Text to Image

Cinematic Hanfu Tea Room Portrait — AI Image Prompt

Generates a moody editorial-style portrait of a Hanfu-clad woman seated in a traditional Chinese tea room with cinematic camera language. - AIPinMaker

GPT Image 2PortraitText to Image
Cinematic Hanfu Tea Room Portrait
Text to Image

Prompt

Create a cinematic portrait photograph of {argument name="character name" default="an elegant young Chinese woman"} seated in a dark traditional Chinese tea room, wearing a layered Hanfu outfit in {argument name="hanfu colors" default="soft dusty blue, peach, and translucent pale gray"} with delicate floral embroidery. She has long black hair styled half-up with ornate gold hairpins, loose strands framing the face, and a calm, poised posture. Compose as an environmental medium-close portrait from a slightly low, intimate table-level angle, using a {argument name="lens" default="35mm wide portrait lens"} look with mild perspective distortion and shallow depth of field. The woman sits beside a wooden table, one hand gently lifting or holding the flowing sleeve fabric, the other arm resting lower and partly out of frame; the face is centered but softly obscured by natural shadow and motion-like blur rather than sharply detailed. In the foreground include exactly 4 visible tabletop items: 1 white-and-blue porcelain teacup on a saucer, 1 pale ceramic lidded jar, 1 small plate of pale pastries, and 1 dark blue book or menu with worn gold decoration. The background is a richly carved dark-wood interior with lattice panels, antique furniture, a hanging landscape scroll, and exactly 2 warm orange lanterns glowing softly. Lighting should feel like dim ambient lantern light mixed with direct on-camera flash, producing a realistic candid editorial snapshot: moody contrast, dark corners, warm highlights, visible wood texture, slight underexposure, natural fabric translucency, and a film-still atmosphere. Use {argument name="aspect ratio" default="3:2 horizontal"}. Avoid modern objects, text overlays, exaggerated glamour posing, fantasy effects, or overly polished studio lighting.

Prompt breakdown

Subject
elegant young Chinese woman in layered Hanfu of soft dusty blue, peach, and translucent pale gray with floral embroidery, long black hair half-up with ornate gold hairpins, calm poised posture
Style
cinematic environmental medium-close portrait photograph with 35mm wide portrait lens look, mild perspective distortion, and film-still atmosphere
Lighting
dim ambient lantern light from exactly two warm orange lanterns mixed with direct on-camera flash, producing moody contrast, warm highlights, visible wood texture, and slight underexposure
Composition
slightly low intimate table-level angle, shallow depth of field, face centered but softly obscured by shadow and motion-like blur, one hand lifting flowing sleeve, four exact tabletop items in foreground
Mood
calm poised posture in realistic candid editorial snapshot with natural fabric translucency, avoiding glamour posing or polished studio lighting

Remix ideas

  • Swap hanfu colors to deep crimson and gold embroidery for stronger contrast against the dark wood
  • Change lens to 50mm to reduce distortion while keeping the low table-level intimacy
  • Move the dark blue book slightly forward so its worn gold decoration catches more flash highlight

Reference images

Cinematic Hanfu Tea Room Portrait reference
Text to Image

How to use this AI Image prompt template

  1. AiVideo Maker stepOne1
    Copy the prompt — grab this template’s prompt and negative prompt.
  2. iVideo Maker stepTwo2
    Pick a model — choose a recommended AI model for the best match.
  3. AiVideo Maker stepThree3
    Generate — open the studio with one click and create your result.

Related templates

Cinematic Stormy Seaside Portrait
GPT Image 2

Cinematic Stormy Seaside Portrait

Create a portrait image of Cinematic Stormy Seaside Portrait. Style: photorealistic. Composition: balanced and well-framed. Lighting: natural with cinematic mood. Category: portrait. Reference: cinematic-stormy-seaside-portrait-23964.

womanmoodywide-angle
Text to Image
Moody Selfie with Plush Toys - Nano Banana Pro AI Prompt for Social Media Post
Nano Banana 2

