Zalando apparel model views: same model, shoes on, sleeves shown
Zalando's apparel guide for model views: same model and styling across views, shoes on, full-length sleeves, simple styling. What to put in an AI prompt.

Zalando's apparel guide asks for one compliant primary packshot or front crop as the catalogue view plus two further compliant images, with the same model and styling in every view of an article, shoes on, and tops with sleeves shown at full length. It also says to keep styling simple so the product stays the focus. These rules are in the Apparel image guide, updated March 3, 2025 (read 2026-10-02), and its AI rules are on the main guidelines page. If you generate model views, those are your prompt constraints.
What does the apparel guide ask for?
The guide is specific about appearance. It asks for models representative of your size range, natural expression, and samples that fit properly. Plus-size articles use plus-size models (minimum size 44), and maternity uses a 45 degree angle with the belly to the left. Sitting models are allowed for the front crop, back view, full body style view and further views.
| Topic | What the page says |
|---|---|
| Consistency | Same model and styling for all views, except unisex and size-inclusive articles |
| Footwear | Models must wear shoes |
| Tops | Sleeves in full length, not folded, rolled up or propped |
| Styling | Simple; props discreet; extra item must not cover the main article |
| Special features | Show value-adding features in a model view |
| Back USP | If the unique feature is on the back, back and front crop are switched |
How do I keep one model across views?
Generating each view from scratch gives a different person every time. Instead, pass the same model photo, plus the garment photo, as input_references in each request, and tell the prompt which view to produce. The Image API docs say models differ in how many references they accept (GPT Image 2.5 takes up to 16), so read input_references in the model's catalog entry first.
Zalando's main page lists inconsistent facial features, body proportions and skin tones across a set as an unacceptable AI distortion, so reject any view where the person drifts.
What must the garment keep?
The garment has to match the real one. The page names mispositioned buttons, distorted text and unnatural patterns as reasons for rejection. Put print, buttons, drawstring length and logo in the prompt as things to keep, then check them. A sleeve that the model folds or rolls breaks the full-length rule even if the garment is right.
The same applies to the garment on the model: check that it sits on the body the way the real one does, with no extra seams or changed necklines.
What should I do next?
Here is the short version, in the order to do it.
- Pick one model reference and reuse it for every view of an article.
- Write shoes on, full sleeves and simple styling into each prompt.
- Check garment details and model consistency across the set.
- Photograph back USPs and details when the source photo does not show them.
Sources
Related posts
More in Use cases
- Zalando image rejection 117 and 123: too few views, a mannequin
Zalando rejects articles for missing images (reason 117) and visible mannequins in mandatory views (reason 123). Duplicates do not count. What to regenerate.
- Zalando image size: ask for 2000x2880, an exact 1:1.44
Zalando wants 1:1.44 JPEG portraits, best practice 1801x2600. Sume image_size takes multiples of 16, so 2000x2880 is an exact 1:1.44. Request it with jpeg.
- Zalando jewellery packshot: lower third, symmetry, back view
Zalando's jewellery guide: primary packshot in the lower third of the grid, a back view showing fasteners, no upside-down logos. A prompt checklist for Sume.
- Zalando packshot grid: article at about 80% of the frame, centred
Zalando's apparel and shoes grid puts the article at about 80% of the frame, centred; bags sit in the lower third. How to ask for that framing on Sume.
Written by Sume