Zalando adds light grey behind white packshots: what to upload
Zalando says it applies a light grey background to primary packshots submitted on white. Send pure white, not grey. How to ask Sume for it.

Zalando's image guidelines say it automatically applies a light grey background to primary packshots that were submitted with a white background (read 2026-10-02). So send a primary packshot on pure white (R255 G255 B255) and let Zalando apply the grey; do not generate your own grey background.
What the page says
The page was marked last updated October 1, 2026 when read. Below are the background lines from Zalando's image guidelines and the Premium/Designer guide (both read 2026-10-02).
| View | Background |
|---|---|
| Primary packshot | White; Zalando applies a light grey automatically |
| Designer packshot | White, mandatory R255 G255 B255 / #FFFFFF |
| Designer model view | Grey/beige, best practice R241 G241 B241 / #F1F1F1 |
| Other views | Plain, lifestyle or ambient settings |
Why a pure white file matters
If the grey is applied to a white background, an off-white or tinted file may not take it cleanly. A soft grey shadow baked into the image can also read as a different article background. Ask for pure white and a clean edge, and keep any ground shadow subtle.
Asking Sume for it
Use an edit on your real photo: keep the garment identical, replace only the background with pure white. Send the photo in input_references as a public HTTPS URL, and use aspect_ratio: "auto" to match the reference (Image API). Models vary on background support; the docs list auto, transparent and opaque for ChatGPT Image 2.5, so opaque is the closest option, read the catalogue for others.
Then sample the corner pixels of the result yourself. Models can return 254 or 250 where you wanted 255, and the check is cheap.
A quick corner test
Open the result, sample the four corner pixels and the middle of each edge, and expect 255, 255, 255. Anything else is a failed edit. For a batch, script it: any image where a sampled pixel is below 255 on any channel is sent back for another pass. It takes seconds per image and prevents a visible tint reaching the catalogue.
Batch note
One edit job per SKU, an Idempotency-Key each, and a pixel check as the gate before upload (Jobs and results). The frame rule is a separate check: the article sits near 80% of the frame (framing post).
Sources
Related posts
More in Use cases
- AI album cover generator: square art at 3000×3000
Generate square album art, then upscale: Apple recommends at least 3000×3000. On Sume, generate 2400×2400 and upscale it 1.25× to reach 3000×3000.
- AI avatar for online course videos: build and update lessons
Use an AI avatar as your online course instructor: one reusable avatar, a short talking video per section, captions, and one Timeline join per lesson.
- Talking avatar for PowerPoint presentations, slide by slide
Make a talking avatar presenter for PowerPoint: one Sume clip per slide, up to 60 seconds each, in 16:9 or 4:3 to match the slide, inserted as MP4.
- AI avatar for YouTube videos: Shorts and long-form
Use an AI avatar in YouTube videos: a 9:16 talking video of up to 60 seconds for a Short, or 16:9 segments joined into one long-form video.
Written by Sume