Moody Selfie with Plush Toys - Nano Banana Pro AI Prompt for Social Media Post

{ “subject”: { “description”: “An ultra-realistic vertical selfie photograph taken by a young woman with long dual-toned hair, lying face down on a bed in a moody atmosphere.”, “body”: { “physique”: “A slender yet curvy hourglass figure. The pose highlights the curve of her lower back and round glutes accentuated by the black bikini bottoms. The skin is flawless and completely free of any tattoos.”, “pose”: “Lying face down on her stomach, holding a smartphone to take a mirror-style selfie (likely reflecting off a surface or using a wide-angle lens). Her head is turned to look at the phone screen/camera with a pouty expression. Her upper body is slightly propped, showing her face, while her lower body extends behind her, showing the back of the bikini bottom and glutes.”, “features”: “Long straight hair with platinum blonde and dark brown streaks framing her face. Striking blue-grey eyes gazing at the camera, full lips.” } }, “wardrobe”: { “top”: “A white, tight-fitting asymmetric crop top with a single strap design (visible on the upper body).”, “bottom”: “A black string bikini bottom worn high on the hips (visible at the back).”, “accessories”: “Small silver hoop earrings and a silver chain bracelet on the right wrist (holding the phone).” }, “pose_action”: “Taking a selfie while lying face down, capturing both her face and rear figure in the frame.”, “scene”: { “environment”: “A bedroom setting focused on the bed area.”, “elements”: “White bed sheets and pillows. The specific plush toys (pink/white bunnies, round black cat with white eye patch) are visible on the bed near her.”, “composition”: “Vertical 9:16 aspect ratio selfie shot. The frame captures her face, torso, and extends to show the glutes from behind.” }, “lighting”: { “setup”: “Atmospheric, dim ambient lighting dominated by cool purple and blue tones, plus the light from the smartphone screen on her face.”, “details”: “The colored moody light washes over the scene and her hair/body. The phone screen casts a brighter, cooler light directly onto her face and eyes.” }, “camera”: { “technical”: “Ultra-realistic selfie photograph. Sharp focus on the face and eyes, with the rear body also visible in the frame. The angle is high-down or wide-angle selfie perspective.”, “constraints”: [ “Aspect Ratio 9:16 (Selfie)”, “Subject must be taking the photo herself (Selfie)”, “Face MUST be visible with pouty expression”, “Rear glutes/bikini bottom MUST be visible in the same shot”, “Subject must have NO TATTOOS”, “Replicate the purple/blue mood lighting exactly”, “Include the specific plush toys” ] } }3c:Tb49,{ “subject”: { “description”: “An ultra-realistic vertical selfie photograph taken by a young woman with long dual-toned hair, lying face down on a bed in

womanmoodywide-angle
Text to Image
Sadie Sink in the Upside Down High-Fashion Editorial - Nano Banana Pro AI Prompt for Social Media Post
Nano Banana 2

Sadie Sink in the Upside Down High-Fashion Editorial - Nano Banana Pro AI Prompt for Social Media Post

{ "image_prompt": { "subject": { "description": "Young woman with long, voluminous, wavy bright red hair parting in the middle.", "features": { "skin_tone": "Pale porcelain skin with realistic texture and natural pores.", "eyes": "Light blue eyes, intense and direct gaze.", "expression": "Neutral to slightly parted lips, confident and dramatic look." } }, "apparel": { "outfit": "Black strapless corset bodysuit with structural boning detail.", "accessories": [ "Sheer black opera-length gloves", "Sheer black tights" ], "styling": "High-fashion editorial aesthetic, monochromatic black outfit with deep cleavage against a upside down with mind flayer movie background." }, "pose": { "type": "Dynamic crouching or kneeling stance.", "action": "Leaning forward towards the camera.", "perspective_play": "Right hand reaching out dramatically towards the camera lens, creating extreme foreshortening and depth.", "focus": "Face is in sharp focus while the reaching hand is slightly blurred due to depth of field." }, "environment": { "setting": "Professional minimalist photo studio.", "background": "Dark, decaying parallel dimension, with a membrane-like flora, toxic spores, and sprawling vines.", "props": "Huge Mind Flayer shadowy hive-mind entity in backdrop." }, "lighting": { "type": "Dark creepy lighting.", "quality": "Even illumination on the face, feep highlights on hair, dark shadows to accentuate the corset structure.", "shadows": Surreal contact shadows on the floor." }, "camera_settings": { "style": "Wide-angle macro shot.", "perspective": "Forced perspective.", "depth_of_field": "Shallow depth of field (bokeh on foreground hand).", "resolution": "8k, RAW photo.", "details": "Ultra-sharp focus on eyes and lips." }, "mood": "Cinematic, intense, bold, fashion-forward, cinematic, vogue-esque." } }

womanwide-anglemoody
Text to Image
Cinematic Meadow Editorial Portrait
GPT Image 2

