One idea has to become four shapes before lunch.
Social work is not one image, it is the same image resized into a matrix of platform requirements — and then the whole matrix again next week for the next campaign. The tedium is the job, which is exactly what makes it worth handing to an agent.
1:1
Feed post
Square feeds and carousels. The safest default.
9:16
Story / Reel
Full-screen vertical. Keep the subject clear of the top and bottom third.
16:9
Link preview
What renders when someone shares a URL.
4:3
Slide / carousel
Multi-card posts and presentation exports.
Approve once, then fan out
The workflow that makes this fast has two phases. First you get one image right — that is a creative decision and it deserves your attention. Then every other size derives from it in a single batched call, which is a mechanical step and deserves none.
- 1
Generate the concept at 1:1
Iterate here. This is where the judgement lives.
- 2
Pass it as a reference for the rest
Every other ratio quotes the approved image rather than re-inventing it.
- 3
Batch the remaining ratios
One multicall, three sizes, back together in one round trip.
- 4
Add a transparent variant
A cutout of the subject for stickers, overlays and video.
- 5
Compress each for upload
Platforms re-encode anyway; going in lighter means less damage on the way through.
{
"name": "multicall",
"arguments": {
"requests": [
{ "tool": "generate_image",
"args": {
"prompt": "<same concept>",
"aspectRatio": "9:16",
"referenceImages": ["<approved 1:1 url>"]
}},
{ "tool": "generate_image",
"args": {
"prompt": "<same concept>",
"aspectRatio": "16:9",
"referenceImages": ["<approved 1:1 url>"]
}},
{ "tool": "generate_transparent_image",
"args": {
"prompt": "<subject only, plain background>",
"referenceImages": ["<approved 1:1 url>"]
}}
]
}
}Do not let the model write your headline
It is the single most common mistake in generated social work. Image models render text unreliably at small sizes, and even when it comes out clean you have created an asset that cannot be localised, cannot be A/B tested, and has to be regenerated for every copy change.
Generate the background. Set the type in a layer above it. One background then serves six headline variants, four languages and every future edit for free.
add to every social prompt
“…no text, no letters, no words, no logos. Leave the lower third visually calm for overlaid type.”
Social graphics questions
Should I generate one image and crop it for each platform?
No. Generate each ratio natively. A model composing for 9:16 puts the subject where a vertical frame wants it; cropping a square into a story leaves you with a subject stuck in the middle and dead space top and bottom.
How do I keep a campaign visually consistent?
Approve one image, then pass it in referenceImages for every other size and variant. Reference images do far more for consistency than repeating adjectives, because they give the model the thing itself rather than a description of it.
Can I put the caption text in the image?
Better not to. Models still handle small type unreliably, and baked-in text cannot be localised or A/B tested. Generate a text-free background, then overlay type in your design tool or at render time — which also lets one background serve six headline variants.
What about logos and stickers that sit over other content?
Those need transparency. Use generate_transparent_image so the asset arrives on a real alpha channel and can sit on video, on a photo, or on a brand colour that changes per campaign.
How many credits does a campaign cost?
A four-platform set from one concept — 1:1, 9:16, 16:9 and a transparent sticker — is roughly 60 credits on a fast model plus 4 for compression. Ten campaigns a month sits inside the Starter plan.