GPT Image 2socialproduct4:5 / 9:16Reusable recipe

Cold Brew Campaign Format

Keep one canned cold-brew identity coherent between feed conversion and kinetic Story creative.

Open in Retake

cold brew campaign format feed example
feed example.

Complete prompt

Copy the direction, then make it yours.

Create a {{FORMAT}} performance creative for an original canned cold brew named "MORROW COFFEE". Use {{SCENE}} with credible premium beverage photography and clear conversion hierarchy. Render only {{COPY}}. Preserve the same can and six-pack identity. Verified facts only: unsweetened, 120 mg caffeine, six-can starter pack. No platform UI, no extra text, no watermark.

Reusable variables

Swap the brief without losing the art direction.

{{FORMAT}}

Format

Choose feed or Story.

Default
portrait 4:5 feed ad
Examples
portrait 4:5 feed ad · vertical 9:16 Story
{{SCENE}}

Scene

Choose the campaign scene.

Default
a six-pack and open can on a clean morning desk
Examples
a six-pack and open can on a clean morning desk · one can over ice with a kinetic coffee splash
{{COPY}}

Copy

Exact campaign lines.

Default
"COLD BREW, CALM ENERGY.", "MORROW COFFEE", and "TRY THE 6-PACK"
Examples
"COLD BREW, CALM ENERGY.", "MORROW COFFEE", and "TRY THE 6-PACK" · "YOUR 2 PM RESET", "MORROW COLD BREW", and "SHOP NOW"

More Retake previews

Same art direction, another filled brief.

cold brew campaign format story example
story example.
copy
"YOUR 2 PM RESET", "MORROW COLD BREW", and "SHOP NOW"
format
vertical 9:16 Story
scene
one can over ice with a kinetic coffee splash

Original Retake direction

Clear prompt and preview provenance.

The subject, composition, copy, variables, and visual system are original Retake content. Every preview was generated as an original Retake Catalog asset during catalog preparation and reviewed against this exact prompt. These previews do not claim output from the target model. Source and license observations remain recorded in the internal Catalog for review.

Official model referenceGPT Image 2 modelOpenAI lists gpt-image-2 as its current image generation and editing model.