How to get a white background product photo with AI
Cut the product out with a background remover and flatten the PNG onto white, or have an image model re-render the shot on white. Both with Sume.

To get a product photo on a white background with AI, cut the product out with a background remover and place the transparent PNG on a pure white canvas, or send the photo to an image model that edits from references and ask for a white studio background. The cutout leaves the white to you; the model redraws the whole picture, so check the product and the white afterwards.
With Sume, the cutout is a Sume RMBG 1.0 job, specified in the OpenAPI document behind the Sume API reference, and the re-render is a POST /v1/images call from the Image API docs. Amazon's seller guide supplies the marketplace side. All were read on 2026-09-27.
How do I cut out the product and put it on white?
Send the photo's public HTTPS URL as image_url to POST /v1/rmbg-1.0/remove. The job runs async by default, so poll GET /v1/jobs/:id/status, then read GET /v1/jobs/:id/result for a PNG with an alpha channel.
- RMBG 1.0 stops at the cutout, and its request has no background color field. Place the PNG on a white canvas in any image editor, then export the flattened file.
- Sume fetches the URL itself. Localhost, private-network, non-HTTPS, and non-image responses are rejected before generation submission.
- Each job takes one
image_url. Remove background API covers modes, webhooks, and results in full.
curl -X POST https://api.sume.com/v1/rmbg-1.0/remove \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"image_url": "https://example.com/inputs/mug.jpg",
"mode": "async"
}'Can an AI model put the product on white in one step?
Yes, as an edit. Send the photo in input_references to POST /v1/images on a model that takes references, such as ChatGPT Image 2.5, and ask for the white background in the prompt. The call waits up to 30 seconds and returns 200 with Sume-hosted, signed image URLs, or 202 with a job if it runs longer. Check two things before you use a result:
- The product. The model generates a new picture, so a label, logo, or small print can come back changed.
- The white. No Image API field sets an exact background color, so check the corners with a color picker when a store asks for pure white.
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": "Studio product photo on a pure white background. Keep the mug and its label identical.",
"aspect_ratio": "1:1",
"n": 2,
"input_references": [
{ "type": "image_url", "image_url": { "url": "https://example.com/inputs/mug.jpg" } }
]
}'What does Amazon ask for in a product photo?
Each marketplace publishes its own image rules, so read the one you sell on. Amazon's product photo guide for sellers is one example:
| Topic | What Amazon's guide says |
|---|---|
| Background | In most cases, a white background (RGB color values: 255, 255, 255) |
| Framing | Have the product fill 85% or more of the frame |
| Size | 500 to 10,000 pixels on the longest side; images larger than 1,000 pixels on each side are preferred, to allow for zoom |
| File type | JPEG, TIFF, PNG, or non-animated GIF |
| Count | At least one image per product, and at least six are recommended |
How much does it cost?
Background removal is $0.0225 per image on API pricing, plus a 5.5% agent fee by default, and the public catalog adds that the price does not vary by image size. An Image API edit is billed per completed image at the model's catalog rate, and a failed generation is not billed. For a whole catalog of photos, see remove background from images in bulk.
What are the limits?
- RMBG 1.0 returns a PNG with alpha, not a flattened white image; the white canvas is your step.
- Both routes take URLs, not file bytes, and each URL must be public HTTPS.
- Nothing in an Image API request fixes the background color or locks the label, so check both in every result.
- Image API result URLs are signed. Download the files you keep.
- Store rules beyond the background, such as Shopify's image sizes, are covered in Shopify product image size.
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