by OpenAI
OpenAI's latest image generation model integrated into ChatGPT with strong text rendering.
GPT Image 1 is OpenAI's natively multimodal image generation model — a GPT-4-class transformer that produces high-fidelity images from natural language prompts. It excels at typography, multi-style generation, and in-place image editing, succeeding DALL-E 3 as OpenAI's flagship image model.
GPT Image 1 inherits GPT-4's language understanding — write prompts like you'd describe to a designer:
A product photo of a matte black wireless speaker on a marble surface,
soft studio lighting from the left, slight reflection on the surface,
minimalist composition, 4K quality
For text rendering, be explicit about what text to include:
A vintage-style movie poster for "The Last Algorithm" featuring
a silhouette of a programmer against a neon cityscape,
the title in bold art deco font at the top
Upload a reference image and describe changes naturally:
Change the background to a sunset beach scene while keeping
the subject exactly the same
| Parameter | Description |
|---|---|
| size | 1024x1024, 1792x1024, 1024x1792 (auto-upscale to 4K available) |
| quality | low, medium, high |
| background | transparent or opaque |
Quick tips from the community about what works with GPT Image 1 right now.
Sign in to share a tip.
No tips yet. Add a tip for this model.