ChatGPT Photorealistic Cozy Hoodie Selfie Prompt Structure and Tips
An analysis of Eesha's 9:16 portrait prompt for ChatGPT image generation, exploring subject details, lighting setups, webcam aesthetics, and practical caveats.
Image source: @MissDelulu9
Generative artificial intelligence tools frequently produce portraits marked by artificial studio gloss and rigid postures. To counter this synthetic look and capture the relaxed intimacy of personal casual photography, creator Eesha (@MissDelulu9) shared a specialized prompt on October 20, 2026, designed to generate a photorealistic close-up selfie framed in a 9:16 vertical ratio with a cozy, domestic aesthetic.
Subject Framing and Facial Detail Prompts
The prompt establishes composition by placing the subject in a tight close-up where her face fills most of the frame. Rather than a rigid frontal pose, the head tilts slightly with the cheek resting against an oversized cream hoodie sleeve. Facial cues specify silky hair with curtain bangs softly covering one eye, expressive eyes with winged eyeliner and fluffy lashes, glowing skin, dusty pink lips in a gentle pout, and a sweet expression. Calling for ultra-detailed eye focus and realistic hair texture guides the model toward crisp focal sharpness.
Styling, Lighting, and Background Composition
The scene balances cozy styling with environmental lighting. The oversized hoodie slips off one shoulder to reveal the collarbone, creating a casual look. Warm indoor lighting illuminates the subject, while a shallow depth of field renders the beige-gray background softly blurred. Muted pastel tones and an authentic webcam selfie vibe complete the relaxed atmosphere. Commenter Zidan (@liluocheng13) confirmed this effect, noting that the soft beige-gray backdrop and cream hoodie convincingly sell the webcam mood alongside attractive pastel tones.
Practical Implications and Inherent Caveats
Emphasizing casual webcam cues helps creators avoid the plastic sheen common in AI imagery. However, practical caveats remain when running this prompt across varying models. Complex physical contact, such as resting a cheek against thick fabric while exposing an off-shoulder collarbone, can trigger clothing distortion or anatomical clipping. Additionally, shallow depth of field settings occasionally blur hair edges or clothing boundaries unevenly. Generating the exact pastel palette and eye clarity shown in the source requires multiple seed trials and fine-tuning.