Original document
GPT Image 2 · en
A dynamic close-up photo of a concert, with the main subject being the performers on stage.{argument name="idol performer" default="Young J-pop female idol"} Shot from the audience's perspective, the scene features a shallow depth of field. She leans towards the camera, one hand reaching towards the foreground, creating a strong perspective compression effect; the other hand holds a black handheld microphone with a red decorative ring close to her mouth. She wears a richly detailed red and white ruffled idol costume: dark brown twin ponytails with bangs, two fluffy red pom-pom hair accessories tied with ribbon bows, red pendant earrings, a red choker with lace and heart-shaped gemstones, a lace-trimmed crop top with a large satin bow at the chest, off-the-shoulder ruffled sleeves, a cinched waist with red ribbon ties and small metal embellishments, a layered satin skirt decorated with sparkling beaded chains, and a heart-shaped gemstone ornament at the waist. Her nails are glossy red with cute white decorative nail art. The lighting is vibrant pink and deep red stage lighting, creating a glamorous live idol atmosphere. The background is filled with soft blurring effects, LED screens, stage setups, and countless glowing and floating heart-shaped confetti, creating a dreamy and romantic concert scene. Employing a photorealistic style, it showcases clear fabric textures, shimmering satin highlights, lace details, concert atmosphere, subtle dynamic energy, and the overall {argument name="color theme" default="Red and pink"} Color scheme. It blends a subtle sense of excitement with a fan-oriented stage presence, like {argument name="theme" default="Cute and romantic idol concert"} Photos of the promotional performance.How to use
- Copy the complete original prompt, including any parameters.
- Replace the subject, text and composition with your own requirements.
- Use a compatible external tool; check its current access conditions and review the result.
Before you start
- Check whether a reference image is required. A compatible model label does not mean this example was generated with that model.
- Keep names, figures and visible text accurate; results can vary between model versions.
