Social Media Post - Giant Forced Perspective City Selfie

A complex prompt for gpt-image-2 utilizing forced perspective to create a 'giant woman' selfie effect in a realistic urban intersection.

提示词

2,336 字符打开 Astorie 创作台 ↗
Subject: {argument name="subject" default="A young woman, using the person in the reference image as the subject, strictly maintaining consistency in facial features, skin texture, hairstyle, glasses (if any), age, and gender. Do not change features, skin color, hairstyle, or gender. Do not use AI-style or sculpted skin; present a natural, realistic portrait effect."}
Clothing: Maintain the clothing from the reference image without modifications.
Pose: Selfie pose, one arm fully extended and raised high, holding a selfie device to capture the shot. The arm is complete and clearly visible, a key part of the frame, but the device itself must not be shown. The other hand reaches toward the lens, holding the provided {argument name="camera product" default="Canon camera product"}, positioning it as the closest and most striking subject. The head is slightly tilted toward the camera with a relaxed expression. The full body is visible from head to toe, with feet touching the ground.
Scene: {argument name="scene" default="A real urban intersection including crosswalks, road markings, traffic signs, cars, bicycles, and real-scale pedestrians, representing a grounded city street environment."}
Composition: Selfie perspective from a top-down extreme high angle, creating a natural selfie perspective. Layers: Canon camera at the forefront, followed by the face, full body, and urban background, providing depth.
Perspective Effect: Forced perspective to make the person appear giant, occupying the main frame while surrounding buildings are reduced to knee height, maintaining a shocking but spatially logical scale.
Atmosphere: Realistic, natural cinematic city life scene highlighting the scale and realistic photography without fantasy elements.
Lighting: Natural daylight, sunny or slightly cloudy, soft realistic shadows, no dramatic or neon effects.
Photography Style: Hyper-realistic cinematic selfie photography, emphasizing natural perspective and high realism.
Product Requirements: The Canon camera must remain consistent in appearance, shape, color, and logo without distortion.
Quality: Maximum photorealism, distinct layers, rich details, no AI artifacts, professional commercial quality.
Negative Requirements: No AI-drawn feel, plastic skin, distorted body parts, extra limbs, or watermarks.
Aspect Ratio: 9:16
来自原帖查看来源 ↗

更多灵感

Game Asset - Warhammer Scene: Rylanor vs Fulgrim

Game Asset - Warhammer Scene: Rylanor vs Fulgrim

Mainstream MadnessGPT Image 2
Ancient Rylanor, the Ancient of Rites of the Emperor's Children, makes his final stand deep beneath the burned world of Istvaan III. He is facing Fulgrim, the Daemon Primarch of Slaanesh.
He stands defiant, battered and half-buried in the ruins of a subterranean vault, his surviving honourable soul burning with hatred for the Traitors. Around him lie the bones of his long-dead loyalist brothers.
Game Asset - Halloween Robot at Tokyo Gym

Game Asset - Halloween Robot at Tokyo Gym

カーブミラーGPT Image 2
A photorealistic, vertical full-body shot of a massive, bipedal humanoid robot standing outdoors in front of a modern Japanese municipal sports hall. The robot is constructed from heavy-duty industrial machinery, featuring segmented white and black armor plating, exposed hydraulic pistons, and complex mechanical joints. Its head is a rectangular sensor array with multiple camera lenses and glowing red emergency lights on the shoulders. The robot is decorated for Halloween: it wears a flowing orange cape patterned with black bats and jack-o'-lanterns, and its body is draped with garlands of purple tinsel, small plastic pumpkins, and triangular bunting flags. Several chest plates are labeled with the text "警視庁" (Metropolitan Police Department) and "MPD".

