
A highly realistic photograph taken with a small digital camera from the early 2000s, 4:3 landscape. Use the reference only to preserve the face and continuity of the same fictional woman character. Hair covered by a floral headscarf tied back, a few strands of hair have escaped. Clothing: a layered traditional dress in earthy brown and maroon tones, a woven wool vest over it, wool socks inside plastic shoes, her hands rough and dried from work, a small wooden loom on her knees. Scene: The mouth of a black goat-hair tent on a Zagros highland at midday, green grass, a tethered goat, a metal teapot on burning leaves, traces of snow on the peaks behind, a plastic chair, a pile of oak wood. A fresh, unposed natural moment: Shot from below, as if someone were sitting on the grass in front of her, about a meter away. She is mid-sentence talking to someone on the left, outside the frame, holding a woven bag with one hand, gesturing with the other, her face calm, a small frown between her eyebrows, a strand of hair fallen into her mouth. The goat's head enters the corner of the frame. Camera: Old small digital camera look, slight light halos around the edges from over-sharpening, purple fringing on the bright sky edge, small sensor grain, washed-out and lifeless colors, somewhat the softness of dated photos from that era, no flash. Random composition: Her knees are cut off by the frame, the tent edge cuts the image from above, too much grass at the bottom. Light and exposure: Harsh midday light, sky somewhat overexposed and white, deep shadow inside the tent behind her, strong shadows under her eyes and chin, her cheeks reddened by the wind, dust and wool fibers on the fabric. Aesthetic: Family archive realism, like a photo found on an old memory card, warm and unadorned. Real skin, real hands, real fabric. By no means: National Geographic magazine gloss, cinematic color grading, professional blurred background, staged and posed studio portrait, skin retouching and beautification, overly broad bright lighting colors, symmetry, props placed for the scene, or the flawless AI body.
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: 4:3 · Nature · Realistic · 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.