How to make AI product photos from a phone photo

Steps

1. 1

   Open the AI Product Photo Generator

   Go to the AI Product Photos tool page. The studio there is set up for product shots, and the prompt already tells the model to keep the product's shape, colors, label and text. You can set it up before you sign in.

2. 2

   Upload your product photos

   Under Product photos, add 1 to 4 clear photos of the product; a plain background works best. Nano Banana takes up to 3, the other models 4. If you are not signed in, a sign-in box opens when you upload: create an account with an email and password, or continue with Google.

3. 3

   Pick a scene

   Choose a marble counter with soft morning light (the default), a white seamless studio background, a wooden table with plants, floating with splashes of water, a podium with pastel shapes, or a festive holiday setting.

4. 4

   Choose a model

   Seedream 4.5 is selected by default. The menu also has Seedream 5.0 Lite, Riverflow 2.5 Pro, Nano Banana, Nano Banana Pro, GPT Image 2 and FLUX.2 [pro].

5. 5

   Set the shape and number of images

   Square 1:1 is preselected; 4:3, 3:4, 16:9 and 9:16 are also there. Seedream 4.5, Seedream 5.0 Lite and GPT Image 2 can make up to 4 images in one run.

6. 6

   Press Generate

   The button shows the credit price before you spend anything, multiplied by the number of images you picked. The shots appear in the results panel after a short wait.

7. 7

   Check the label, then download

   Zoom in on the label and any text before you use a shot, then download it. For a transparent PNG, run the result through the Background Remover.

Tips

• Shoot the product straight on in daylight against a plain wall for the cleanest reference.
• Upload more than one angle for products with text on several sides.
• Use the same scene for every product so the catalog looks consistent.
• Open "Prompt sent to the model" under the settings to see the exact prompt.

Troubleshooting

The label text or logo came out wrong

Generate again, or switch to Riverflow 2.5 Pro or Nano Banana Pro, which hold product text best. Always check text before publishing.

The product shape changed

Upload a sharper photo taken straight on with a plain background, and add a second angle.

I cannot add a fourth photo

Nano Banana takes up to 3 reference photos. Switch to another model to use 4.

The message says "The model's safety filter rejected this request"

The model provider refused the request. Credits are refunded up to a daily limit. Try another model.

The upload says "File is too large" or "Unsupported file type"

Use a PNG, JPEG or WebP under the size limit shown in the message.

The generation failed

The credits are refunded automatically and the result card says so. Try again or pick another model.

Questions