Open Video Image To Video

Open Video Image To Video

Playground

OpenVideo Image to Video is a fast AI image-to-video generation model that creates short cinematic clips with native audio from a single reference image. It gives users full creative control over scene, style, and motion prompts, with support for 480p, 720p, and 1080p output and 3–20 second duration tiers. Ready-to-use REST inference API for cinematic clips, product videos, social media content, advertising creatives, visual storytelling, and professional image-to-video workflows with simple integration, no coldstarts, and affordable pricing.

Features

OpenVideo — Unlimited Image-to-Video (with Audio)

OpenVideo — Unlimited Image-to-Video (with Audio) generates short image-to-video clips with a synchronized native audio track. Upload a reference image, provide a prompt, choose the output resolution and duration, and generate an mp4 video with audio.

Why Choose This?

• Image-to-video with audio Generate short video clips with a synchronized audio track in a single workflow.

• Prompt-following generation The model follows the prompt directly for motion, scene, and overall output direction.

• Flexible resolution options Choose 480p, 720p, or 1080p depending on your quality and cost requirements.

• Short-form video generation Supports clip durations from 3 to 20 seconds.

• Simple workflow Start from a single reference image and a text prompt to generate a final mp4 output.

Parameters

How to Use

1. Upload your image — Provide a reference image in JPG or PNG format.
2. Write your prompt — Describe the motion and scene you want in the output video.
3. Choose output settings (optional) — Select resolution, duration, and seed as needed.
4. Submit — Generate the final video with audio.

Pricing

Billing Rules

• Minimum charge: 5 seconds. Requests shorter than 5 seconds are billed as 5 seconds.
• Maximum billed duration: 20 seconds.
• 720p costs 2x the 480p price.
• 1080p costs 3x the 480p price.
• Billing is based on max(5, min(duration, 20)).

Best Use Cases

• Short cinematic clips — Generate short video scenes with synchronized audio from a single reference image.
• Prompt-driven scene generation — Create motion, camera feel, and scene progression directly from a text prompt.
• Stylized visual content — Generate creative or stylized clips with audio in one pipeline.
• Social media content — Create short-form video content for quick publishing or iteration.
• Creative prototyping — Test scene ideas, motion directions, and visual concepts from one image.

Pro Tips

• Use a clear reference image with the main subject clearly visible.
• Keep the prompt focused on both the scene and the motion.
• Use 480p for faster and lower-cost testing.
• Use 720p or 1080p for higher-quality final outputs.
• Use a fixed seed if you want more reproducible generations.
• Avoid WEBP input images when possible.

Notes

• image and prompt are required fields.
• resolution, duration, and seed are optional.
• Default resolution is 480p.
• Default duration is 5.
• Default seed is -1, which uses a random seed.
• Audio is generated together with the video; no separate audio input is required.
• 480p is the fastest tier.
• Ensure uploaded image URLs are publicly accessible.
• By using this endpoint, you confirm that you have the right to generate the requested content under your jurisdiction.

# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/open-video/image-to-video" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "preset": "tuned",
    "resolution": "480p",
    "duration": 5,
    "seed": -1
}'

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