The create_image endpoint generates entirely new images from text prompts, with optional reference images for style or content guidance (up to 9 references). The modify_image endpoint edits an existing source image based on text instructions, preserving overall composition while applying your described changes.
Was this article helpful?
That’s Great!
Thank you for your feedback
Sorry! We couldn't be helpful
Thank you for your feedback
Feedback sent
We appreciate your effort and will try to fix the article