'%3e%3c/path%3e%3cdefs%3e%3clinearGradient%20gradientUnits='userSpaceOnUse'%20id='lobe-icons-vidu-_R_0_'%20x1='.759'%20x2='26.155'%20y1='5.637'%20y2='17.311'%3e%3cstop%20stop-color='%2340EDD8'%3e%3c/stop%3e%3cstop%20offset='.024'%20stop-color='%2338E7E2'%3e%3c/stop%3e%3cstop%20offset='.084'%20stop-color='%2328DAF7'%3e%3c/stop%3e%3cstop%20offset='.124'%20stop-color='%2322D5FF'%3e%3c/stop%3e%3cstop%20offset='.36'%20stop-color='%231ABFFF'%3e%3c/stop%3e%3cstop%20offset='.85'%20stop-color='%230786FE'%3e%3c/stop%3e%3cstop%20offset='.909'%20stop-color='%23047FFE'%3e%3c/stop%3e%3c/linearGradient%3e%3c/defs%3e%3c/svg%3e)
We plugged reference images into the Vidu Q1 API and our avatar kept its face across every clip. Consistency we could never get before.
The Vidu Q1 API generates a 5-second 1080p video from reference images and an optional natural-language prompt (Vidu Q1) — preserving identity and character consistency across frames, adjustable motion amplitude (auto / small / medium / large), optional background music, reproducible seed, and a single OpenAI-compatible REST endpoint, 15% below the official rate.
Input
The text prompt sent to the model
Output
SampleRun the model to replace this previewVidu Q1 API: Reference-to-Video
Use the Vidu Q1 API to generate consistent 5-second 1080p clips from reference images of your subject.
The Vidu Q1 API (video_generate.vidu_q1_r2v_novita) generates 5-second 1080p video clips from reference images and an optional natural-language prompt. Each Vidu Q1 API call locks the identity and appearance of your subject using the supplied reference images, producing a temporally consistent output with adjustable motion amplitude — auto, small, medium, or large — and optional background music, all through a single OpenAI-compatible REST call on the Vidu Q1 API. The Vidu Q1 API is built for character-driven work — an avatar, a mascot, or a game hero — where the same face and outfit must survive every frame, and the Vidu Q1 API reads the reference set to lock identity before rendering.
Pricing on the Vidu Q1 API is $0.34 per generation — 15% below the published rate. The Vidu Q1 API uses one RouterBase key; no Vidu-specific SDK or separate account is required. Because the Vidu Q1 API is async and OpenAI-compatible, you can queue reference-to-video jobs beside your other generations, batch a whole cast overnight, and pull finished clips from one CDN URL.
Six reasons teams ship on the Vidu Q1 API
From reference-image consistency to per-call motion control — what the Vidu Q1 API gets right.
Identity consistency
Supply reference images and the Vidu Q1 API preserves the face, outfit, and proportions across every frame of the 5-second 1080p clip, so a character stays on-model from shot to shot.
5-second 1080p clips
Every Vidu Q1 API call produces a 5-second 1080p video — the fixed duration removes encoding guesswork and keeps cost and storage predictable across a batch.
Motion amplitude control
Pass auto, small, medium, or large per call. Small keeps a portrait steady, large drives action, and auto lets the Vidu Q1 API pick the movement from the scene.
Optional background music
Set bgm=true and the Vidu Q1 API scores the clip with a fitting track; omit the flag for a silent output you can pair with your own audio.
$0.34 / generation
15% below the published rate on the Vidu Q1 API — flat per generation regardless of motion amplitude, reference count, or BGM, so spend stays predictable.
OpenAI-compatible REST
One endpoint, one key — the Vidu Q1 API uses the same JSON shape and Bearer header as every RouterBase model, so switching to the Vidu Q1 API is only a model ID change.
Quickstart
Get started with the Vidu Q1 API in 3 steps
From sign-up to your first reference-to-video call in under 5 minutes.
Upload your reference image
Host your subject image on a public URL — the Vidu Q1 API accepts one or more reference image URLs, and extra angles sharpen identity consistency.
POST to the Vidu Q1 endpoint
Send reference_images, an optional prompt, motion_amplitude, and bgm in JSON to POST /v1/images/generations. The Vidu Q1 API returns an async job id immediately; poll GET /v1/images/generations/{id} until status=success.
Download the clip
The success response from the Vidu Q1 API contains a signed CDN URL under the results array. Drop it into a <video> tag or copy the file to your own bucket — the 5-second 1080p MP4 is ready with no post-processing.
Pay only for what you use
RouterBase passes through partner-tier pricing. Compared against the model's official published API rate.
| Resolution | RouterBase | Official | Save |
|---|---|---|---|
| generation | $0.340 | −15% |
One run at the default settings (generation) costs $0.340.With $1 you can run this model approximately 2 times.
What teams build with the Vidu Q1 API
Real production loads running on the Vidu Q1 API and the RouterBase catalog.
One call with a reference photo — same character, 5-second clip, live in 90 seconds. Our influencer team loves it.
Reference-to-video means we stopped re-uploading frames for continuity. One photo, done.
We pipe reference images into the Vidu Q1 API nightly. BGM on, motion auto — character intact every morning.
Swapped the base URL to RouterBase and passed reference_images. The Vidu Q1 API kept my game character consistent across ten clips.
RouterBase puts 200+ models behind one key. The Vidu Q1 API is the one our brand team books every sprint.
At $0.34 per clip it fits inside our ad budget — and our spokesperson looks the same in every video.
Same JSON shape, different model ID. Reference-to-video was the easiest migration in our 42-service rollout.
15% off the rate adds up fast when you generate thousands of brand-consistent clips per week.
Frequently Asked Questions
Common questions about the Vidu Q1 API reference-to-video task.
The Vidu Q1 API reference-to-video task uses reference images of a subject to maintain identity and character consistency across the 5-second 1080p clip — unlike image-to-video, which animates a single input image. It is the right choice when a character must stay recognizable across many clips.