YouMind
Sign in

Architecture / Interior

Explore free Architecture / Interior video prompts from YouMind's AI prompt library, grouped under subjects. Every prompt is curated from real creative workflows and ready to copy, adapt, and reuse.

1824 promptsDaily highlights
Seedance 2.5
View full prompt & copy

Create a 30-second ultra-realistic cinematic Halloween video of a majestic haunted castle glowing with warm orange lights, surrounded by jack-o’-lanterns, twisted trees, blue fog, and wet reflective cobblestones. The camera slowly moves toward the castle as autumn leaves drift, candles flicker, and bats fly across the moonlit sky. Elegant glowing text appears: “Happy Halloween.” End with a dramatic wide shot of the illuminated castle. Photorealistic details, smooth camera movement, volumetric fog, spooky magical atmosphere, 4K, no people, no distortion, consistent scenery, vertical 9:16, exactly 30 seconds.

Generate video
Seedance 2.5
View full prompt & copy

A breathtaking, photorealistic Halloween festival at night featuring a spooky Gothic mansion glowing jack-o’-lanterns, a black cat wearing a witch hat flying bats floating ghosts autumn leaves, vintage lanterns, a misty pathway and a giant full moon. Cinematic orange and midnight blue lighting, magical atmosphere, realistic textures, atmospheric fog, smooth camera movements spooky ambient music, gentle wind, and magical sound effects. Premium cinematic resolution 4K, 16:9 ratio.

Generate video
Seedance 2.5
View full prompt & copy

① Blackboard (First frame image 1 / 10 seconds) Morning cafe. On a blank blackboard, chalk lines appear stroke by stroke on their own, forming three horizontal lines of text: 'Today's Recommendation / Chestnut Mont Blanc / 680 Yen'. Fixed camera. ② Hikari (Reference image 1 / 10 seconds) Morning park. Walking from right to front. Opens one hand to show '5' while saying 'It starts in five minutes!' ③ Window (Reference image 1 / 10 seconds) Daytime Japanese room. Walks towards the window, pushes the sliding door open sideways. Sound of rail resistance. Wind slightly moves papers on the desk. ④ Two Anime Characters (Reference image 1 / 30 seconds) Both in Japanese 2D anime style. Daytime riverbank. One plays bass, the other dances spinning around. High-five at the end, then says 'Let's play with sound!'. No cuts for 30 seconds, camera orbits half-circle around the two.

Generate video
Seedance 2.0
View full prompt & copy

A hyper-realistic cinematic slapstick romance told across four seamless shots outside a traditional two-story residential building in South Korea during bright afternoon daylight. Natural handheld smartphone cinematography. Use Image Reference 1 as the woman and Image Reference 2 as the man. Preserve both identities, facial features, hairstyles, and clothing consistently throughout every shot. SCENE A modest Korean villa-style apartment building with pale concrete walls, an open second-floor window, and a white bedsheet hanging from an outdoor laundry rack. A narrow pedestrian walkway runs beneath it, surrounded by potted plants, parked scooters, utility cables, and neighboring buildings. SUBJECTS A Korean woman with her hair tied in a neat bun, wearing a casual patterned house dress and simple indoor slippers. A scruffy, eccentric-looking Korean man with messy hair, light stubble, worn casual clothes, and old sneakers. SHOT 1 | THE UNEXPECTED ENCOUNTER The woman stands at the second-floor window, struggling to straighten a large white bedsheet with a long bamboo laundry pole. Suddenly, the pole slips from her hands and falls toward the street. The camera tilts downward, revealing the man walking beneath the window while looking at his phone. The bamboo lands beside him with a loud THUNK, startling him so badly that he stumbles backward and falls onto a soft pile of laundry bags. He looks up in disbelief. The woman leans out of the window, embarrassed. Woman: "Oh my God! I'm so sorry!" Man: "It's okay... but you owe me a kiss!" SHOT 2 | THE FLIRTY CHALLENGE The woman rolls her eyes but notices the man's exaggeratedly charming smile. She laughs despite herself. Woman: "A kiss? You must be dreaming!" The man dramatically places one hand over his heart and pretends to faint. She giggles, covering her mouth, while he suddenly springs back up and points toward the window. Man: "Then let me come up and prove I'm worth it!" She shakes her head, smiling, and gestures for him to wait. SHOT 3 | THE IMPOSSIBLE ROMANTIC MOVE The man grabs the fallen bamboo pole, runs several steps, and plants it firmly against the ground like a pole vaulter. The bamboo bends dramatically as he launches upward toward the second-floor window. The handheld camera races upward, tracking his ridiculous flight with dynamic motion blur. The woman gasps as he arrives at window level, clinging to the flexible bamboo. He steadies himself, leans forward, and puckers his lips comically. The woman initially looks shocked, then starts laughing at his ridiculous expression. Man: "So... can I have my kiss now?" She pauses for a beat, looks into his eyes, and unexpectedly leans forward. SHOT 4 | THE KISS AND THE LAUNCH The woman gives him a quick, playful kiss on the lips. Both freeze for a split second, eyes wide with surprise. The man beams with happiness. Man: "Worth every second!" But the overloaded bamboo snaps, sending him tumbling back down into the laundry bags.

