Create from a prompt
Generate logos, product shots, social creatives, UI mockups, and concept art from a written idea.
Generate and edit images with GPT Image 1.5
A fast OpenAI image model for production-ready visuals. Describe what you want, or upload a photo and change only the parts that matter — including cutouts with transparent backgrounds.
Text to imageImage editing
3
What it is good for
Generate and edit images with GPT Image 1.5
A fast OpenAI image model for production-ready visuals. Describe what you want, or upload a photo and change only the parts that matter — including cutouts with transparent backgrounds.
Edit what you already have
Try new clothing, restyle a room, translate on-image text, remove objects, or place a product in a new setting.
Keep characters consistent
Reuse the same look across scenes for stories, campaigns, and multi-frame boards.
Key capabilities
Why creators pick GPT Image 1.5
Fast when you need volume
Ideal for drafts, iterations, and campaign batches where speed and cost matter as much as quality.
Readable text in the frame
Posters, mockups, labels, and marketing layouts with lettering that stays clear enough to use.
Edits that keep the subject
Change an outfit, lighting, or prop without rewriting the whole photo. Faces and composition stay put when you ask.
Transparent backgrounds
Create cutouts and overlays when you need a clean subject on a transparent background.
Work from your own photos
Upload one image to edit it, or several to blend style and subject into a single result.
How to get a strong result
Tips for better results
Start with the subject, then add lighting, style, and anything that must stay the same. Upload a reference whenever you want a more controlled edit.
- 1
Say what you want
Be concrete. “Add soft coastal daylight” works better than “make it better.”
- 2
Describe the look
For photos, mention lighting and framing — soft daylight, close-up, wide shot — so the result feels intentional.
- 3
Protect what should stay
When editing, spell out what must not change: the face, pose, outfit, or camera angle.
- 4
Put words in quotes
For text inside the image, write the exact line in “quotes” and say how it should look.
- 5
Change one thing at a time
Start with a strong base image, then refine with small, clear adjustments.
- 6
Point to each reference
With several uploads, say how they relate — “use the style from the first image on the person in the second.”
Series compare
Compare GPT Image versions
Pick the version that fits your workflow — then open its page to create with that model locked in.
| Feature | GPT Image 2 Open page | GPT Image 1.5Current You’re viewing this model |
|---|---|---|
| Best for | Complex prompts, in-image text, photoreal products | Everyday production work and cutouts |
| Speed | Balanced | Fast |
| On-image text | Excellent | Very good |
| Transparent background | Not supported | Supported |
| Sizes & framing | Wide range, up to 4K experimental | Standard ratios |
| Editing | Up to 16 references | Strong prompt following + input fidelity |
More models
Try another model
Explore popular image models outside this series, or browse the full catalog.
Nano Banana 2
Fast Gemini image generation with sharp text, wide aspect ratios, and up to 4K.
Nano Banana Pro
Studio-grade control for posters, mockups, and multi-image blends with pro-level detail.
Seedream 5 Pro
ByteDance flagship Seedream 5 Pro for sharp 1K/2K generation and editing.
FLUX.2 Pro
Flagship FLUX.2 quality for generation and editing with up to eight references.