In the foreground, two police officers wearing dark blue uniforms, tactical vests, and helmets stand with their backs to the viewer; their vests also bear the text "警視庁 MPD". To the right, a crowd of civilians includes a woman taking a photo with her smartphone and a child dressed in an orange witch costume with a pointed hat. The background features a large concrete building with glass windows and prominent signage reading "区立総合体育館" (Ward General Gymnasium). A tall vertical banner hangs on the right side of the building, displaying a cartoon pumpkin and the text "ハロウィン スポーツ フェスティバル" (Halloween Sports Festival). The scene is lit by bright, natural daylight under a clear blue sky.
Product Marketing - Olive Green Waxed Canvas Roll-Top Backpack

Product Marketing - Olive Green Waxed Canvas Roll-Top Backpack

SjoltGPT Image 2
A high-resolution product photograph of a dark olive green waxed canvas roll-top backpack. The bag features two vertical tan leather straps with square brass buckles on the front, and a horizontal zippered pocket below them with a brass zipper pull. A matching fabric grab handle is visible at the top center. The backpack sits upright on a light beige stone surface against a plain, textured cream-colored wall background. Soft, diffused daylight illuminates the scene from the left, casting gentle shadows to the right.
Profile / Avatar - Retro American Cartoon Style Image Transformation

Profile / Avatar - Retro American Cartoon Style Image Transformation

SairahGPT Image 2
Transform the exact uploaded image into a full body illustration designed in a 1960s–1980s retro American cartoon style. Preserve the exact subject, facial identity, hairstyle, clothing, accessories, colors, proportions, pose, body language, facial expression, camera angle, framing, composition, perspective, lighting, and every visible detail from the original image. Do not redesign, reinterpret, simplify, replace, or invent any elements. The uploaded image must remain instantly recognizable, changing only the artistic style.

The character should feature exaggerated rubber hose proportions, expressive body language, a slightly oversized head, simplified anatomy, elastic limbs, large classic oval cartoon eyes with simple black pupils, thin expressive eyebrows, rounded hands, clean geometric shapes, and a playful vintage personality while preserving the exact likeness, expression, and silhouette of the original subject.

The illustration features thick bold black outlines, flat solid colors, minimal cel-style shading, subtle vintage film grain texture, slightly desaturated tones like old animation cels, smooth hand-drawn 2D linework, simple color blocking, soft retro print texture, and a classic mid-century American animation aesthetic.

Preserve the original background exactly as shown in the uploaded image unless otherwise specified.

Keep the original composition, framing, perspective, and camera angle exactly the same. Full body should remain visible if it is visible in the original image. High resolution, clean illustration, no realism, no 3D rendering, no anime, no Pixar, no Disney, no modern cartoon style, only authentic 1960s–1980s American retro animation aesthetics.
Profile / Avatar - Retro Showa Halloween Portrait

Profile / Avatar - Retro Showa Halloween Portrait

いがぐりメタボGPT Image 2
A vertical, medium-shot portrait of a young Asian woman with short dark hair and bangs, wearing a homemade Halloween costume consisting of an orange paper pumpkin hat and a matching jagged orange paper collar tied at the neck over a black long-sleeved dress. She is leaning slightly forward, making a peace sign with her right hand near her cheek, while holding a small brown paper bag decorated with a jack-o'-lantern and black cat in her left hand. The background is a narrow, dimly lit retro Japanese alleyway (yokocho) at night, featuring wooden storefronts, glowing lanterns, and blurred figures of other people walking away. On the left, there are hanging paper decorations including a jack-o'-lantern and a white ghost. On the right, a vertical banner reads 'おもちや' (Omo-cha). The image has a strong Showa-era retro aesthetic, characterized by warm, faded colors, visible film grain, scratches, dust spots, and soft focus typical of vintage instant photography.
Profile / Avatar - Retro Halloween Vampire Girl

Profile / Avatar - Retro Halloween Vampire Girl

いがぐりメタボGPT Image 2
A retro-style photograph of a young Asian woman with short, messy dark hair sitting in a vintage floral armchair. She is wearing a beige chunky knit sweater over a plaid skirt, paired with slouchy white socks and brown loafers. A black velvet vampire cape with red satin lining is draped over her shoulders, tied at the neck with a ribbon. Her hands are raised in a playful claw gesture, and she has small fangs visible. The background features Halloween decorations including orange jack-o'-lanterns and black bat cutouts on the wall, along with an old CRT television set to the left. The image has a nostalgic Showa-era aesthetic with warm lighting and film grain.

寻找下一个方向

ASTORIE CANVAS

让灵感,继续生长。

在同一个创作空间,连接提示词、参考素材和生成结果。

打开创作画布 ↗