Create a new video by describing the scene and motion you want.
Get the right result: check these first
Choose the starting point. Use a written prompt here. Use Image-to-Video when a specific supplied image must be the starting frame, or AI Image Generator when you need a still picture.
Set duration in the controls. Choose a supported duration under Settings. Asking for a longer movie in the prompt does not override that selection. AI Video Extender is the separate workflow for continuing an existing clip.
Prompt instructions are not locks. Review scene continuity, text, identity, and audio in the actual output. Do not assume a negative instruction such as “no text” guarantees that nothing unwanted will appear.
Still stuck? Contact support with the tool name, project link or visible ID if available, model, complete prompt, duration, audio/reference settings, and timestamp of the unwanted result. Keep the project while it is reviewed. How to send useful troubleshooting details.
Step by step
Open Text-to-Video and sign in.
In Prompt, describe the subject, action, setting, camera movement, and visual style. Keep the requested action appropriate to a short clip.
Choose a model and use its available duration, resolution, and aspect-ratio settings.
Review Audio. Generated sound and an uploaded recording are different options; use a model that explicitly supports the audio input you need. Add References only when the selected workflow supports them.
Check the estimate and select Generate Video. Review the completed video and audio before downloading.
Example prompt
“A cyclist rides along a quiet coastal road at sunrise. The camera follows steadily from behind. Natural light, gentle motion, no scene change.” Use the aspect-ratio control for output shape.
Use a recording or keep a person consistent
For a supplied voice or song, follow the linked audio-input guide. References and end frames can conflict with uploaded audio in some models. A saved Character can help consistency in compatible modes, but does not guarantee an identical face in every frame.
A longer story needs a plan
Break a story into separate scenes and review each clip. A plan allowance is not the maximum length of one generation. To continue an existing clip, use AI Video Extender.
The result misses part of the prompt
Reduce the number of actions or camera moves. Put the main subject and action first. Compare one change at a time; repeated generations use additional credits.
Cost, limits, and your result
These instructions cover the Dashboard. Sign in to generate and check the displayed credit estimate and access requirements. File limits and settings can depend on the tool, model, and plan. Follow the upload and validation messages shown for your selection.
Review the completed result before downloading. For signed-in projects, see find and download your creations.
If a job is still processing or failed
For a job still processing, check its status before submitting again. For a failed or technically broken output, see generation failures and credits.