by OpenAI
OpenAI's latest image model. 4x faster than GPT Image 1, precise edits, better consistency. Available in ChatGPT and via API.
GPT Image 1.5, released December 2025, is OpenAI's latest image generation model. It's 4x faster than GPT Image 1, with better consistency, precise editing, and native integration in ChatGPT.
The killer feature — iterate naturally in ChatGPT:
You: Create a logo for a coffee shop called "Morning Ritual"
[generates image]
You: Make the text larger and add steam rising from the cup
[precise edit, keeps everything else]
You: Change the color scheme to earth tones
[another precise edit]
GPT Image 1.5 excels at following complex instructions:
Create a product mockup of a smartphone showing a fitness app. The phone should be floating at a 15-degree angle with a subtle shadow below. The app screen shows a running dashboard with a map, heart rate at 142 BPM, and distance of 5.2km. Background is a gradient from dark blue to teal. Include the text "FitTrack Pro" below the phone in a clean sans-serif font.
"photorealistic, DSLR quality" — real-world photography
"flat vector illustration" — clean, scalable graphics
"watercolor painting" — artistic, organic
"3D render, studio lighting" — product visualization
"pixel art, 16-bit" — retro gaming aesthetic
| Use Case | Quality |
|---|---|
| Iterative design (ChatGPT) | Excellent (unique advantage) |
| Text and typography in images | Excellent |
| Product mockups | Excellent |
| Logos and branding | Very Good |
| Photo editing (in ChatGPT) | Very Good |
| Fine art | Good (Midjourney is more artistic) |
Quick tips from the community about what works with GPT Image 1.5 right now.
Sign in to share a tip.
No tips yet. Add a tip for this model.