Image to video: turn the images on your canvas into clips
Attach a video node to any image you like, use it as the first frame, and say how it should move, how long, and whether it needs sound. Clips line up on the canvas in order, so the whole cut is easy to follow.
Turn these three frames into 5-second clips with a slow push-in, and end the third one on the product.
What it builds on the canvas (illustration).
How it does it
The image is the first frame
Any image on the canvas can take a video node. The shot starts from a frame you're already happy with, instead of rolling the dice from text.
Describe the motion in words
Push in, orbit, follow, a turn of the subject. Pick length and ratio on the node, and for models that support it, choose whether to include sound.
Clips in a line
Clips sit on the canvas in order with the voiceover beside them. If one clip isn't right, redo only that one.
Questions
Can I use my own footage?
Yes. Drop a video in and use it as the reference for editing or extending it. Longer videos can be split into segments and handled one by one.
Does it spend credits without asking?
No. Before any generation that costs credits, an approval bar lists what this batch will do, and nothing runs until you approve. Building nodes, writing prompts and arranging the canvas cost nothing.
Where do the results go?
They stay on the canvas nodes, where you can revise any single one. You can also have it write the finished files back to a folder on your computer.
Do I need to write prompts?
No. Say what you want in plain words and it breaks the request into a prompt for each node. If one isn't right, edit that node directly.