Wan 3.0 Video Model

Thirty seconds in one generation — long enough for a continuous camera move, a full beat of dialogue, or a scene that builds instead of resetting every five seconds. Or bring up to twenty images, clips and audio files as references and hold them consistent across a fifteen-second take.

Optional
Optional
50

Key Features of Wan 3.0

30-Second Generation

One run produces up to thirty seconds. No stitching, no matching a cut between two clips that almost line up. A push down a corridor stays one unbroken move; a spoken line finishes inside the same shot it started in. You name the exact length rather than picking from a short menu — any whole second from two to thirty — and cost scales linearly with it, so a six second clip really is half of a twelve second one at the same resolution. There is no reason to round up. Reference runs are the one exception: they cap at fifteen seconds, because your reference footage and the generated output share the same thirty-second budget upstream.

Omni-Reference

Attach up to twenty assets at once — ten images, five video clips, and five audio files. The model reads them in the order you attach them, so arrange them the way you mean to refer to them: the character first, then the camera move you want copied, then a voice. The same face, the same product, the same room, held across every shot in the take — the same reference to video workflow, running inside a single generation instead of across separate clips.

INPUT

Girl A — outfit

Girl B — outfit

Girl A — face

Girl B — face

PROMPT

A cinematic fashion blockbuster featuring two female protagonists, with an extremely fast pace and pure jump cut editing logic. Shot with the Arri Alexa 65 and Panavision anamorphic lenses, it captures the texture of Kodak Vision3 500T film, boasting 8K resolution and photo-realistic quality, with no text. The facial features of the characters are fully locked onto Girl A @Image1 and Girl B @Image2. [0-3 seconds: rapid entrance and contrast] (hard cut) A stark white minimalist space is sharply shadowed by intense side lighting. Left screen/left side: Girl A wears a black deconstructed leather suit, her eyes cold and elegant under the cold light, swiftly turning to look directly at the camera. Right screen/right side: Girl B wears a flowing champagne gold silk dress, her eyes languid under the warm light, swiftly turning to look directly at the camera. Real film graininess. [3-6 seconds: extreme close-up of material] (hard cut) Extremely close-up macro shot. Girl A's reference outfit @Image3: Cold light casts on the sharp creases of black leather and metal accessories, presenting a cold and high-end luster. Girl B's reference outfit @Image4: Warm light outlines the lines of her collarbone, with silk fabric flowing like water waves, and the skin exhibits a hyper-realistic translucent and hydrated texture, with visible fine hairs. [6-9 seconds: Tension Interlace (High-Speed Photography)] (Hard Cut) The two characters walk towards each other in a pure white space and pass by each other. High-speed photography (1000fps slow motion). The toughness of black leather collides violently with the softness of champagne silk in an instant of interlace, with skirt hems and hair flying in the air. In the zero-point-one second of interlace, their eyes meet sharply. [9-12 seconds: Back-to-back pressure] (Hard cut) The two stand back-to-back. Strong rim lighting simultaneously outlines their facial contours and highlights the golden edges of their hair. They simultaneously turn their heads quickly and look directly at the camera. Their expressions exude a strong sense of pressure, professionalism, and the confident aura of top supermodels. [12-15 seconds: Relaxation and freeze] (Hard cut) The two people stand side by side, slightly tilting their heads to look at each other, revealing a contagious, relaxed, and confident smile. The camera slowly zooms out, revealing the perfect proportions of the two people in the grand light and shadow space, and the image gradually fades in a high-end glow. Camera movement: Quick handheld panning, rapid zooming, high-speed photography in slow motion, pure hard cuts, without fancy visual effects. Color: High-contrast black, white, and gray tones, embellished with cool metallic luster and warm champagne gold, with film-grade color grading.

OUTPUT VIDEO

0:15

Synced Audio

Sound is generated with the picture, not layered on afterward, so dialogue lands on the mouth and footsteps land on the step. Describe what should be audible with the same care you give to what should be visible — the model is reading that half of the brief too, and it costs nothing extra. Turn it off when you want a silent plate to score yourself.

First & Last Frame

Give Wan 3.0 the image you want to open on and the image you want to land on, and it builds the motion between them. It's the image to video case with both ends pinned instead of one. Useful when both endpoints are fixed and only the path between them is open — a product that has to end in a specific position, a match cut into the next shot, a logo lockup that has to sit exactly where the brand guide says.

