Why this works
The phrase “four stacked berry gummies over one eye” supplies the image’s distinctive vertical focal accent, while “tight framing” keeps the face and product gesture dominant in the portrait-closeup composition. “Soft spring-green gradient” and “diffused natural daylight with gentle highlights” establish the fresh wellness mood, with the reported brown and white dominance likely coming from the auburn hair, warm skin, gummies, and clean highlights. “Sharp focus on the face and gummies” paired with “subtle natural skin texture” balances polished campaign clarity against realistic detail.
FAQ
→How do I make the gummies more prominent than the woman’s face?
Replace “holding four stacked berry gummies over one eye” with “holding four oversized berry gummies directly in front of the camera, centered in the foreground, with the face softly behind them,” and change “sharp focus on the face and gummies” to “sharp focus on the gummies, slightly softer focus on the face.”
→How do I shift this from cheerful wellness to a darker, more luxurious beauty campaign?
Replace “soft spring-green gradient” with “deep forest-green to black gradient,” “diffused natural daylight” with “controlled low-key studio lighting with a narrow warm key light,” and “cheerful polished wellness aesthetic” with “moody luxury skincare campaign aesthetic.”
→How do I create a consistent series of variations from this portrait?
Keep “tight framing,” “sharp focus on face and gummies,” “realistic skin detail,” and “editorial beauty photography” unchanged, then vary only “spring-green gradient” with colors such as “lavender,” “peach,” or “cobalt blue,” and replace “berry gummies” with one flavor at a time, such as “citrus gummies,” “peach gummies,” or “mint gummies.”
Learn the technique behind this
- Why can't AI spell, and how do I get readable text in an image? — Older diffusion models had no character-level representation of text, so they produced letterform-shaped texture instead of words.
- Why does AI get hands and faces wrong, and how do I fix it? — Hands fail because they're small in frame, extremely variable in pose, and self-occluding — the model has less usable signal per pixel than for any other body part.
- How do I keep the same character across multiple images? — Text prompts alone won't hold a face across images — a description defines a type, not a person.
Related prompts
Playful brunette beauty ad portrait
Red Lip Balm with Lychee Freshness
Premium wellness pouch with golden spices
Teal-Accented Bunny Toy Studio Portrait
