Product shadow: add a natural shadow to a product photo
A product shadow grounds the item on its surface. Cut-outs lose it; add it back with an AI image edit, or keep it by changing only the background.

A product shadow is the soft dark area a product casts on the surface below it, and it is what makes the item look like it stands on something instead of floating. A cut-out product photo loses its shadow; to add one back, edit the flattened image with an AI image model and ask for a soft contact shadow on the surface, or keep the original shadow by changing only the background instead of cutting the product out.
The steps below use Sume's Image API and the OpenAPI document behind the Sume API reference, read on 2026-09-28.
What kinds of product shadow are there?
- Contact shadow: a thin, dark line where the product touches the surface. It does most of the work of grounding the product.
- Drop or cast shadow: the longer, softer shape the product throws away from the light.
- Reflection: a faint mirror image on a glossy surface, used for glass, electronics, and jewelry.
- Natural or added: a shadow from the original shoot, or one drawn in afterwards.
Why does my cut-out product look like it's floating?
A background remover keeps the subject and makes everything else transparent. The shadow lies on the background, so a cutout can lose it. Sume RMBG 1.0 (POST /v1/rmbg-1.0/remove) returns a PNG with alpha; placed on white, a product without a shadow reads as pasted on. Remove background API covers the cutout itself.
How do I add a shadow to a product photo with AI?
Two routes. To keep the shadow you already have, don't cut out at all: edit the original photo, change only the background, and say the shadow stays. How to change the background of a photo with AI covers that edit. To add a shadow to a flat image, such as a cutout already placed on white, send it as a reference and describe the shadow:
curl -X POST "https://api.sume.com/v1/images" \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openai/gpt-image-2.5",
"prompt": "Add a soft, natural contact shadow directly under the bottle and a faint shadow falling to the right, as if lit by a large soft light from the upper left. Keep the bottle, its label, and the white background exactly the same.",
"input_references": [
{ "type": "image_url", "image_url": { "url": "https://example.com/bottle-on-white.png" } }
],
"aspect_ratio": "auto",
"n": 3
}'What should the shadow prompt say?
- Where the light comes from, so the shadow falls the opposite way.
- How soft the shadow is and how far it reaches.
- The surface: a white sweep, a wooden table, a stone slab.
- What stays: the product, its label, its colors, and the background.
- For a set of products, the same wording on every image, so the shadows match.
Can I get a transparent PNG that keeps the shadow?
Not with the steps on this page. The cutout is the transparent file here, and the RMBG reference doesn't describe keeping a shadow in it; the AI-drawn shadow lands in an ordinary image with its backdrop. Plan on shadows baked into an opaque image, on white or on a colored backdrop.
| Step | Endpoint | Returns | Price |
|---|---|---|---|
| Cut out (optional) | POST /v1/rmbg-1.0/remove | A PNG with alpha | $0.0225 per image, plus a 5.5% agent fee by default |
| Add or keep the shadow | POST /v1/images | Images on the backdrop you asked for; result URLs are signed, so download them | Per completed image; failed or cancelled generations are not billed |
Sources
Related posts
More in Use cases
- How to add a video to a Shopify product page
Add a video to a Shopify product page from the product's Media section: upload the file or paste a YouTube or Vimeo link. Your theme must support video.
- AI 360 rotation video: spin a product from two photos
From one photo, AI invents every side it can't see. For a 360 rotation video, pin the front and back as frames, make two half turns, and join them.
- AI avatar for events: a host for screens and lobby loops
An AI avatar can host an event's scripted parts: the welcome, housekeeping, sponsor thanks, and session intros as short 16:9 clips, joined or looped.
- AI avatar for healthcare: patient education videos
Use an AI avatar in healthcare for general patient education: short, clinician-reviewed videos, captioned for waiting rooms, with no patient data.
Written by Sume