Generate video
Seedance 2.0
View full prompt & copy

Multi-shot 9:16 video, photorealistic time-lapse renovation ad, static camera, bright white room with concrete floor and window: Shot 1 (0-3s): man in orange overalls rakes a huge pile of cucumber slices, spreading them across the entire floor. Shot 2 (3-6s): man and woman in red overalls pour white self-leveling epoxy from buckets over the cucumbers. Shot 3 (6-9s): they squeegee the resin flat; cucumbers vanish under glossy white liquid. Shot 4 (9-13s): workers in yellow hi-vis vests polish the floor with grinding machines, revealing cucumber slices embedded in white terrazzo. Shot 5 (13-17s): man in orange kneels, touching the finished glossy surface. Shot 6 (17-20s): two workers assemble a beige bed in the room. Shot 7 (20-23s): final empty bedroom, white bed, side table with eucalyptus vase, designer floor with green cucumber cross-sections. Fast motion, motion blur on people, consistent lighting and geometry, 4K, satisfying ASMR vibe.

Generate video
Seedance 2.0
View full prompt & copy

Vertical 9:16 hyper-realistic transformation video, documentary style, static wide-angle camera from the corner of an empty white room with one bright window and a bare concrete floor. Shot 1 (0–4s): A bearded man in blue denim overalls and a black long-sleeve shirt rakes a huge cone-shaped pile of thousands of antique brass and iron keys with a black leaf rake, methodically spreading the keys evenly until the entire floor is covered in a dense carpet of old keys. Shot 2 (4–8s): A woman with long brown hair in red overalls and black gloves pours thick glossy white self-leveling epoxy resin from a large white plastic bucket; the milky liquid flows outward in smooth waves, swallowing the keys and covering the whole floor with a mirror-smooth white surface, a few key silhouettes poking through. Shot 3 (8–17s): A worker in a yellow high-visibility vest, black cap and grey work pants pushes a red-and-white ride-on floor grinder with a black vacuum hose, polishing the hardened epoxy in smooth passes; golden key shapes emerge embedded in the glossy floor like terrazzo, reflections of the window and the worker visible on the mirror-like surface. Shot 4 (17–23s): Two workers in black polo shirts and black caps assemble a dark walnut bed frame in the center of the room, place a white mattress, smooth out white bedding and pillows, then wooden nightstands with white ceramic lamps appear on both sides; the finished bed with beige accent pillows stands on the polished floor full of golden keys as the workers walk out of frame. Bright natural daylight, soft shadows, satisfying ASMR renovation timelapse mood, photorealistic textures, smooth motion, no text, no watermark.

Generate video
Claude Opus 5.5
View full prompt & copy

Use CMAB (Tsinghua University) ©OpenStreetMap to construct a 3D city of Beijing. Then, using this 3D city as the main subject of the video, introduce the complete history of Beijing. Use clear male narration from EdgeSpeak to generate audio, with highlighted Chinese and English subtitles. Based on the historical content explained, intersperse rich, diverse forms of video elements and visuals with top-tier aesthetics and Chinese artistic sense. In short, I hope you do your best to create a video that allows people to feel Beijing's history through various forms. Materials are not limited to OpenStreetMap; you can obtain all materials from the internet without restriction.

Generate video
Seedance 2.5
View full prompt & copy

Create a 10-second ultra-realistic cinematic vertical video (9:16) of a mysterious young woman performing powerful martial arts movements in a traditional Chinese temple courtyard at night during heavy rain. She has long black hair, a serious expression, and wears a black leather outfit with a long flowing black coat, black shorts, and black athletic sneakers. The ground is wet and reflective, mirroring the warm golden and orange lights of traditional Chinese architecture. Heavy rain falls continuously, creating realistic splashes beneath her feet. Begin with a low-angle wide shot as she performs a dynamic spinning kick, then smoothly transition into a series of fast martial arts movements, powerful high kicks, and low defensive stances. Her coat and hair flow naturally with every movement. Use realistic human anatomy, fluid motion, accurate foot placement, natural body physics, cinematic camera tracking, subtle slow motion during the highest kick, dramatic nighttime lighting, atmospheric rain, realistic reflections, and professional action-film cinematography. End with the woman standing confidently in a powerful warrior pose as rain falls around her. Style: Photorealistic, cinematic action film, ultra-detailed textures, 4K quality, dramatic lighting, realistic rain physics, smooth transitions, sharp focus, no text, no subtitles, no watermark. Maintain consistent character appearance throughout the video.

