- 1024x1024, 1536x1024, 1024x1536
Sizes
- Up to 10, with optional mask
Input images
- Up to 10
Images per request
- Low, medium, high, auto
Quality levels
About GPT Image 1.5
GPT Image 1.5 is an earlier OpenAI image model in the GPT Image line. Like the newer versions, it generates images inside the same model that reads your prompt, so it follows detailed instructions well and handles in-image text better than older diffusion models.
In Masonry, GPT Image 1.5 accepts up to 10 input images for edits and references, plus an optional mask to confine a change to one area. It outputs square (1024 by 1024), landscape (1536 by 1024), or portrait (1024 by 1536) images at low, medium, high, or auto quality, and returns up to 10 images per request.
OpenAI has since released GPT Image 2 and GPT Image 2.5, which add sizes up to 3840 pixels; GPT Image 2.5 also adds xhigh and max quality. GPT Image 1.5 is still useful for existing workflows that depend on it, and for masked edits at the three standard sizes.
Why teams choose GPT Image 1.5
Choose GPT Image 1.5 when an existing workflow depends on it, or when you want masked edits at the three standard sizes. For larger sizes, higher quality levels, or new work, start with GPT Image 2 or GPT Image 2.5.
What GPT Image 1.5 can do
The capabilities that set GPT Image 1.5 apart and earn its place in a brief
Edits with an Optional Mask
Supply an image and a mask to change only the masked area, such as a label, a background, or one object, while the rest stays put.
Up to 10 Input Images
Give it products, references, or images to blend, combine, or merge, up to 10 per request.
Up to 10 Images per Request
Ask for up to 10 variations at once to compare directions in one round.
Four Quality Settings
Choose low, medium, or high quality, or let the model pick with auto. Lower settings return faster for drafts.
Strong Instruction Following
Write the layout, props, and copy as plain instructions, and it tends to keep each one.
Text in Images
Handles signs, labels, and short headlines. Proof every character before publishing.
Where teams reach for GPT Image 1.5
- Masked edits to product photos, such as swapping a background or a label
- Combining several product or reference images into one scene
- Social posts and mockups at square, landscape, or portrait sizes
- Batch variations, up to 10 per request
- Existing workflows built on GPT Image 1.5
Frequently asked questions
What teams need to know about creating with GPT Image 1.5 in Masonry
What is GPT Image 1.5?
GPT Image 1.5 is an earlier OpenAI image model in the GPT Image line. It generates and edits images from detailed instructions.
What sizes does GPT Image 1.5 support in Masonry?
Three: 1024 by 1024 square, 1536 by 1024 landscape, and 1024 by 1536 portrait. For larger sizes up to 3840 pixels, use GPT Image 2 or GPT Image 2.5.
Can GPT Image 1.5 edit only part of an image?
Yes. In Masonry it accepts an optional mask with the input image, so the change stays inside the masked area.
How many images can I give it and get back?
Up to 10 input images, and up to 10 output images per request.
Should I use GPT Image 1.5 or GPT Image 2?
For new work, start with GPT Image 2 or GPT Image 2.5, which add larger sizes; GPT Image 2.5 also adds higher quality levels. Keep GPT Image 1.5 for workflows already built on it.
Can I run GPT Image 1.5 from the command line?
Yes. Install the Masonry CLI with npm install -g @masonryai/cli, sign in with masonry login, then run masonry image with your prompt and --model gpt-image-1.5.
How does my team use GPT Image 1.5 in Masonry?
Open a Masonry canvas, pick GPT Image 1.5 from the model selector, and describe the image you need: a product shot, an ad creative, a social post. Masonry generates it, then you refine, edit, and combine GPT Image 1.5 with other models in one workspace.
Is GPT Image 1.5 free to try?
New Masonry accounts get 50 free credits to try GPT Image 2.5 Flare. GPT Image 1.5 is included in every paid plan, and the editor shows the exact credit cost before you generate.
How do I write good prompts for GPT Image 1.5?
Write the prompt as instructions: what to show, where it goes, and any exact text in quotes. For edits, say what to change and what to keep, and add a mask when the change must stay in one area. See the prompt gallery on this page for real GPT Image 1.5 prompts you can copy and adapt.
Who makes GPT Image 1.5?
GPT Image 1.5 is built by OpenAI. Inside Masonry it runs alongside 50+ image and video models, so your team can pick the right one for each brief without switching tools.
Can I see examples made with GPT Image 1.5?
Yes, the prompt gallery on this page shows real images teams have generated with GPT Image 1.5 in Masonry, each paired with the exact prompt you can copy and adapt for your own brand.
Start creating with GPT Image 1.5
Generate, edit, and compare across 50+ models in one workspace.
Guides for GPT Image 1.5
Prompt walkthroughs and examples from the Masonry blog
Explore more AI models
Compare GPT Image 1.5 with other models teams run in Masonry