Hi, welcome to the community!
Based on:
Because image generation is now native to GPT‑4o, you can refine images through natural conversation. GPT‑4o can build upon images and text in chat context, ensuring consistency throughout. For example, if you’re designing a video game character, the character’s appearance remains coherent across multiple iterations as you refine and experiment.
If I want ChatGPT to draw the same person in different places or poses, I do:
- Describe the person in detail the first time, what they look like, what they’re wearing, where they are.
- Give the person a name, like “Alex” or “Elena.” Tell ChatGPT, “This is Alex. I’ll use that name from now on.”
When I want a new image, I just say:
Show Alex doing something else, but keep him looking exactly the same.
For example:
