What can I create with P-Video-2 Pro?

P-Video-2 Pro is suited for cinematic clips, social video concepts, product visuals, and motion tests from text or image references. On each::labs, creators can choose duration, resolution, aspect ratio, and generation mode for short AI video workflows.

How is this video generator configured?

This Pruna model supports 480p and 768p output, 5 to 15 second durations, speed or quality mode, and generated audio in the returned video. Prompt upsampling is configurable, and reference images can define the first frame, last frame, or both.

Example inputhover

mode: "quality"
image
prompt: "Photoreal fashion product film, 8 seconds. Hero: an unstructured red wool overcoat with black buttons, no labels, hanging on a simple wooden hanger in a white studio. Slow push-in, then a slight orbit so the lapel, buttons and wool texture stay readable. Soft daylight. No people, no captions. Audio: quiet studio, a faint fabric rustle from air, no music, no voiceover."
duration: 8
resolution: "768p"
aspect_ratio: "16:9"
prompt_upsampler: "turbo"

Pruna | P-Video 2 Pro

Image Gen·P-video·by Pruna AI

P-Video-2 Pro generates AI video from prompts and optional first or last frames, with 480p/768p quality modes for cinematic clips with audio.

Try it now →

API reference

Runtime (p50): 20s
Estimated price: $0.01–$0.075 per second, depending on mode and resolution

Call the API

prediction.sh

curl -X POST \
  -H "Authorization: Bearer $EACHLABS_API_KEY" \
  -H "Content-Type: application/json" \
  --data '{
    "model": "p-video-2-pro",
    "input": {
        "mode": "quality",
        "image": "https://cdn-us.eachlabs.ai/defaults/e0da62aaadf14ec69bdcdc5aacbcbdb1.png",
        "prompt": "Photoreal fashion product film, 8 seconds. Hero: an unstructured red wool overcoat with black buttons, no labels, hanging on a simple wooden hanger in a white studio. Slow push-in, then a slight orbit so the lapel, buttons and wool texture stay readable. Soft daylight. No people, no captions. Audio: quiet studio, a faint fabric rustle from air, no music, no voiceover.",
        "duration": 8,
        "resolution": "768p",
        "aspect_ratio": "16:9",
        "prompt_upsampler": "turbo"
    },
    "webhook_url": ""
}' \
  https://api.eachlabs.ai/v1/prediction/

Related models

4 models

Alibaba | Wan | 3.0 | Image to Video AI model preview

Alibaba | Wan | 3.0 | Image to VideoAlibaba

Storm Trend EffectUnified AI API for hundreds models. Access video, image, and audio generation from leading providers through one integration with eachlabs.

Alibaba | Wan | 3.0 | Prime | Image to Video AI model preview

Alibaba | Wan | 3.0 | Prime | Image to VideoAlibaba

Alibaba | Wan | 3.0 | Prime | Reference to Video AI model preview

Alibaba | Wan | 3.0 | Prime | Reference to VideoAlibaba

* FAQ

About Pruna | P-Video 2 Pro

01 / 03

What is P-Video-2 Pro text-to-video?

P-Video-2 Pro is a Pruna video generation model that creates short AI video from a written prompt. It also accepts optional first-frame and last-frame images, so creators can guide the opening or ending composition while keeping the prompt as the main direction.