Performance Max logo assets: 1200x1200 square and 1200x300 landscape
Performance Max takes a 1:1 logo at 1200x1200 (minimum 128x128) and a 4:1 landscape logo at 1200x300. How to prepare both with Sume. Read 2026-10-03.

Performance Max wants two logo shapes: a square 1:1 logo recommended at 1200x1200 pixels (minimum 128x128) and a landscape 4:1 logo recommended at 1200x300. Both ratios are on Sume's image aspect-ratio list, but an image model should adapt your existing logo, not invent a new one.
The logo requirements
These values come from the Google Ads API page on Performance Max asset requirements, read on 2026-10-03.
| Asset | Ratio | Recommended size | Minimum size |
|---|---|---|---|
| Logo | 1:1 | 1200x1200 | 128x128 |
| Landscape logo | 4:1 | 1200x300 | Not read |
File formats
The page lists GIF, JPG and PNG as accepted image formats. A logo with a transparent background should be a PNG, because JPG has no alpha channel and would put a solid box behind the mark on any colored placement.
What an image model should and should not do
A generative model is poor at reproducing an exact wordmark from a text description, and a brand mark that drifts between assets undermines the point of a logo. The safer routes:
- Export the square and landscape logos from your design files whenever you have them.
- Use Sume only for derivative work: extending a background, producing a clean padded canvas, or making a transparent-background variant from a reference.
- Pass the real logo as an
input_referencesentry and ask for it unchanged, then compare the output to the original at full size. - Never ship a logo you have not looked at pixel by pixel; a single dropped letter is easy to miss at thumbnail size.
Ratios and transparency on Sume
The Image API lists 1:1 and 4:1 among its normalized aspect ratios, and a given model accepts only the subset in its catalog descriptors. background: transparent is documented for ChatGPT Image 2.5, and output_format can be png. ChatGPT Image 2.5 takes up to 16 image references and its image_size accepts custom pixels where both edges are multiples of 16, with a maximum edge of 3840 and aspect ratio at most 3:1.
That last limit matters here: a 4:1 canvas is wider than 3:1, so check the model's descriptor before assuming a native 1200x300 output. If a model rejects it, generate the nearest accepted ratio and pad or crop to 4:1 in your own tooling.
{
"model": "openai/gpt-image-2.5",
"prompt": "Keep the logo exactly as in the reference, centered, transparent background, no extra elements",
"input_references": [
{ "type": "image_url", "image_url": { "url": "https://example.com/logo.png" } }
],
"background": "transparent",
"output_format": "png",
"aspect_ratio": "1:1"
}Final checks
Before upload, confirm the pixel size is at least 128x128 for the square logo, that the landscape file is a true 4:1 shape, and that the mark stays legible when displayed small on a dark and a light background.
Sources
Related posts
More in Use cases
- Pinterest ad disclosure: "modified with AI" or "AI-generated person"
Pinterest labels AI content from IPTC metadata, classifiers and creator disclosure. For ads you disclose via the ellipsis menu. Which wording fits which image.
- Pinterest see-fewer AI Pins: beauty, decor, fashion, food and drink
Pinterest's see-fewer GenAI controls cover beauty, art, fashion, decor, health and sport, plus food and drink from December 12, 2025. What it means for Pins.
- Seedance 2.5 C2PA, watermark and real-face rules: an ad checklist
BytePlus lists C2PA credentials, visible watermarks and real-face limits for Seedance 2.5. A checklist of what to confirm and record before an ad clip ships.
- Shopify product video: five recommended ratios at 30 to 60 fps
Shopify recommends 16:9, 9:16, 4:3, 3:4 or 1:1 video at 30 to 60 fps. Seedance 2 on Sume lists the same five ratios, so one prompt can fill a full ratio set.
Written by Sume