video_generate.vidu_q3_pro_i2v_novita
vidu/vidu-q3-pro/image-to-video

The Vidu Q3 Pro API animates a single input image from an optional text prompt — clips up to 16 seconds, up to 1080p, five aspect ratios (16:9/9:16/4:3/3:4/1:1), general or anime style, an attachable audio track and a reproducible seed, via one OpenAI-compatible REST endpoint 15% below official.

Input
The text prompt sent to the model
Output
Sample edited image — run the model to replace this previewSampleRun the model to replace this preview

Vidu Q3 Pro API: Image-to-Video

Use the Vidu Q3 Pro API to animate a still image into a clip from an optional prompt: 1080p, 16 seconds, five aspect ratios.

The Vidu Q3 Pro API (video_generate.vidu_q3_pro_i2v_novita) turns a single still image into a moving video from an optional prompt: pass one image URL in image_urls, describe the motion, and the Vidu Q3 Pro API animates that frame while honoring its composition, lighting, and subject. Duration runs 1 to 16 seconds -- the longest in the Vidu i2v family -- resolution scales up to 1080p, and aspect_ratio covers five ratios: 16:9, 9:16, 4:3, 3:4, and 1:1. A style toggle renders general or anime output, and a seed makes the Vidu Q3 Pro API reproducible.

Pricing on the Vidu Q3 Pro API is $0.425 per generation -- 15% below the official rate of $0.500. It runs on one RouterBase key with the same JSON shape across 200+ models, and because the Vidu Q3 Pro API is async and OpenAI-compatible you POST /v1/images/generations with model=video_generate.vidu_q3_pro_i2v_novita, one image URL, and an optional prompt, then poll GET /v1/images/generations/{id} until status=success and pull each clip from a signed CDN URL. Teams reach for the Vidu Q3 Pro API when a still exists and they want motion without a reshoot.

Why this model

Six reasons teams ship on the Vidu Q3 Pro API

From one still image to 16-second 1080p output — what the Vidu Q3 Pro API gets right.

Animate one still image

Supply one image URL and the Vidu Q3 Pro API animates that frame from an optional prompt — the hero shot moves while its composition and lighting stay intact.

Up to 16-second duration

Set any duration from 1 to 16 seconds — the longest in the Vidu i2v line. The Vidu Q3 Pro API lets one render fit a short loop or a full sixteen-second story.

Five aspect ratios

Pick 16:9, 9:16, 4:3, 3:4, or 1:1 per call. The Vidu Q3 Pro API turns one source image into landscape, vertical, and square cuts covering every placement.

General or anime style

Flip the style toggle between general and anime in one request. The Vidu Q3 Pro API gives the same source image a photoreal or stylized anime look on demand.

Attach an audio track

Pass an optional audio URL and the Vidu Q3 Pro API mixes that soundtrack into the finished clip — motion and sound land together.

Up to 1080p, 15% off

Render at 540p, 720p, or 1080p at $0.425/generation — 15% below the official rate. The Vidu Q3 Pro API uses the same JSON shape as every RouterBase model; switching is only a model ID change.

RouterBase dashboard preview
Quickstart

Get started with the Vidu Q3 Pro API in 3 steps

From sign-up to your first image-to-video call in under 5 minutes.

  1. Pick your source image

    Host one clean, well-lit image at a public URL and put it in image_urls — the Vidu Q3 Pro API animates exactly this frame, so a sharp source sharpens the result. Choose an aspect_ratio for your placement.

  2. POST to the Vidu Q3 Pro API endpoint

    Send image_urls plus optional prompt, duration, resolution, aspect_ratio, style, audio, and seed to POST /v1/images/generations. The Vidu Q3 Pro API returns an async job id; poll GET /v1/images/generations/{id} until status=success.

  3. Poll and download the clip

    The success response from the Vidu Q3 Pro API contains a signed CDN URL in the results array. Drop it into a <video> tag or copy it to your bucket — ready with no post-processing.

Pricing

Pay only for what you use

RouterBase passes through partner-tier pricing. Compared against the model's official published API rate.

ResolutionRouterBaseOfficialSave
540p 5s$0.191$0.225−15%
720p 5s$0.425$0.500−15%
1080p 5s$0.510$0.600−15%

About $0.085 per second.One run at the default settings (720p) costs $0.425.With $1 you can run this model approximately 2 times.

Customer stories

What teams build with the Vidu Q3 Pro API

Real production loads running on the Vidu Q3 Pro API and the RouterBase catalog.

Marcus Reyes
Marcus ReyesCTO, Paradigm AI

We fed a product still into the Vidu Q3 Pro API and it moved on-brand at 1080p. The sixteen-second reach lets one render tell a whole story.

Priya Lakshmi
Priya LakshmiFounder, Quillo

One image, one prompt, a 9:16 clip — we turn a photo into a post in minutes, and the Vidu Q3 Pro API gives us square and landscape cuts from the same source.

Thomas Beck
Thomas BeckStaff Engineer, Northbeam

Variable 1-16s duration means no more stitching. The Vidu Q3 Pro API gives us exactly the length we ask for.

Aoi Tanaka
Aoi TanakaML Lead, Daybreak Robotics

We batch our catalog overnight on the Vidu Q3 Pro API at 1080p across five aspect ratios. Every still ships in every placement by morning.

Jonas Keller
Jonas KellerIndie Developer

The anime style toggle was the surprise. I passed one photo to the Vidu Q3 Pro API and got a stylized short with an audio track in a single call.

Ethan Nguyen
Ethan NguyenHead of Engineering, Compound Studio

RouterBase puts 200+ models behind one key. We made the Vidu Q3 Pro API our default for turning stills into motion.

Sophia MartinCTO, Relay

At $0.425 per clip the Vidu Q3 Pro API fits our ad budget, and five aspect ratios mean one image covers every feed.

Lucas Fernandes
Lucas FernandesEngineering Manager, Light

Same JSON shape, different model ID. Adding the Vidu Q3 Pro API was the easiest change in our rollout.

David Okonkwo
David OkonkwoCo-founder, Figment

15% off adds up fast when the Vidu Q3 Pro API generates thousands of image-to-video clips per week.

Frequently Asked Questions

Common questions about the Vidu Q3 Pro API image-to-video task.

The Vidu Q3 Pro API image-to-video task animates a single still image into a video from an optional text prompt. It is the right choice when you have a hero image and want motion without a reshoot.