INPUT

First frame

Last frame

PROMPT

【One-Take, Slow Aesthetic Camera, No Cuts, 15-Second Long Take — Rock-Color Painting Mineral Pigment Texture Meets 3D Rendering, Azure Blue × Gilded Gold Color Clash】 Global Settings: Chinese rock-color painting aesthetic with visible mineral pigment grain texture and gold leaf accents. Strong contrasting palette of azure blue and gilded gold. The scene is West Lake at dawn in thin mist: the lake surface rendered in matte azure-blue washes, golden morning light piercing through cloud layers to form Tyndall light beams. In the distance, the stone pagodas of Three Pools Mirroring the Moon and Leifeng Pagoda emerge faintly through the fog. In the foreground, lotus leaves and lotus blossoms. The central figure is Xizi, the Water Goddess of West Lake: rendered in rock-color painting texture, with an oval face, willow-leaf eyebrows, phoenix eyes, a vermillion floral mark at the center of her brow, skin like mutton-fat jade glowing with a soft luminescence, and a pale golden halo floating behind her head. Her hair is swept up in a high bun adorned with a single gilded gold lotus hairpin. Her skirt and flowing shawl are composed entirely of living lake water, gradient azure blue, with a shimmering, rippling surface. Audio & Sound Design: Background features gentle guzheng and bamboo flute. Ambient sound includes subtle water ripples and early morning birdsong. Starting at the 8-second mark, an ethereal, tender female voice slowly recites: "If I compare West Lake to the fair Xizi—" The second line follows during the glance-back segment: "Light or heavy makeup, she is always beautiful." The delivery is slow, with a slight reverb, leaving a lingering resonance. [0-3s: A Water Drop] Extreme close-up, macro shot. At the edge of a lotus leaf at dawn, a water droplet gathers, plump and full, reflecting golden morning light, then slowly falls. The camera follows the droplet with a tilt down as it drops into the lake, triggering a ring of gold-and-blue ripples that expand outward in concentric layers. [3-7s: Water Takes Shape] At the center of the ripples, the lake water slowly rises and gathers into the form of the goddess Xizi: the water transforms into her azure-blue skirt and translucent shawl, with fine streams of water flowing and swirling around her body. She rises slowly from the center of the lake, her eyes gently closed, then slowly opening. The gilded gold lotus hairpin glows with a faint light. The camera slowly orbits her half-lowered eyes and the skirt woven from flowing water. [7-11s: One Step, One Lotus] She walks barefoot across the lake surface, each step sending out a ring of golden ripples from beneath her feet, lotus blossoms blooming one after another within the ripples. The camera pulls back to a medium-wide shot: the thin mist parts, and in the distance the three stone pagodas of Three Pools Mirroring the Moon light up with warm glow, Leifeng Pagoda emerges in the morning light, and willow branches along the shore brush the water. At the 8-second mark, the female voiceover begins: "If I compare West Lake to the fair Xizi—" Her shawl trails a long streak of gold-and-blue water light behind her. [11-15s: The Glance Back · Always Beautiful] She stops and looks back over her shoulder toward the camera. The camera slowly pushes in to a half-body close-up: morning light falls across her face, her water-woven shawl drifts gently at her side, a few luminous water droplets fall from her hair tips, dissolving into fine particles of light mid-air. The voiceover continues with the second line: "Light or heavy makeup, she is always beautiful." She smiles softly. Behind her, Leifeng Pagoda stands in the morning glow, with Three Pools Mirroring the Moon hazy in the distance. In the final second, the frame freezes completely on her glance-back close-up, locked into a perfect cinematic poster composition.

OUTPUT VIDEO

0:15

Character Consistency

Faces keep their features across a long take instead of drifting between shots. Clothing, props, and set dressing stay where they were. References are the lever you have over it: hand the model the face, the product or the room that has to stay the same, and it carries them through the whole generation.

INPUT

Product image

PROMPT

The lip gloss product image @Image1, generate a model lip color test video, 15 seconds, portrait orientation, highlighting the lip color effect

OUTPUT VIDEO

0:15

Precision Video Editing

Describe the change in plain language and Wan 3.0 rewrites only that part of an existing clip — remove an object, relight the scene, change what someone is doing — while everything else stays exactly as shot. Select a time range and regenerate just that stretch, or extend footage you already have. It covers the part of an AI video editor workflow that timeline tools can't do at all: not cutting what you shot, but changing what's in it.

INPUT

Source clip

PROMPT

In Video 1, the man on the left is removed, and the surrounding background is used to fill the space naturally, while the rest of the characters, actions, and images remain unchanged.

OUTPUT VIDEO

0:05

GETTING STARTED

How to Create with Wan 3.0

1
Pick Wan 3.0 and your starting point

A prompt, a first frame, or a set of references. Starting from a frame, upload it on image to video.

2
Attach whatever has to stay consistent

Character images, a camera move to copy, a voice to match. Ten images, five clips, five audio files.

3
Set length and resolution, then iterate

Stay at 480p while you're finding the shot. Change one thing, run it again, then re-run at 1080p.

Ready to create your first video?

FAQs

Wan 3.0 is Alibaba's video generation model, released in 2026. It handles text, image, and reference-driven generation in one model, produces sound alongside the picture, and rewrites parts of existing footage from a plain-language instruction.

Anything that needs to run long and hold together — product demonstrations, dialogue scenes, UGC-style ads, short narrative pieces, music performance clips. The thirty-second ceiling and reference control make it a better fit for complete scenes than for isolated shots you plan to cut together.

Attach up to twenty assets in a single run — ten images, five video clips, five audio files — and address each one directly in the prompt. One image fixes the character, one clip supplies the camera move, one audio file supplies the voice.

Use clean, well-lit images where the subject fills the frame, and keep the description of that subject identical between runs. Refer to each asset explicitly rather than assuming the model will infer which is which. Fewer scene changes within a single run also help the reference hold.

Yes. Describe the change and it rewrites that part while the rest of the frame stays as shot — remove an object, relight the scene, alter what someone is doing. It can also extend existing footage, with input and output together capping at thirty seconds.

Yes — free credits cover Wan 3.0 runs. A thirty-second 1080p clip is one of the heavier renders here, so start at 480p while you're testing prompts.

Create Videos with Wan 3.0

Thirty seconds in one generation, with the soundtrack already in it — and up to twenty references to keep the take consistent from the first frame to the last.