---
title: Testing the new gpt-image-1 model
url: https://calvin.my/posts/testing-the-new-gpt-image-1-model
published: 2025-04-26
updated: 2026-09-17
category: AI
tags:
- OpenAI
- Image
- edit
- nextbyai
summary: The post tests gpt-image-1’s generation, editing, and image-extraction capabilities across quality, size, format, moderation, and background settings. It generates an illustrated scene from a prompt, then modifies the character’s expression and replaces notice-board text with simplified Chinese. In a product-extraction test, the model creates a menu-style image from a pastry photo and adds prices, though it introduces one extra item while correctly identifying the others.
---

# Testing the new gpt-image-1 model

## Available Settings

1. Quality: auto, high, medium, low 
2. Size: auto, 1024x1024, 1024x1536, 1536x1024
3. Format: jpeg, png, webp
4. Moderation: auto, low
5. Background: auto, transparent

* * *

## Image Generating

Our prompt:

```markup
A young girl, in yellow dress, looking at a notice board.
The notice board says: We are closed on Monday 28/4/2025
In studio ghibli style
```

1. 1024x1024, high setting

   ![](https://camy-pub.s3.ap-southeast-1.amazonaws.com/ff13a5c1-51ef-4884-8ecc-e60f4dc627f3.webp)

2. 102x1024, medium setting

   ![](https://camy-pub.s3.ap-southeast-1.amazonaws.com/9ec3fa4a-b4bd-41b2-9da1-8b1850d460b6.webp)

* * *

## Image Editing

1. Change the facial expression

   ```markup
   Make the little girl look a bit disappointed on her face
   ```

   ![](https://camy-pub.s3.ap-southeast-1.amazonaws.com/d03a467b-dcbb-48a5-9da8-86446a9dac24.webp)

2. Multiple instructions.

   ```markup
   Translate the text on the notice board to simplified Chinese.
   Then replace the original text with the translated text.
   ```

   ![](https://camy-pub.s3.ap-southeast-1.amazonaws.com/baaa7a5e-9def-426c-84a0-10dc32ab500b.webp)

* * *

## Items extraction

1. Extract items from a photo taken by the camera. Using got-image-1 high setting.

   ```markup
   Extract the pastries in the photo.
   Design a menu-like image based on these pastries.
   ```

   Source image:

   ![](https://camy-pub.s3.ap-southeast-1.amazonaws.com/61a1bf42-3b3f-4d4a-9cb2-005189fd03bb.png)

   Output Image:

   ![](https://camy-pub.s3.ap-southeast-1.amazonaws.com/b2d06538-1f5d-43f3-a85b-690b1c7548c7.webp)

   The image shows one extra item, but the other items are correctly extracted.

2. We try to add a price to each of the items.

   ```markup
   Please add a price tag to each item in the image.
   All of them are RM 3.50, except the first item, which is RM 4.80
   ```

   ![](https://camy-pub.s3.ap-southeast-1.amazonaws.com/4e99b5d2-6783-444f-ba4c-c3deccfe9db0.webp)