Turn an idea into AI video
An AI video generator for scenes from text, images or references. Direct the motion, the camera and the sound.






Create a new vertical 10-second cinematic screen-break illusion. Begin behind an audience in a dark cinema with red seats. A huge realistic dinosaur approaches through a misty forest on the cinema screen, then its head appears to cross the screen boundary into the auditorium. Nearby viewers duck and turn in surprise as the camera shifts toward a seated viewer, keeping the dinosaur close above the seats. Build tension, then a comic reaction; maintain coherent creature scale, theatre geometry and light. Choose a new dinosaur design and audience rather than copying the exact faces. Add a suitable original suspense-and-reaction soundtrack.
How it works
Try it now- 01
Say what you want
A sentence or two is enough.
- 02
Keep Auto, or set it
Choose the settings that fit what you want to make.
03Make it
Start creating, then keep working with HowWorks.
Explore the possibilities










About
Make a short video around one moment worth watching: a character turns toward the camera, a product moves into the light, or a drawn world comes to life. Start from a text prompt, animate an image, connect first and last frames, or use visual references to guide the scene. Choose the input method that fits what you already have. Each model offers its own duration, framing, resolution and sound settings. Watch the full clip, then develop the next shot or refine the idea with HowWorks.
Questions
How do I create an AI video?
Choose how you want to begin: a written scene, a starting image, two endpoint frames or visual references. Describe the subject, one main action and the camera movement. Choose a supported model and settings, then generate the clip.
Can I turn an image into a video?
Yes. Open Image to Video, upload a starting picture and describe what should move. Include what the camera does and which details should stay recognizable. Prepare the image composition for the shot you want.
What is the difference between first/last frames and reference images?
First & Last Frame uses two pictures as the opening and destination of the shot. Reference to Video uses images to guide the subject, setting or style of a new scene. Choose the input method before deciding how to direct the movement.
Can an AI video include sound?
Supported models can generate audio with the picture. Some include sound automatically; others offer a sound switch. Describe the ambience, action sounds or dialogue you want, then check the actual soundtrack alongside the video.
Which video lengths and resolutions can I choose?
They depend on the model, tier and input method. Review the options shown after selecting a model. The model pages explain those differences so you can choose the format your shot needs.










