Prompt do canal

Foto a83

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, body proportions, exact hair length, natural hair color, hair density, and real hair
  texture. Use all uploaded personal reference photos together as a high-priority identity set. They are the sole authority for the real person's face, body, and natural appearance. Match the
  same real person exactly as shown in the personal reference photos; do not invent, reconstruct, average, beautify, idealize, stylize, or reinterpret any facial feature or body proportion.
  Preserve the real facial asymmetry, exact eye shape and size, nose, lips, jawline, cheeks, skin tone, age, and any natural marks exactly as visible in the personal photos. If the reference
  photos differ because of angle, expression, or lighting, preserve the consistent real features instead of creating an averaged or perfected face. The mood image is only for styling, standing
  courtyard pose, sleeveless black V-neck dress, black sunglasses, Louvre courtyard, glass pyramid, historic stone architecture, bright daylight, lighting, color palette, and composition. Do not
  copy the mood-image face, expression, body, hair length, hair color, hairstyle, hair texture, or proportions. Create a realistic candid travel photo of the same person standing in the Louvre
  courtyard in Paris with the glass pyramid clearly visible behind her. The photo should feel spontaneous and unplanned, like a friend took it during an ordinary sunny day, not like a
  professional fashion photoshoot. The final result must look like an ordinary unretouched smartphone photograph of this exact real person, not a beauty portrait, fashion-model interpretation,
  doll, or fictional person. Place the person in the lower center-right of the vertical frame, framed naturally from head to above the knees; she is standing with relaxed shoulders, both arms
  resting naturally by her sides, both feet grounded, and her body facing the camera with a casual everyday posture. Keep the glass pyramid and the historic Louvre façades clearly visible behind
  her. Expression and emotion must come from the uploaded personal reference photos, not the mood image. Outfit: simple sleeveless black V-neck dress with a short relaxed skirt, black sunglasses,
  and a delicate bracelet, with realistic fabric folds and no visible branding. Preserve the exact identity, facial features, natural skin texture, body proportions, and expression from the
  personal reference photos. Do not change the face, add makeup, enlarge the lips, reshape the nose, smooth the skin, or make the face more symmetrical. Preserve the exact hair length, natural
  color, density, structure, and real texture from the uploaded personal reference photos. Hair may fall naturally around the face and shoulders, but it must keep the exact personal length,
  color, density, and texture. Do not copy the mood-image hairstyle or hair texture. The courtyard scene should include the transparent glass pyramid, pale stone paving, historic Louvre façades,
  distant visitors, queue barriers, natural architectural perspective, and a clear blue sky with soft daylight. Location: the Louvre courtyard in Paris with the glass pyramid, ornate historic
  stone buildings, pale stone plaza, visitors in the distance, and bright natural daylight. Keep the city background realistic and atmospheric but secondary, not a studio and not overly staged.
  Any signs, labels or printed text must be blurred, abstract, or unreadable. Photo quality: highest available quality and maximum detail, natural iPhone 17 Pro Max or compact-camera realism,
  universal vertical 4:5 crop suitable for Instagram and Pinterest, bright direct daylight, realistic natural shadows, true skin texture, visible natural pores, true-to-life facial anatomy,
  realistic human eyes with natural iris detail and realistic sclera, fine facial microtexture, subtle natural asymmetry, natural skin depth and translucency, realistic black dress fabric,
  sunglasses, bracelet, glass, stone, architecture and plaza details, detailed courtyard textures, slight handheld framing, natural smartphone color and exposure, unretouched everyday optical
  rendering, natural sharpness without digital enhancement, subtle sensor grain, mild imperfections, no haze, no vintage blur, no cinematic grading, no AI-polished look. Negative prompt: 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 color, no altered hair
  texture, no invented facial features, no reconstructed face, no averaged face, no idealized face, no face redesign, no identity drift, no facial symmetry enhancement, no model-like face, no
  fictional person, no age change, no beauty filter, no beauty retouching, no cosmetic retouch, no skin smoothing, no face reshaping, no body reshaping, no heavy makeup, no fake eyelashes, no
  enlarged lips, no smaller nose, no doll eyes, no plastic skin, no waxy skin, no porcelain skin, no doll-like face, no glassy eyes, no artificial iris detail, no unnaturally enlarged eyes, no
  airbrushed skin, no flawless skin, no beauty-mode processing, no synthetic skin texture, no artificial eye sharpness, no artificial catchlights, no HDR face, no over-processed skin, no perfect
  symmetry, no over-posed fashion shot, no studio lighting, no missing glass pyramid, no missing black dress, no distorted pyramid, no warped architecture, no distorted hands, no extra fingers,
  no warped arms, no warped legs, no bags, no backpacks, no wallets, no belts, no bag-shaped objects, no CGI, no illustration, no readable text, no visible logos, no watermark, no screenshot UI.

O prompt está em inglês — assim o modelo entende com mais precisão. Não precisa traduzir.

O que fazer com ele

  1. 1

    Toque em «Copiar» — o prompt inteiro vai para a área de transferência.

  2. 2

    Abra o ChatGPT e cole num chat novo.

  3. 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