GPT Image 1.5 AI Image Generator

Frequently asked questions

What is GPT Image 1.5?

GPT Image 1.5 is OpenAI's image generation model that creates and edits images from text prompts. It supports multi-image input, precise text rendering on images, and outputs in medium or high quality modes.

What can I create with GPT Image 1.5?

You can generate images from text descriptions, edit existing images with natural language, combine multiple reference images, and create visuals with accurate embedded text like posters, logos, or infographics.

How is GPT Image 1.5 different from DALL-E or other models?

GPT Image 1.5 offers better text rendering accuracy, supports up to 16 reference images as input, and delivers higher fidelity output. It is OpenAI's latest image generation model with better instruction following.

Can I upload multiple images at once?

Yes. Officially, GPT Image 1.5 accepts up to 16 input images, and Viw AI currently supports up to 16 images per generation. You can use them for style reference, composition blending, or editing multiple elements in a single generation.

What's the difference between medium and high quality?

Medium quality (7 credits) is faster and suitable for drafts and iterations. High quality (37 credits) delivers sharper details, better color accuracy, and is ideal for final output.

Does GPT Image 1.5 handle text in images well?

Yes. Text rendering is significantly improved in GPT Image 1.5 and works well for signs, labels, titles, watermarks, and typographic designs. Complex layouts may still need iteration.

What aspect ratios are supported?

GPT Image 1.5 supports 1:1 (square), 2:3 (portrait), and 3:2 (landscape) aspect ratios. Choose the one that fits your use case.

Is GPT Image 1.5 free to use?

You get free credits when you sign up. Medium quality costs 7 credits and high quality costs 37 credits per image. Failed generations refund your credits automatically. See our Pricing page for details.