



📱 Casual phone snapshot, 9:16; 18–22 years old, clearly adult beautiful East Asian woman, about 1.75 m tall, delicate small face with clear features, cool fair skin, tall slender model figure, chest visually about a natural E cup. Light peach-blonde long hair half tied half down, cream knit sweater × floral deep V camisole dress × light-colored socks and shoes, paired with trendy personalized small accessories, fresh and sweet. 🪟 Bright bedroom by the window on a rug, light-colored bedsheets and green plants in the background, strong sunlight with slight overexposure; high-saturation dreamcore tones, leaning toward a youthful cyan cast, low-resolution phone snapshot texture, slight blur, noise, and natural exposure, like a real everyday moment captured on impulse. Random action pool: 🌤️ Sitting on the rug hugging knees, side profile looking toward the sunlight by the window 🫧 Sitting with legs naturally bent, head down adjusting the hem of the dress 📱 One hand on the ground and the other holding a phone, as if just finished taking a selfie 🌿 Sitting on the floor with back against the bed, looking up blankly at the camera 🎀 Sitting cross-legged adjusting half-tied hair, expression youthful and relaxed 🪞 Body slightly leaning forward, fingers lightly touching the side of the face or chin ☁️ Sitting by the window stretching out both legs, sunlight falling on hair strands and the dress hem 💐 Sitting on the rug hugging a throw pillow, turning back with a faint smile 🎲 Around different actions, freely vary camera angles, bedroom details, sunlight overexposure, hair strand state, and dreamcore color tones, pursuing fresh girly everyday life × low-resolution phone snapshot × bright bedroom lifestyle feel. Produce one comprehensive preview image containing different actions, so I can choose from them.
This image was generated with GPT Image 2 by OpenAI. The prompt on this page is the exact text used to create it.
The example was generated with GPT Image 2 using: 941:1672 · Cinematic · Fashion · Portrait. Reusing these settings gives the closest match.
Copy the prompt as-is first, then replace only the subject while keeping the style, lighting, and composition keywords. Generate a few variations — outputs differ between runs.
Yes. Prompts work best as starting points — adjust descriptors, aspect ratio, or style tags to make the output your own.