Cinematic Meadow Editorial Portrait

Generate a vertical 3:4 cinematic editorial portrait using the reference photo for exact face and identity. A lone figure stands in a vast, wind-swept sage green (color) meadow, tall grass surging in strong currents like ocean waves, partially obscuring the body, conveying depth, motion, and solitude. The subject wears a loose, light white shirt contrasting softly with the lush green surroundings. Dark hair is lightly disheveled, strands catching the breeze. Head gently bowed, gaze directed downward, expressing quiet introspection and melancholic calm. Expression is distant and emotionally restrained. Frame the shot slightly off-center from a subtle elevated angle. No horizon visible, the entire frame filled with grass texture. Color palette: muted sage green, deep olive, and warm off-white. Vertical 3:4 format, telephoto perspective, shallow depth of field, cinematic framing. Analog film aesthetic with grain, soft edge vignette, atmospheric natural light, and motion blur in the grass. Quiet, poetic storytelling; ultra-detailed yet organic, magazine-cover editorial quality. No text, no watermark.

womanmoodywide-angle
Text to Image
Censored Goth Portrait in Graffiti Ruins
GPT Image 2

Censored Goth Portrait in Graffiti Ruins

Create a gritty ultra-wide cinematic fashion photograph of a young goth woman (subject) standing close to the camera in the center foreground, shot from a low angle with an extreme wide-angle lens. Her face is completely obscured by a large centered square censor block in a soft brown skin-tone gradient, covering the entire face from forehead to chin. She has messy long black (hair color) hair blowing around her shoulders and wears a black lace gothic top with sheer floral sleeves, a high lace choker collar, layered dark necklaces, and a moody alternative style. Place her in front of towering ruined Gothic cathedral walls covered in bright graffiti, with pointed arches and broken stonework rising dramatically behind her. Use a saturated deep blue sky, harsh contrast, crushed shadows, vivid reds, yellows, blues, and pinks in the graffiti, high-grain street-photography texture, slightly distorted perspective, intense sunlight, dramatic color grading, and a rebellious punk editorial atmosphere. Compose in a 16:9 horizontal frame, subject centered, ruins filling the background, no readable text, no watermark.

womanwide-anglemoody
Text to Image
Rainy Train Schoolgirl Portrait
GPT Image 2

Rainy Train Schoolgirl Portrait

Create a moody cinematic square portrait of a young Japanese schoolgirl (character description) sitting alone on a train or bus on a rainy day, leaning her head against a fogged window covered in raindrops and condensation. She has long wet-looking black hair falling over her shoulders and wears a white sailor-style school uniform with a dark navy collar and ribbon tie. The composition is close and intimate, with the window occupying the left half of the frame and the girl on the right, her posture tired and melancholic as she looks downward toward the glass. Add exactly one large opaque square censor block over the center of her face, colored muted dark brown-gray, hiding all facial features. Outside the window, show a soft blurred green countryside landscape under overcast gray weather. Use natural low-light photography, shallow depth of field, muted green and gray tones, realistic rain droplets on glass, soft film grain, emotional rainy-day atmosphere, and a 1:1 aspect ratio. No text, no watermark, no extra characters.

womanmoodybokeh
Text to Image

Explore more prompts

Browse more AI image and video prompts by category.

FAQ

Why specify exactly four tabletop items?
The prompt deliberately lists the white-and-blue teacup, pale jar, pastries, and dark blue book to anchor the scene in believable tea-room detail without visual clutter.
How does the mixed flash and lantern lighting work?
Direct on-camera flash combined with the two warm orange lanterns creates the realistic underexposure, wood texture, and fabric translucency of a candid editorial snapshot.