Can I start with only a script?
Yes. A scene script is required; images are optional. Describe a visible action and ending rather than pasting a long article or a list of abstract benefits.
Can one video contain several shots?
You can request a few ordered shots within the selected duration. Exact cuts and timing depend on the model and result; they are not separate editable timeline clips.
Will it read my script aloud?
Scene directions are not read aloud by default. You may request dialogue or sound in the script, but this is generative audio, not a separate narration service or a guarantee of exact words.
Does it make long videos and subtitles?
This workflow returns one model-length video. Long scripts, independent voiceover tracks, subtitle files and automatic multi-clip assembly require a separate production workflow.
What do reference images control?
Identify which image guides a character, object, location or style. They are visual references, not automatically ordered storyboard panels or fixed opening and closing frames.
Does loading an example use credits?
No. It fills an editable script and settings, plus the original reference image where provided. Generation starts only after you submit and accept the displayed quote.