand upon your creative intent, resulting in more detailed and visually cohesive outputs. * **Optimize for Platform:** Select the appropriate `aspect_ratio` (e.g., 9:16 for mobile, 16:9 for desktop) early in the process to avoid cropping issues later. * **Control Consistency:** When generating multiple clips for a single campaign, use the `seed` parameter to maintain visual consistency across different generations. * **Audio-Video Sync:** When using the `audio` input, ensure your audio file is clean and clear, as the model uses the audio frequency and rhythm to guide the motion dynamics of the video. ## About P Video is provided by prunaai and hosted via the Replicate platform. Built on a high-performance generative architecture, it is designed to support the demanding workflows of creative professionals. The model is maintained under Cog version 0.16.12, ensuring stability and compatibility with modern AI infrastructure requirements.
Model input reference derived from preset schema.
| Name | Type | Required | Default | Description |
|---|---|---|---|---|
| fps | select | No | 24 | Frames per second of the video. |
| seed | integer | No | null | Random seed. Set for reproducible generation. |
| audio | audio | No | null | Input audio to condition video generation. Supports flac, mp3, wav. |
| draft | boolean | No | true | Draft mode. Generates a lower-quality preview of the video. |
| image | image | No | null | Input image to generate video from (image-to-video). Supports jpg, jpeg, png, webp. |
| no_op | boolean | No | false | Health check mode - returns status without inference. |
| prompt | string | Yes | null | Text prompt for video generation. |
| duration | integer | No | 5 | Duration of the video in seconds (1-20). Ignored when audio is provided. |
| resolution | select | No | "720p" | Resolution of the video. |
| save_audio | boolean | No | true | Save the video with audio. |
| aspect_ratio | select | No | "16:9" | Aspect ratio of the video. Ignored when an input image is provided. |
| last_frame_image | image | No | null | Reference image for the last frame of the video. Supports jpg, jpeg, png, webp. |
| prompt_upsampling | boolean | No | true | Use prompt upsampling to enhance the prompt. |
| disable_safety_filter | boolean | No | true | Disable safety filter for prompts (and input image). When disabled, prompts are not checked for unsafe content before generation. |