I Started with Two Reference Images and a Simple First Prompt

I Started with Two Reference Images and a Simple First Prompt — generated with Nano Banana Pro

What this prompt does: Produces a character portrait image using Nano Banana Pro. Style cues: cinematic, dramatic. Sourced from a verified fair-citation repository (Shine by Nous ✨) and reproduced here unchanged with full attribution per the source license.

Prompt
I started with two reference images and a simple first prompt:
" Change the clothes of the woman to the {argument name="new outfit" default="yellow and green outfit"}, keep her face the same" 

Once I had that result, I reused the generated image as the new base. 
I added a fresh outfit reference and kept the prompt structure identical, only changing the outfit name:

"Change outfit to [NAME] outfit"