Home Depot primary image: 1000x1000 white and what to ask Sume
Home Depot's content best-practices sheet: product only, plain white, 1,000x1,000 minimum. The Sume model, size and background settings that match.
What does Home Depot require for the primary image?
Home Depot's Content Enrichment best-practices sheet says the primary product image should feature the product only, with no props or additional products, on a plain white background, and be at least 1,000 by 1,000 pixels to enable zoom. If the product is itself white, the sheet allows a different background, hex code #F5F5DC.
Scope matters here. This sheet is titled The Home Depot Perfect SKU and sits under Home Depot's IDM content process for suppliers; I did not read a page written for Home Depot's third-party marketplace. It also says certain categories have exceptions and points to category-specific Data Standards, which I did not read, so check your category before you build a batch.
The sheet's image rules
Besides the primary image, the sheet lists extra visual assets and says lifestyle images are strongly recommended because items with them achieve higher conversion.
| Asset | What the sheet says |
|---|---|
| Primary image | Product only, no props, plain white background, minimum 1,000 x 1,000 pixels to enable zoom |
| White products | Acceptable alternative background hex code #F5F5DC |
| Lifestyle / scene shots | Show the real-life application, in use or once installed; strongly recommended |
| Other assets | Video, alternate images and close-up detail images of special features |
| Category exceptions | Refer to category-specific Data Standards |
Which Sume settings fit?
The sheet prints the white hex as five digits, #FFFFF, which looks like a typo for #FFFFFF; the prompt below just says plain white. A 1,000 pixel edge is not a legal custom edge for ChatGPT Image 2.5, since 1000 divided by 16 is 62.5. A 1024 by 1024 request is, at 1,048,576 pixels, and it clears the 1,000 pixel minimum on both edges.
ChatGPT Image 2.5 (openai/gpt-image-2.5) takes up to 16 references and background values auto, transparent and opaque. For the lifestyle shots, the same model or any catalog model that lists input_references can place the real product in a scene; read the descriptors on GET /v1/images/models to see which.
What to ask Sume for
Request one primary shot per SKU with an opaque background, then a separate lifestyle call. Ask for white-on-white products to be handled deliberately, since the sheet allows an off-white background for them.
``json
{
"model": "openai/gpt-image-2.5",
"prompt": "Product only, centered, no props, plain white background",
"input_references": [{"type": "image_url", "image_url": {"url": "https://example.com/drill.jpg"}}],
"image_size": "1024x1024",
"quality": "high",
"background": "opaque",
"n": 1
}
``
Verify the background color of the output yourself; a prompt does not guarantee an exact hex value. See also AI lifestyle product photography for the scene side.
Sources
Related posts
More in Use cases
- How many hook clips does $20 buy: Wan 3.0 vs Seedance 2.5
Twenty dollars buys 64 five-second Wan 3.0 clips at 480p. Whole-clip counts for Wan 3.0 and Seedance 2.5 at 5, 10 and 15 seconds, from the rate card.
- How to make a TikTok micro-drama with AI: six steps and the costs
A six step workflow for a vertical AI micro-drama episode with Sume: script, shots, first frames, assembly, captions and the is_aigc flag. About $52 for 90 s.
- How to remix a video with AI: four routes by what you change
Remixing a clip means a prompt edit, a person swap, a motion transfer, or a new clip from references. Which Sume route fits each, with the fields.
- Ideogram 4 tops out at 2048 px: upscale to 4K with Sume
Ideogram 4 outputs run 256 to 2048 px per the Hugging Face card. To go bigger, send the file to Sume's image upscale endpoint: public URL, factor, poll.
Written by Sume