AI Video Generator: Turn Text into Product and Ad Videos

Describe the shot, choose a model, length and resolution, and get a clip ready for product pages, ads and social feeds. You can also use your product photo as the first frame, set the first and last frames, or guide the video with up to 9 reference images.

First frame
(optional)
Switch models to add images
Video settings
Aspect ratio
Resolution
Image input
Model
Model
Results kept 7 days · tied to this browser — Sign in to access them across devices
Loading tasks…
Updates paused · Retrying

Sample Results

Food & Beverage
Cold Brew Coffee Ad

A glass bottle of cold-brew coffee on a marble counter, ice cubes dropping into a glass beside it, condensation on the bottle, slow orbit shot, soft morning window light, commercial product video

Feature Demo
Sneaker Product Spin

A white running sneaker rotating slowly on a floating concrete block, dust particles drifting in a beam of light, camera dolly in to the textured mesh and sole, dark studio background, sports product commercial

Beauty
Skincare Serum Close-Up

A frosted glass serum bottle with a gold dropper on a wet stone slab, water ripples spreading around it, a single drop falling from the dropper in slow motion, soft studio light, clean skincare commercial

Lifestyle Scene
Sports Bottle Ad from a Photo

The two sports bottles stand on a dark gym floor, a hard light sweeps across them from the side, water droplets bead on the matte surface, camera slowly pushes in and rises to the flip-top lids, energetic fitness product commercial

How It Works

1
✍️

Describe the video

Write what happens in the shot: the subject, the action, the camera movement and the mood, in up to 2000 characters.

2
🎛️

Choose a model and settings

Pick a model, then set the aspect ratio, length and resolution. The Generate button shows the exact credits for the video before you submit.

3
📥

Download the video

The video is generated in the background and appears in your task list as an MP4 file, ready to download.

Video models available

MiniMax

MiniMax H3 and H3 Max, up to 2K resolution with synchronized sound.

Seedance

Seedance 2.5, 2.0, 2.0 Fast and 2.0 Mini by ByteDance, from 480p to 1080p with synchronized sound.

Wan

Wan 3.0 and Wan 3.0 Prime by Alibaba, from 480p to 1080p, with sound you can turn on or off.

Kling

Kling 4.0, Kling 3.0 and Kling 3.0 Turbo by Kuaishou, in 720p or 1080p. Kling 4.0 makes up to 30 seconds in one take, and Kling 4.0 and 3.0 let you turn sound on or off.

Google Veo

Veo 3.1 and Veo 3.1 Fast by Google, in 720p, 1080p or 4K with synchronized sound.

Frequently Asked Questions

Write a prompt describing the scene, choose a model, set the aspect ratio, length and resolution, then click Generate. The video is created in the background and appears in your task list when it is ready.

To keep costs low, start with Wan 3.0 or Seedance 2.0 Mini. For 4K output, choose Veo 3.1 or Veo 3.1 Fast. To use your own images, choose First frame, First & last or Reference images in the Image input menu next to the model. The model menu shows each model's starting price in credits.

Yes. Choose an image mode in the Image input menu next to the model. With a first frame, the video opens on your picture. With first and last frames, it moves from the first picture to the last. With reference images, it draws on up to 9 pictures for the subject, scene and style. Use JPG, PNG or WebP files up to 10 MB each and at least 300 px on the short side.

The price depends on the model, resolution and length, and the Generate button shows the exact number before you submit. Videos start at 30 credits. If a video fails, the credits are refunded automatically.

Most models generate synchronized sound together with the picture. Wan 3.0, Wan 3.0 Prime and Kling 3.0 let you turn sound on or off with the Sound switch.

Most videos are ready within a few minutes, depending on the model, length and resolution. Generation runs in the background, so you can close the page and find the finished video in your task list later.

Yes, provided your prompt and any image you upload do not infringe the rights of others and the content complies with our Terms of Service. No attribution is required on paid plans or credit packs; free-plan outputs require attribution to LubanAI. Results are kept for 30 days (7 days for free accounts) and then deleted automatically.

Tasks are processed in the order they are submitted. Paid tasks from subscribers and credit pack buyers are picked up first. Free tasks may wait longer during peak hours.

We use cookies to improve your experience. See our Privacy Policy.