GPT Image 1.5
OpenAI's updated image generation model. GPT Image 1.5 improves on GPT Image 1 with enhanced visual quality, higher prompt accuracy, and better handling of complex image instructions — the recommended OpenAI image model for most use cases.
What is GPT Image 1.5?
GPT Image 1.5 is the updated version of OpenAI's GPT Image 1 model, with improvements across visual output quality, instruction accuracy, and text rendering. It's the recommended OpenAI image generation model for users who want the best available from OpenAI's image generation family.
The 1.5 update improves the model's handling of detailed, complex prompts — more elements described in a single prompt are rendered correctly and in the right spatial relationship. The visual output quality has been improved for photorealistic scenes, human subjects, and fine textures. Text-within-image accuracy, one of GPT Image 1's distinguishing strengths, is further improved in 1.5.
For users who are familiar with GPT Image 1 and using it in production workflows, upgrading to 1.5 will produce noticeable improvements in quality across most prompt types without requiring changes to prompt style or workflow.
Enhanced quality
Improved over GPT Image 1
GPT language model
Deep prompt comprehension
Better text rendering
More accurate in-image text
Higher accuracy
Complex prompts, better results
How to generate images with GPT Image 1.5 on project.video
Open the composer
Go to your project.video dashboard. GPT Image 1.5 is available under OpenAI models in the image generation section.
Select GPT Image 1.5
Choose GPT Image 1.5 for OpenAI's best image quality. Recommended over GPT Image 1 for all new generation workflows.
Write your prompt
Write a detailed description in natural language. GPT Image 1.5 handles complex, multi-clause instructions — the clearer and more specific your description, the more accurate the output.
Generate and review
Generate and review the output. Check that all described elements are present and correctly rendered. Adjust specific elements in the prompt and regenerate to refine.
Technical specs
Best use cases
Professional product and brand imagery
Generate polished product photography, brand imagery, and marketing visuals. GPT Image 1.5's enhanced quality makes it suitable for professional commercial contexts where output needs to stand on its own.
Complex scene construction
Describe scenes with multiple subjects, specific interactions, precise environmental details, and stylistic requirements. GPT Image 1.5's improved complex prompt handling translates detailed briefs into accurate visual outputs.
Text-embedded design assets
Generate posters, book covers, packaging designs, advertisements, and any design asset where readable text is part of the visual. GPT Image 1.5's best-in-class text rendering makes it the right choice for these tasks.
Human subject generation
GPT Image 1.5 produces accurate, natural-looking human subjects across different demographics, expressions, and contexts. Applications include lifestyle photography, editorial portraiture, and diverse representation in brand imagery.