Generate video
Seedance 2.5
View full prompt & copy

Create a realistic 20-second cinematic travel vlog featuring a young woman exploring a charming European old town. She walks through narrow cobblestone streets lined with colorful historic buildings, smiles naturally at the camera, stops at a traditional bakery to taste a fresh pastry, and enjoys the lively outdoor market with colorful umbrellas. End with her standing at a beautiful hilltop viewpoint overlooking red rooftops and the city skyline. Keep the same woman's face, hairstyle, and outfit consistent throughout the video. Natural expressions, realistic walking movements, authentic hand gestures, soft daylight, cinematic camera movement, detailed textures, natural colors, and a premium travel influencer aesthetic. Smooth transitions between scenes, realistic physics, subtle background activity, vertical 9:16 format, ultra-realistic 4K quality. No text, no subtitles, no logos, no watermarks.

Generate video
Seedance 2.5
View full prompt & copy

Blue brick courtyard, pearl-white Yinglong slowly descending, woman in moon-white robe confronting the dragon; 15-second vertical screen. Duration: 15 seconds Aspect Ratio: 9:16 Vertical Format: Pure text-to-video, no reference images. Style: Eastern fantasy realistic cinematic feel, slow pace, coexistence of oppression and tranquility. No dialogue, no narration, no subtitles, no interface text, no audio lyrics. [Subject] A deep blue-brick circular courtyard well, with multi-layered pavilion-style brick patterns extending upwards on the well walls. Shallow water at the bottom reflects faint light. An adult Eastern Yinglong (single horn, long whiskers, four claws), scales are pearl-white with indigo edges, slowly descending from above the well wall. Standing by the shallow platform edge is an adult Eastern female, wearing a moon-white cross-collar robe and mist-blue shawl, hair loose, facing the giant dragon, expression calm. [Camera and Action] 00:00–00:04: Camera makes extremely slight clockwise arc movement along the shallow platform edge, while slightly retreating, forming slow perspective changes between the person, water reflections, well walls, and the dragon winding down the well; strictly no violent Orbit. 00:04–00:10: The Yinglong's head pushes downward first, neck forms a soft arc, power transmits slowly along the chest section; front claws slightly open then close. The rear half of the dragon body coiling around the well wall performs extremely slow S-shaped delayed undulation. Wing root membranes only tremble lightly, do not expand or flap. Dragon mouth slightly opens exhaling a small amount of cold mist. Thin mist in the well spirals down, fine ripples on the water surface expand outwards. 00:10–00:15: The woman in moon-white clothes remains almost motionless, hem and long hair blown back by pressure wind. Architecture is absolutely stable. Camera slowly pushes in to a close-up of the woman and dragon facing each other, then freezes. [Lighting] Cold azure sky light pours down from the top of the courtyard, wet reflection on well walls; dragon scales and cold mist have subtle highlights. [Negative] Reference image dependency, subtitles, recognition boxes, HUD, Western dragon shape, multiple heads, limb proliferation, violent shaking, teleportation, cartoon plastic texture, watermark, platform Logo, dialogue, music overpowering ambient sound.

Generate video
Seedance 2.0
View full prompt & copy

STYLE: Animated classical Persian miniature painting, flat layered perspective, intricate floral and geometric patterns, gold leaf sky with swirling stylized clouds, ornate border, delicate graceful motion. Color grade: lapis blue, turquoise, rose, saffron, gold. A colossal Simurgh with a peacock-like body, jeweled wings and a long sweeping tail of patterned feathers. A palace garden with turquoise domes, cypress trees and reflecting pools, courtiers, musicians and a prince on a white horse. SHOT 1 (0 to 3s): Wide shot matching the reference image, the Simurgh spreads its wings across the gold sky, its tail feathers unfurling one by one in shimmering patterns. SHOT 2 (3 to 6s): Medium shot, 35mm lens, musicians in the courtyard stop playing, a courtier drops a pomegranate that rolls across the tiles, the prince's horse rears. SHOT 3 (6 to 9s): Close-up, 85mm lens, the Simurgh's crowned head bows low, its eye glinting like a sapphire, gold patterns rippling across its feathers. SHOT 4 (9 to 12s): Low angle wide shot, 20mm lens, the Simurgh lands in the garden, its wings sweeping over the reflecting pools, petals and leaves of the cypress trees lifting in a spiral. SHOT 5 (12 to 15s): Extreme wide shot, 16mm lens, the prince rides forward and bows, the Simurgh lowers one wing like a staircase, and the swirling gold clouds open into a path across the sky. Fountain water, birdsong, an oud and tar melody that stops suddenly, a vast silken wingbeat, a deep melodic bird call, daf drums and santur building into a triumphant theme.

Generate video
Loading more prompts

FAQ

Where do YouMind prompts come from?
YouMind curates high-signal AI prompt examples from creator communities and public creative workflows. The library focuses on prompts that are useful to inspect, reuse, and adapt.
How are video prompt categories organized?
Video prompts are grouped into use cases, styles, and subjects. Use cases cover the production goal, styles cover motion or rendering language, and subjects describe the main scene or entity.
How are prompts assigned to categories?
YouMind uses AI to analyze each video prompt, its title, metadata, and generated result when available, then assigns the closest categories. Editors can refine categories as the taxonomy evolves.
What is YouMind?
YouMind is an AI workspace for turning research, ideas, and creative references into usable outputs. The prompt library is one public part of that workflow, built to help creators learn from strong examples faster.