Use spatial language for combining image elements
Employ clear spatial terms like 'left,' 'right,' 'foreground,' and 'background' when instructing AI to combine image elements.
When combining elements, use clear spatial language—such as left, right, foreground, and background—to describe relationships.
To accurately place or combine elements within an image, use precise directional and positional terms. This helps the AI understand the intended layout and relationships between different parts of the image.
For example, 'Add the headline “WEEKLY PLAN” in bold sans-serif, white, centered at the top, 72pt. No other text.'
When instructing AI to combine or place elements in an image, use precise spatial language. Terms like 'left,' 'right,' 'foreground,' and 'background' help define relationships and ensure accurate placement.
Spatial language provides the AI with clear positional cues, enabling it to accurately render the relationships between different elements within the image composition.
When the desired arrangement is highly abstract or does not rely on conventional spatial relationships.
- Creating images with ChatGPT ↗OpenAI · OpenAI News · Apr 9, 2026 · quoted as shared
First seen on Subvolts Apr 9, 2026. Updated Sep 11, 2026. Spotted a problem? Tell us.
- Creating images with ChatGPTOpenAI · OpenAI News · Apr 9, 2026
The Playbook: reusable how-tos, prompts, configs and tips pulled out of the news.
- HeuristicIterate on images with small, targeted revisionsRefine generated images by making small, specific changes one element at a time. · 3 min
- ChecklistChecklist for effective image generation promptsEnsure your image prompts are clear, specific, and include necessary details for best results. · 3 min
- HeuristicUse clear, specific language for image generation promptsPrioritize clarity and specific details over clever phrasing for effective image generation prompts. · 2 min
- HeuristicUse explicit constraints for fixed elements in image editingClearly state what should not change when editing existing images to maintain consistency. · 2 min
- HeuristicUse step-by-step revisions for consistent image refinementRefine images by making one adjustment at a time to maintain consistency and control. · 3 min
- HeuristicGenerate images with complex object relationships and traitsCreate images with up to 20 distinct objects, precisely bound to their traits and relations. · 5 min
Questions people ask
- Which AI tools does this work with?
- Any current model. It was seen with ChatGPT in the sources.
- Where did this come from?
- OpenAI (OpenAI News). Subvolts collected, normalized and credited it; the link above opens the original.