Brand visuals: set the style once, roll it out to every size
Posters, banners, social verticals and packaging all need the same look in different sizes. Lock the style in one key visual, and it carries that style to every format. Change one requirement and the whole set follows.
Using this key visual, roll out an autumn campaign set: a vertical poster, a website banner, a social story and a square header.
What it builds on the canvas (illustration).
How it does it
Define the style once
Start from one key visual, generated or one you already have. Color, typographic feel and composition all come from it.
Carry it to every size
One node per format, each with its own ratio and the key visual connected as a reference. Layouts are recomposed for each size rather than cropped from one image.
One change, the whole set
Say "make the main color deep green" or "remove the people" and it applies the change to every node, then regenerates the set together.
Questions
Can I use the text in the images as-is?
Text drawn by image models isn't always accurate. For final assets, leave space for titles and prices and set them afterward, or check the generated text by eye.
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.