Reference-driven AI video
How to use
Vidu.
Creating short videos with reusable characters, products, props, scenes, or styles and maintaining visual continuity across reference-driven shots.
Vidu is a AI video platform for text, image, reference, character-consistent, and API generation. Creating short videos with reusable characters, products, props, scenes, or styles and maintaining visual continuity across reference-driven shots. This guide covers the whole path in one place: official access, a first session that produces something reviewable, the checks that make output trustworthy, and the permissions worth limiting before you connect real work.
AI should make the work easier to inspect. If the workflow removes the source, the owner, or the review step, redesign the workflow.
Access & setup
Find, install, and sign in to Vidu
Get into the official Vidu experience with the right account and a setup you understand.
- 01
Start at https://www.vidu.com/ and confirm the domain before entering account or payment information.
- 02
Availability: Vidu is available through its web creator and developer platform, with text-to-video, image-to-video, start-and-end-frame, multi-reference, reusable subject, sound, enhancement, and API workflows.
- 03
A supported account or API credential, credits or plan access, authorized reference assets, and explicit decisions about privacy, end-user consent, content monitoring, commercial rights, disclosure, and regional compliance.
- 04
Sign in with the account you intend to keep using, then review plan, data, notification, and permission settings.
- 05
Run one low-risk test task before connecting sensitive files, repositories, or workspace data.
- Use official download pages.
- Review permissions during setup.
- Keep installers and applications updated.
First session
Your first useful Vidu session
Learn the interaction loop using a small task with a clear outcome.
- 01
Define the story beat, subject, action, camera, setting, duration, aspect ratio, sound, continuity rules, and distribution rights.
- 02
Prepare one to seven clean authorized references that show stable identity, product, scene, or style details without private metadata.
- 03
Name each reference clearly in the prompt, specify only necessary motion, and generate a short economical preview.
- 04
Review face, outfit, object, logo, scene, camera, motion, audio, disclosure, and rights across every frame before downloading or publishing.
- State the outcome before the background.
- Provide the real source material.
- Review the result before expanding the task.
Quality control
Check the quality of Vidu output
Turn a promising generation into an asset you can legally and safely ship.
- 01
Restate the brief, the deliverable format, and where the asset will appear before judging any output.
- 02
Inspect at full resolution: generated media hides its errors at thumbnail size.
- 03
Check the details these systems reliably get wrong — hands, text, logos, reflections, symmetry, and edge artefacts.
- 04
Confirm the licence and commercial-use terms for your plan, and check the output does not reproduce a recognisable style, mark, or likeness you have no right to use.
- 05
Review for accessibility and delivery: alt text, contrast, colour profile, file size, and the exact export format.
- Inspect at full resolution before approving anything.
- Confirm commercial-use rights before an asset reaches a client.
- Keep the prompt and settings with the asset so it can be reproduced.
Privacy & permissions
Use Vidu safely
Use the platform without surrendering rights, likenesses, or client material you do not control.
- 01
Confirm you hold the rights to every reference image, voice, or clip before uploading it.
- 02
Check whether your plan trains on submitted content, and opt out before uploading client work.
- 03
Never upload a real person's likeness or voice without their explicit, documented consent.
- 04
Review the output for marks, styles, or likenesses you have no licence to reproduce.
- 05
Label synthetic media where your client, platform, or jurisdiction requires disclosure.
- Multi-reference generation can reproduce identifiable people, brands, products, locations, and styles. Vidu requires sufficient rights and consent, may monitor inputs and outputs for operational purposes, and prohibits hiding deep-synthesis indicators or using person-related output for consequential decisions. Keep references minimal and authorized, preserve provenance, review privacy and cross-border processing, test continuity frame by frame, and validate commercial terms for the exact web or API service used.
- Follow your organisation's approved-use policy.
- Never treat fluent output as authorization to act.
Core workflows
Step-by-step ways to use Vidu for the work it does best.
Each workflow below has its own outcome, steps and review checkpoints.
Coordinate product, character, and scene references without losing brand accuracy or authorization across generated motion.
↓ 02 WorkflowOperate a governed Vidu API video workflowAdd reference-driven video to an application with bounded inputs, consent, credentials, cost, moderation, and human release control.
↓Workflow 01
Build a multi-reference brand video in Vidu
Coordinate product, character, and scene references without losing brand accuracy or authorization across generated motion.
Outcome: Create a short brand-safe draft whose important visual elements remain recognizable and legally cleared.
- 01
Define the audience, placement, story beat, product claims, aspect ratio, duration, character, scene, camera, sound, brand rules, and approval criteria.
- 02
Prepare one to seven minimal authorized references with clear names, stable angles, approved logos and colors, and no hidden personal or confidential information.
- 03
Use Reference to Video, assign each reference a specific role in the prompt, request one simple action and camera move, and generate a short preview.
- 04
Compare every frame with source references for identity, product geometry, label text, color, logo, props, scene continuity, physics, audio, and unsupported claims.
- 05
Correct the prompt or reference rather than hiding defects, finish precise text and sound externally, preserve provenance, and obtain brand, legal, and accessibility approval.
What good use looks like
- Give each reference one clear role.
- Verify product geometry frame by frame.
- Finish exact copy outside generation.
Workflow 02
Operate a governed Vidu API video workflow
Add reference-driven video to an application with bounded inputs, consent, credentials, cost, moderation, and human release control.
Outcome: Run a reliable generation pipeline that cannot silently accept unauthorized identities or publish unsafe output.
- 01
Define allowed users, inputs, models, durations, resolutions, references, regions, cost limits, retention, moderation, disclosures, and prohibited use cases.
- 02
Keep API credentials server-side, minimize uploaded data, obtain documented end-user consent, use isolated storage, and bind each request to an authenticated owner.
- 03
Validate file type, size, metadata, rights attestations, prompt content, reference count, idempotency key, and budget before submitting the generation.
- 04
Poll with bounded retries, handle failure and timeout safely, quarantine output for automated and human review, and preserve required deep-synthesis indicators.
- 05
Test abuse, impersonation, prompt injection, duplicate requests, cost exhaustion, deleted users, provider failure, unsafe output, audit logs, and a human-approved publication path.
What good use looks like
- Keep credentials and publishing server-side.
- Require rights attestation and consent.
- Quarantine every output before release.
Official references
Check the current product documentation.
Features, plan limits, availability, and data controls change. These official pages are the starting points used for this guide.
- Vidu official site ↗
- Vidu Reference to Video ↗
- Vidu platform Terms of Use ↗
- Vidu platform Privacy Policy ↗