Poshmark listing photos are 3:4 portrait: how to make them
Since March 2026 Poshmark listing and cover photos are portrait 3:4 instead of square. Request 3:4 from the Sume Image API and reframe old square shots.

Poshmark listing photos and cover photos are now portrait, 3:4, instead of 1:1 square, according to Poshmark's own March 25, 2026 post. Existing square photos remain in listing details. If you make photos with Sume, set aspect_ratio to 3:4 in the Image API and you get a portrait frame directly instead of cropping a square.
This is from the Poshmark blog, read on 2026-10-02. The post gives no pixel size, file size or photo count, so this article does not either. Check Poshmark's seller help for anything beyond the ratio.
What changed on Poshmark?
Poshmark describes a switch in how listings display photos.
| Item | What the page says |
|---|---|
| Post date | March 25, 2026 |
| Listing photos | Portrait 3:4 instead of 1:1 |
| Cover photos | Portrait 3:4 instead of 1:1 |
| Existing square photos | Still shown in listing details |
| Pixel and file-size limits | Not stated on the page |
Is AI-generated photo content allowed on Poshmark?
The Poshmark page does not say. It covers the portrait ratio only. Before you generate anything, read Poshmark's current seller policy; a listing photo still has to show the item you are selling. A generated backdrop is not the same as your item, so keep generated images for promotion and use real photos in the listing.
How do I request 3:4 from Sume?
The Sume Image API accepts aspect_ratio values that include 3:4, and input_references takes up to 10 public HTTPS images. Explicit pixel size is not served and returns 400 unsupported_parameter, so use the ratio plus a resolution tier.
If the call takes longer than 30 seconds you get a 202 with a job envelope instead of an image; read it from status_url. Failed or cancelled generations are not billed.
import os, requests
r = requests.post(
"https://api.sume.com/v1/images",
headers={"Authorization": f"Bearer {os.environ['SUME_API_KEY']}"},
json={
"model": "sume/auto",
"prompt": "Reframe this exact jacket as a vertical portrait photo on a plain neutral wall, soft daylight, do not alter the jacket",
"input_references": [
{"type": "image_url", "image_url": {"url": "https://example.com/closet/jacket.jpg"}}
],
"aspect_ratio": "3:4",
},
timeout=60,
)
body = r.json()
if r.status_code == 200:
print(body["data"][0]["url"])
else: # 202: poll the job
print(body["data"]["status_url"])
What about the square photos I already have?
Poshmark says they stay visible in listing details, so you do not have to redo everything. For the cover photo, which is the first thing a shopper sees, a portrait reshoot is the cleaner fix. For anything you reshape with AI, compare it with the original before posting, because a changed color or missing detail is the fastest way to a return.
Sources
Related posts
More in Use cases
- Turn a product changelog into a 30-second update video
Convert release notes into a short update video: pick three changes, write a 70-word script, voice it with TTS, add real screenshots and render with Timeline.
- Launch teaser from product shots: Gemini Omni Flash reference images
Feed up to 10 product references to gemini-omni-flash-1.1 on Sume, address them as IMAGE_REF_0 in the prompt, and get a 3-10 second teaser with native audio.
- Product photo on a white background: one image edit call on Sume
Turn a messy product photo into a clean white-background shot with one POST /v1/images edit. Which model, which fields, and what to check before you publish.
- Re-roll one shot in a stitched film without redoing the rest
Regenerate a single bad shot, swap its source_url in the Timeline 1.0 video array, and re-render the cut for $0.10 per output minute. The other shots stay.
Written by Sume