What this workflow creates
Remove the background from a person or product image. One image per request.
- Who it’s for
- Ordinary users, designers, sellers
- What it does
- Identify the subject and generate a transparent background
- Where to use it
- Design, e-commerce, presentation
One image per request.
What you need
- Original photo of the person or product to be cut outRequired · 1 image
- Provide body outlines, hair/edges, holes, translucent materials, and surface text that must be preserved.
- Subject to preserveRequired when applicable · 1 item
- Indicates which object is cut out. The model does not select people or products by itself.
When to provide it: When the original image contains multiple characters or product candidates
Provide every required input. Add optional inputs only when useful, and mark conditional inputs as applicable only when they apply to this request.
How to use this workflow
Open the generation form
Select “Use this workflow” to see the required inputs. You’ll need to sign in before generating.
Add the required inputs
Prepare: The original photo of the person or product that must be cut out (1 photo) + the subject that needs to be retained (1 photo). Complete every required field, add optional inputs only when useful, and mark each conditional input as applicable or not applicable.
Review text and output settings
Check “Subject to preserve” for accuracy, then choose the aspect ratio, resolution, and quality that fit this use case. The generation form shows the available options.
Generate and review
Select “Generate image,” then review the result and open the full-size image. Check it against the detailed requirements below. One image per request.
Do I need to write a prompt?
No full prompt needed—add a description when the selected option requires it.
When the original image contains multiple characters or product candidates, complete “Subject to preserve”. You do not need to write generation instructions. Use the form fields to provide the images, exact copy, data, or description requested by this workflow.
Detailed result requirements
The original photo of the person or product that must be cut out (1 photo) + the subject that needs to be retained (1 photo)
The edges of the subject should be as clear as possible and contrast with the background.
No universal public standard is available. Check the requirements of the platform or service you will use.
Set the output canvas from the selected platform placement or production template, not from a reference image. Choose the option that matches this request: Transparent cutout working canvas — 1:1 (recommended). Use a different ratio only when a verified placement or production template requires it. If the platform does not require a fixed aspect ratio, use 1:1 as the recommended working canvas for transparent cutout. Compose the subject with appropriate breathing room. Create one aspect-ratio-specific deliverable per request; generate each additional placement as a separate output. Recompose for the selected ratio while preserving the complete subject, all text, and every required safe area. Never stretch the subject or treat cropping important content as adaptation.
Body outlines, fine hair, hair and translucent edges.
No universal public standard is available. Check the requirements of the platform or service you will use.
No fill/transparent.
No universal public standard is available. Check the requirements of the platform or service you will use.
No universal public standard is available. Check the requirements of the platform or service you will use.
No universal public standard is available. Check the requirements of the platform or service you will use.
Transparent PNG.
Automatic recognition may accidentally delete fine hair or low-contrast areas, which must be checked and restored.
Official and platform requirements
No universal public standard is available. Check the requirements of the platform or service you will use.
FAQ
What can I create with this workflow?
Remove the background from a person or product image. One image per request.
Do I need to write a prompt?
When the original image contains multiple characters or product candidates, complete “Subject to preserve”. You do not need to write generation instructions. Use the form fields to provide the images, exact copy, data, or description requested by this workflow.
What do I need to upload?
“Original photo of the person or product to be cut out”: 1 image; required. JPG, PNG, and WebP are supported, up to 10 MB per image.
What does one generation produce?
One image per request.
Common search terms
Public evidence and sources
1 directly relevant public source has been found, and 5 types of specific constraints have been extracted. The following content only restates information that appears clearly from the source; no filling in of blank fields will be made.
