Make every frame
move with Vidu

Describe a scene, start from a still or bring a set of references, and get a clip with sound back.

Try Vidu

Meet Vidu

Made with Vidu

Open the generator

Vidu Q3 Image to Video

The soldier moves from a static position, raising his rifle into a ready-to-fire stance, and begins to advance slowly and cautiously through the rubble. The smoke in the background thickens, and wind blows, kicking up dust from the ground. Handheld camera style with slight shake, adding immediate urgency.

Try it now

Vidu Q4 Reference to Video

Use the character reference image to create a high-energy cinematic fashion video. The same man stands in a dark industrial space, then slowly turns toward camera as a strong gust of wind moves his jacket and hair. He takes one confident step forward while sharp white lights flicker behind him, creating metallic reflections across the distressed leather jacket and sunglasses. Add subtle handheld camera movement, a quick low-angle push-in, dramatic shadows, smoky atmosphere, fast light streaks, and a powerful streetwear campaign mood. Keep his face, hairstyle, sunglasses, outfit, body proportions, and overall character design consistent with the reference image. Cool, edgy, futuristic, premium fashion-film aesthetic.

Try it now

Vidu Q3 Text to Video

A retro taxi driving slowly on a rainy New York street at night, neon lights reflecting on the wet pavement, pedestrians with umbrellas walking hurriedly, camera tracking the taxi, cinematic film grain, photorealistic, 8k, moody atmosphere.

Try it now

Vidu Q3 Image to Video

Two futuristic robots engage in intense hand-to-hand combat. The white robot throws a heavy punch, and the black robot blocks and counters. Sparks fly from metal impacts, fast and fluid motion. Dynamic handheld camera with strong impact and motion blur.

Try it now

Vidu Q4 Image to Video

The red-haired woman walks down the Paris street holding two baguettes. A cheeky pigeon suddenly swoops toward the bread, making her quickly pull the baguettes closer to her chest and laugh in surprise. The pigeon flies past and out of frame. Natural reaction, cinematic handheld tracking, warm Paris daylight, realistic motion, playful movie-like moment.

Try it now

Vidu Q3 Text to Video

Gentle 2D slice of life anime. Students laughing and walking down a school hallway filled with sunlight during sunset. Warm color palette, soft watercolor background textures, relaxed atmosphere, expressive character designs.

Try it now

Vidu Q3 Image to Video

Photorealistic cinematic shot of a rider on a powerful, muscular horse galloping through an open, sunlit field. The rider, dressed in rugged equestrian gear, suddenly exhales sharply — “吁~” — as they firmly grip the reins and bring the horse to an abrupt, natural stop. The horse’s muscles tense, its ears flicking, eyes locked forward with alertness, head slightly lowered in controlled stillness. Natural lighting casts dynamic shadows across the terrain, with realistic textures on the horse’s coat and rider’s clothing. The background is a blurred, expansive landscape — grassy plains, distant trees — emphasizing motion and sudden halt. High detail, accurate anatomy, lifelike motion, and authentic equestrian realism. Medium shot, eye-level perspective, capturing the tension and calm after the stop.

Try it now

Vidu Q3 Text to Video

Vibrant 3D anime idol concert. A group of female idols dancing and singing on a glittering stage with large LED screens playing graphics. cheering crowd with lightsticks. Flashy visual effects, smooth motion capture animation, bright and colorful stage lighting.

Try it now

Pick your Vidu

Vidu Q4

Image and reference to video with 3 to 16 second clips, 540p up to 4K, up to 15 reference images and 3 audio clips.

Try it now

Vidu Q3

Text, image, start and end frame and reference to video, 1 to 16 seconds at 540p to 1080p, with Pro and Turbo tiers.

Try it now

Models and pricing

Prices are per generation and update live. Options such as resolution, duration or quality can change the final price, which the generator shows before you run.

ModelInputFrom
Vidu Q4 Image to VideoImage + prompt$0.095Generate
Vidu Q4 Reference to VideoReference images + prompt$0.095Generate
Vidu Q3 Text to VideoPrompt$0.15Generate
Vidu Q3 Image to VideoImage + prompt$0.15Generate
Vidu Q3 Start and End to Video1 or more images$0.15Generate
Vidu Q3 Reference to VideoReference images + prompt$0.154Generate

Frequently asked questions

Which Vidu model should I use?

Choose Vidu Q4 for image and reference to video with the longest reference lists and 2K or 4K output. Choose Vidu Q3 for text to video, start and end frame interpolation and multi-subject references; it also has Pro and Turbo tiers.

How long can a Vidu video be?

Vidu Q4 generates from 3 to 16 seconds and Vidu Q3 from 1 to 16 seconds, in whole seconds.

Which resolutions and aspect ratios are available?

Vidu Q4 offers 540p, 720p, 1080p, 2K and 4K. Vidu Q3 offers 540p, 720p and 1080p. Reference to video supports 16:9, 9:16, 1:1, 3:4 and 4:3.

What can I use as references?

Vidu Q4 Reference to Video takes up to 15 images and up to 3 audio clips alongside your prompt. Vidu Q3 Reference to Video takes 1 to 4 images.

Does Vidu generate sound?

Yes. Audio generation is on by default for Vidu Q4 and Q3 and can be switched off. Q4 Reference to Video also accepts audio clips to guide the result.

Can I use Vidu through an API?

Every model in the table above has a REST API. Open a model page for the request schema and code samples; prices shown here update live.

Your next scene starts here