Kandinsky5 Pro Image To Video

Kandinsky5 Pro Image To Video

Playground

Kandinsky 5 Pro Image-to-Video turns a single image into a coherent 5-second video guided by a natural-language prompt. It preserves subject and composition while adding smooth motion and cinematic dynamics. Output at 512p or 1024p in common aspect ratios for social posts, ads, and concept previews. Built for stable production use with a ready-to-use REST API, no cold starts, and predictable pricing.

Features

Kandinsky 5 Pro Image-to-Video

Kandinsky 5 Pro Image-to-Video turns a single image + text prompt into a 5-second MP4 video, adding natural motion and cinematic camera behavior while keeping the original composition anchored to your input frame. It’s built for fast iteration on short-form clips—ideal for ads, story beats, and social content.

Key Features

• Image-to-Video animation (5s) Animate a static image into a short, coherent video clip.

• Prompt-guided motion & camera Use text to direct what moves, how it moves, and how the camera behaves.

• Resolution options Choose 512p for faster drafts or 1024p for sharper, higher-detail outputs.

• Production-friendly output Returns an MP4 clip ready for publishing or post-production.

Parameters

How to use

1. Upload or paste your image URL into image_url (make sure it’s publicly accessible).

2. Write a prompt that describes:

   • the subject and setting,
   • the motion (clear verbs),
   • the camera behavior (e.g., “slow dolly-in”, “subtle handheld”),
   • the visual style (optional).

3. Select resolution:

   • 512p for quick previews,
   • 1024p for final quality.

4. Click Run to generate a 5-second MP4.

Prompt tips (works best)

• Keep grammar simple and direct.
• Prefer a “single-shot” instruction rather than multiple scene changes.
• Use explicit motion verbs: “turns”, “walks”, “breathes”, “waves”, “camera pushes in”.
• If you want a calmer clip, specify “subtle motion” or “minimal movement”.

Pricing

Based on your rate setup (512p baseline; 1024p uses a 3× resolution multiplier):

Billing note: Duration is currently fixed at 5 seconds for this endpoint.

Use Cases

• Character animation and story beats from key art
• Product hero shots with subtle motion and camera moves
• Social media short clips from posters or stills
• Marketing creatives and quick concept previews

# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/kandinsky5-pro/image-to-video" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "resolution": "512p",
    "duration": 5
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"