The user-uploaded handheld shower head, placed upright at the center of the frame.Background: Pitch black (RGB 0,0,0) void.

Model: 28-year-old male model from Europe and America

A vertical descending travel shot, cinematic style, following a user-uploaded product in free fall from the sky. The product’s pose is fully locked to the uploaded reference image and remains consistent throughout the entire video, with only minimal natural motion allowed. Camera movement in three phases: an initial rapid approach toward the product, closing in quickly; a slower, smooth approach as the product passes through dynamic, soft clouds; finally, the camera follows the product’s downward free fall, gradually slowing near the end into a brief levitation phase, without any significant change in the product’s pose. Fighter jets streak across the background at extremely high speed, with motion blur and heat trails. Realistic lighting, atmospheric depth, golden hour sky, soft sunlight and shadows on the product. Focus: sharp on product, background slightly blurred for depth. Ultra-realistic, cinematic, 4k, vertical frame, no text, no logo, no watermark.

Using the user-uploaded over-ear headphone image as the sole visual reference, retain all original materials, logos, buttons and details, with the standing upright on a matching-tone surface

Use the uploaded product image as reference. Create a one-storey shop that sells the product. The building itself should be realistic and human-scale, with exterior colors and design matching the colors of the product, creating a harmonious look. Place a giant, oversized model of the product on the rooftop as the main visual focus. The product model should be highly detailed, with realistic material, depth, and three-dimensionality, dominating the scene. Include a natural entrance at street level, with warm interior lighting visible from outside. Show people standing or walking nearby, but the visual center remains on the rooftop product model. Place the building on a fashionable street in Paris, surrounded by old Parisian buildings. Include stylish pedestrians walking by to enhance the lively, urban atmosphere. Use an eye-level camera in a documentary photography style, ultra-realistic, with cinematic lighting. Final output image ratio: 9:16.

Maintain the consistency of the main product. The product and the balloons float up and down, left and right, forming a coordinated rhythm (presenting a dynamic appearance of a swing). The product slides left and right on the rectangular base as the balloons move. The main stone and the crushed diamonds reflect a flowing luster as they swing, and the top diamond glitters slightly.

Duration: 12s | Aspect Ratio: 9:16 | Soundtrack: Soft romantic Valentine's Day instrumental (tempo elevates gently with scene progression) Shot 1 (0–1s)Cut to a high-saturation deep red matte backdrop. A lipstick (matching reference imagery) anchors the frame’s absolute center, with soft, naturally diffused lighting wrapping its form. Shot 2 (2–4s)The lipstick executes a seamless 360° rotation—camera stays fixed as the product spins smoothly, showcasing every angle of its casing. Shot 3 (4–6s · Close-Up)Transition to a tight close-up of the tube: the lipstick bullet extends ultra-smoothly at a slow pace (rising ~1/4 of its total length). The frame locks onto the bullet’s texture, highlighting its fine, even finish. Shot 4 (6–12s)Camera pulls back to frame the full lipstick (tube + extended bullet). Fine golden glitter particles bloom slowly at the frame’s core; over 1 second, they trace a fluid path to form a glowing heart outline (with a gradient CG halo along its edges). The luminous heart holds steady for the remainder of the clip.

{ "duration": "10.0s", "camera": "Static, directly overhead flat-lay perspective", "lighting": "Warm chiaroscuro studio lighting with a gentle moving spotlight; the scene starts near-dark, then a soft, warm light sweeps smoothly from left to right, subtly revealing metallic details, surface textures, and decorative elements, before fading back into darkness. Avoid any cool or bluish tones.", "subject": "The product exactly as shown in the nano pro generated image, including all shapes, colors, materials, logos, and layout. Do not alter or reinterpret the product.", "motion": "All objects remain completely still. As the gentle light moves across the frame, metallic parts, gold-toned botanical elements, and hot-stamped gold lettering shimmer naturally. Crucially, the buds on the gold branches **actively and visibly bloom in direct response to the passing light**, opening gradually and fully during the sweep. This blooming action is mandatory and synchronized with the light." }

Use the reference video as the base for motion, timing, and composition. At the beginning of the video, only a picnic box covered with a checkered tablecloth is visible in the scene. No toys or products are visible before the box opens. When the picnic box opens, replace the anthropomorphized food elements in the reference video with the products from image_2, making the products the main visual focus. Replace the plush pony in the reference video with the toy pony from image_1, positioning the toy pony as a secondary accessory placed beside the products. Maintain the original dynamics exactly: the products and the toy pony bounce out of the picnic box together, follow the same motion trajectory and timing as the reference video, and finally land on top of the picnic box. The products should remain visually dominant in size, framing, and attention, while the toy pony stays adjacent as a companion prop. At the final moment, when all floating objects land on the picnic box, preserve the original visual effect from the reference video: transparent bubbles of varying sizes and yellow colorful balls burst outward from behind the picnic box. This bursting effect must remain unchanged in timing, scale, direction, and intensity. Keep all other elements unchanged, including background, lighting, camera movement, animation rhythm, and environment. Ensure the colors, materials, textures, and proportions of the toy pony and products strictly match the uploaded images. Do not introduce any new elements or alter the original animation sequence.

