# Vidu Reference Canonical page: https://fuser.studio/models/vidu-reference Vidu Reference in Fuser generates video that keeps characters, outfits and props consistent across shots, built from several reference images at once. ## Specs | Spec | Value | | --- | --- | | Versions | Q3 Mix, Vidu Q1, Vidu | | Inputs | Prompt (text), Images (image) | | Output | video | | Duration | 1–16 seconds | | Resolution | 360p, 540p, 720p, 1080p | | Aspect ratios | 16:9, 9:16, 4:3, 3:4, 1:1 | | Audio | Generates audio | | Cost | 97–3,395 credits per run | Cast your own characters and props into one continuous, sharp-likeness shot, with sound, from a handful of reference images Creator: ShengShu Technology [Cast the scene](https://app.fuser.studio) ## How Vidu Reference works Start from images, not a blank prompt: upload up to four references, describe how they interact, and let the chosen tier handle motion, length and sound. ### Upload your reference images Add one to four clean, well-lit portraits, costume turnarounds, props or environment stills on uncluttered backgrounds. ### Direct the interaction Write a clear action prompt naming who does what, then pick model, duration, aspect ratio and movement amplitude. ### Render with sound Generate a continuous scene with locked character likeness and, on Q3 Mix, synchronized native audio. ## What Vidu Reference is good at Built for scenes where several referenced subjects share one frame, from fusing designs into hybrids to carrying a cast through a 16-second take. ### Multi-subject feature fusion Merge elements from separate reference images into one new entity, like the front of one design with the back of another, without losing core likeness. Spell out which subject does which action. ### Long-form Q3 Mix with native audio Q3 Mix runs 1 to 16 seconds at up to 1080p and generates foley, ambience and voices in a single pass. Pick it for continuous narrative beats; its cost scales with duration and resolution. ### Movement amplitude control On Q1, set Small, Medium or Large to protect facial detail in portraits or drive sweeping action. Q1 trades length and resolution for that dial and optional background music; Q3 derives motion on its own. ### Multi-angle identity anchoring Feed front views, costume details and turnarounds so wardrobe, face and silhouette hold across a multi-second shot in 16:9, 9:16, 4:3, 3:4 or 1:1. ## Made with Vidu Reference A gallery of reference-driven clips: wardrobe-locked commercials, prop-led visualizers, weather-beaten documentary frames, vertical dance and candlelit period drama. ### Commercial spot with high-contrast motion and reference-locked wardrobe ### Album visualizer blending custom prop references and atmospheric lighting ### Archival-style documentary framing with physical weather dynamics ### Vertical dynamic motion with controlled silhouette geometry ### Cinematic period drama with precise prop interaction ## What people build with Vidu Reference Story directors, brand teams, fashion creators, anime studios and musicians use it when a recognizable cast or product has to hold up across shots. ### Multi-character film scenes Turn character sheets and concept art into scenes where two or more established characters meet, trade props and react, with faces and costumes that stay recognizable across the shot. ### Brand campaign spots Lock a mascot, model or hero product from reference stills and build a 16-second commercial beat with matching ambience, sound effects and a vertical or square cut. ### Fashion lookbook motion Bring costume turnarounds to life so fabric swing, silhouette and colorway hold true on the move, without a runway shoot. ### Anime and stylized series Keep a 2D or 3D stylized cast consistent from clip to clip, so episodes, openers and animatics share one look and each hero keeps their face. ### Album visualizers and music clips Place a band member, an instrument prop and a stage environment from separate references into one looping-feeling shot that matches the record's mood. ## Vidu Reference questions ### What's the difference between Q3 Mix and Vidu Q1? Q3 Mix is the long-form, high-definition tier; Q1 is the fixed-length tier with motion control. Q3 Mix makes 1 to 16 second clips up to 1080p with synchronized native audio, with pricing that scales by duration and resolution. Q1 has a fixed clip length and lower maximum resolution, no native sound effects or dialogue, but offers a Movement Amplitude setting and optional background music at a fixed cost. ### Which Vidu Reference model should I use for a multi-character story scene? Use Q3 Mix. It is built for multi-entity storytelling, supports up to four reference images, runs up to 16 seconds at 1080p, and generates footsteps, ambience and dialogue in the same pass. Expect longer render times on 1080p long clips. ### When would I pick the original Vidu model instead of Q3 Mix or Q1? Pick it for lightweight reference tests or legacy workflows that don't need feature fusion or native audio. It is the baseline engine, so interaction physics and prompt adherence are less capable than Q3 Mix. ### How many reference images can I use, and what should they look like? Use one to four references. Clean, well-lit portraits or object turnarounds on neutral backgrounds give the sharpest likeness. Avoid low-resolution or heavily cropped images, and avoid mixing conflicting lighting and art styles unless you want a deliberate fusion. ### What is Vidu Reference weak at? It struggles with fine hand work like playing piano or tying knots, legible in-frame text and typography, and abrupt scene cuts inside one take. Fast large-amplitude camera moves can soften background texture, and three or more closely overlapping subjects can occasionally blend. ### Does Vidu Reference generate audio? Yes, with Q3 Mix, which generates synchronized foley, ambience and vocalizations natively when Generate Audio is on. Describe sounds or dialogue in your prompt to steer it. Q1 does not make sound effects or dialogue, but can add background music; it was created by ShengShu Technology. ## Try Vidu Reference on Fuser Cast your own characters and props into one continuous, sharp-likeness shot, with sound, from a handful of reference images [Cast the scene](https://app.fuser.studio) ## Related models - [Kling 4.0](https://fuser.studio/models/kling-4-0.md) - [MiniMax H3 Reframe](https://fuser.studio/models/minimax-h3-reframe.md) - [Kling 3.0 Video](https://fuser.studio/models/kling-3-0-video.md) - [MiniMax H3](https://fuser.studio/models/minimax-h3.md) - [Seedance 2](https://fuser.studio/models/seedance-2.md) - [Gemini Omni Video](https://fuser.studio/models/gemini-omni-video.md) Node reference: [Vidu Reference docs](https://docs.fuser.studio/docs/nodes/video/vidu-reference.md) ## More articles - [Vidu Q1 Reference Guide: Consistent Characters and Products from Up to 7 Images](https://fuser.studio/articles/vidu-reference-guide.md) - [Sora Alternatives: What to Use Now That Sora Is Shut Down (2026)](https://fuser.studio/articles/sora-alternatives.md)