Prompt do canal
Foto a56
Copie o prompt, cole no ChatGPT e anexe suas fotos. Ele vai fazer essa mesma foto com você.

Prompt
Use the uploaded personal reference photos as the only reference for identity, face, facial expression, emotion, body proportions, exact hair length, natural hair color, natural hair structure, and real hair texture. The mood image is only for styling, motion pose, oversized plaid shirt outfit, glasses, shoulder bag, parking garage setting, lighting, and composition. Do not copy the mood-image face, expression, emotion, body type, hair length, hair color, hairstyle, or texture. Create a maximally realistic candid iPhone photo of the same person walking through a parking garage or concrete underground space, caught mid-motion while adjusting her hair or glasses. Outfit: oversized brown-and-gray plaid button-up shirt worn loose and slightly open over a simple dark fitted tank top with proper coverage, relaxed blue jeans, black shoulder bag with a chain strap and no visible brand logo, thin rectangular glasses, simple jewelry, short neat French manicure. The pose is active and clear: body facing the camera while walking forward, both hands lifted near the hair or glasses as if adjusting them, shoulders loose, shirt sleeves slightly moving, natural expression from the personal references. The moving hands, hair tips, and shirt sleeves may have subtle subject motion blur, while the face, eyes, glasses, outfit, and garage background remain mostly sharp; it should look like the subject moved during the shot, not like the photographer’s hand shook. Preserve exact identity, facial features, skin tone, natural facial proportions, real body proportions, and expression from the personal reference photos. Make the face look like a real unretouched iPhone photo: visible pores, real skin texture, peach fuzz, natural under-eye texture, slight unevenness, small imperfections, tiny blemishes if present, natural skin shine, real lip texture, real eyelashes, natural eyebrows, natural asymmetry. Do not make the face cleaner, smoother, prettier, younger, slimmer, more symmetrical, more made-up, glossy, or model-like. No beauty retouching, no beautification, no beauty filter, no airbrushed skin, no poreless skin, no plastic skin, no waxy skin, no skin smoothing, no face reshaping, no jaw reshaping, no nose reshaping, no lip enhancement, no enlarged lips, no added lashes, no fake eyelashes, no glam makeup, no doll eyes, no cosmetic retouch, no polished AI face. Preserve exact hair length, natural color, density, structure, and real texture from the uploaded personal reference photos. Hair may move naturally with the hand motion, but visible hair must keep the exact personal length and texture. Do not copy the mood-image hairstyle, do not shorten, lengthen, over-smooth, add salon volume, or change the natural hair. Location: minimal concrete parking garage or underground interior with pale concrete floor, low ceiling, soft daylight or fluorescent overhead light, distant parked cars or blurred garage details, open space, and realistic urban atmosphere. Keep the background simple and secondary. Any signs, labels, license plates, or printed details must be blurred, abstract, or unreadable. Photo quality: highest available quality and maximum detail, crisp modern iPhone or compact-camera realism, universal vertical 4:5 crop suitable for both Instagram and Pinterest, natural high-resolution face detail, true skin micro-texture, realistic plaid shirt fabric, tank texture, denim folds, glasses reflections, chain bag detail, concrete floor texture, controlled subject motion blur, subtle sensor grain, slight handheld framing, no haze, no vintage blur, no AI-polished look. Realistic imperfections: slight handheld framing, tiny exposure unevenness from garage lights, natural skin shine on the nose and cheeks, small stray hair strands, real fabric wrinkles, casual shirt folds, organic shadows under the glasses, jawline, hands, shirt, bag, jeans, and concrete floor. Negative prompt: no full-image camera shake blur, no smeared face, no blurred eyes, no copied mood-image face, no copied expression, no copied body, no copied hair, no changed identity, no changed body proportions, no changed hair length, no altered hair texture, no beauty filter, no beautification, no skin smoothing, no airbrushed skin, no poreless skin, no perfect skin, no plastic face, no glossy AI face, no doll-like face, no polished AI skin, no face reshaping, no jaw reshaping, no nose reshaping, no enlarged lips, no fake eyelashes, no eyelash extensions, no heavy makeup, no glam makeup, no over-sharpened eyes, no missing plaid shirt, no missing dark tank, no missing jeans, no missing glasses, no missing black shoulder bag, no visible brand logo, no readable text, no watermark, no screenshot UI, no distorted hands, no extra fingers, no warped arms, no warped bag strap, no waxy skin, no CGI, no illustration, no warped anatomy.
O prompt está em inglês — assim o modelo entende com mais precisão. Não precisa traduzir.
O que fazer com ele
- 1
Toque em «Copiar» — o prompt inteiro vai para a área de transferência.
- 2
Abra o ChatGPT e cole num chat novo.
- 3
Anexe duas ou três fotos suas e envie. A foto chega em um minuto.
Mais prompts
Na biblioteca há mais 494 fotos
Trinta prompts novos por semana. Cada um com o exemplo pronto.
Do mesmo set