[{ "id": "Shot-1", "duration": "00:00 - 00:05", "camera": "The camera performs a continuous 1080-degree rotation around the central display over 5 seconds (equivalent to three full rotations), maintaining a medium shot and eye-level perspective.", "lighting": "Bright, even, and soft studio lighting illuminates the subjects, creating minimal shadows. The background is a vibrant pink, suggesting colored lighting or a colored backdrop.", "subject": "A well-arranged handbag and matching sunglasses (uploaded by the user) placed on a white pedestal.", "motion": "The camera executes a smooth, continuous rotation around the stationary arrangement of bags and sunglasses at an increased speed, completing three full rotations over the 5-second duration. The subjects themselves remain static." }]

The user-uploaded cookware, placed upright at the center of the frame.Background: Pitch black (RGB 0,0,0) void.

{ "description": "Cinematic shot of a sunlit Scandinavian bedroom. A sealed InsMind box trembles, opens, and in a single continuous burst all flat pack furniture and decor assemble simultaneously into a fully finished, serene Scandinavian bedroom, highlighted by a yellow InsMind throw on the bed. No secondary assembly or additional elements appear afterward. No text.", "style": "cinematic", "camera": "fixed wide angle", "lighting": "natural warm with cool accents", "room": "Scandinavian bedroom", "elements": [ "InsMind box (logo visible)", "bed with yellow throw", "bedside tables", "lamps", "wardrobe", "shelves", "mirror", "art", "rug", "curtains", "reading chair", "plants" ], "motion": "box opens once; all furniture and decor assemble simultaneously in one continuous motion, then remain completely static", "ending": "calm, modern space fully assembled, no further motion or changes", "text": "none", "keywords": [ "16:9", "InsMind", "Scandinavian", "single assembly", "one-time build", "no secondary motion", "warm & cool tones" ] }

{ "scene_description": "A user-uploaded sneaker floats mid-air, slowly spinning. Suddenly, a burst of vibrant paint splashes across it — yellow and pink. The shoe transforms instantly into a bold fashion-forward version in the original style with yellow and pink details. In the blurred background, a skatepark can be seen, but the focus remains solely on the shoe.", "visual_style": "high-fashion streetwear", "camera_movement": "slow-motion rotation of the sneaker, locked-on shot with shallow depth of field", "main_subject": "User-uploaded sneaker transforming mid-air with yellow and pink paint details", "background_setting": "blurred skatepark with ramps and urban textures", "lighting_mood": "even, soft light with focus on color contrast and texture", "audio_cue": "slow whoosh, paint burst impact, subtle tone shift at the transformation" }

{ "description": "Cinematic close-up of a cold, dewy user-uploaded bottle sitting alone on a weathered beach table in the foreground. It begins to hum, vibrate. The bottle cap *pops*—and the entire environment unfolds from inside: palm trees rise, lights string themselves, speakers assemble mid-air, sand shifts into a dance floor. A DJ booth builds from driftwood. Music kicks in. A beach rave is born in the background, creating depth and perspective with the foreground bottle in sharp focus. No text.", "style": "cinematic, magical realism", "camera": "starts ultra close on the bottle, zooms out and cranes overhead to reveal the beach rave, emphasizing depth and perspective", "lighting": "sunset turning to neon—golden hour illuminating foreground, party glow in background", "environment": "quiet beach transforms into high-energy beach rave with clear foreground-background separation", "elements": [ "user-uploaded bottle (label visible, condensation dripping) prominently in foreground", "pop-top cap in slow motion", "exploding citrus slice", "sand morphing into dance floor", "palm trees rising", "neon lights snapping on", "DJ booth building itself", "crowd materializing mid-dance", "fire pit lighting", "surfboards as signage" ], "motion": "explosion of elements from bottle, everything assembles in rapid time-lapse with foreground bottle as anchor", "ending": "user-uploaded bottle prominently in foreground on a beach table, beach rave in full swing behind it with clear depth and perspective", "text": "none", "keywords": ["user-uploaded bottle", "beach party", "bottle transforms", "rave build", "sunset to night", "cinematic", "foreground-background depth", "no text"] }