Start from the first uploaded image. The floating collage-style fashion items visible in the first image remain suspended briefly. Then, the floating garments begin to move toward the model one at a time, in a clear and sequential order. The first floating garment rapidly flies toward the model. At the moment of impact, reality subtly distorts — the surrounding air and background stretch inward for a brief instant, as if space itself is being pulled toward the garment. Simultaneously, a playful cartoon-style overlay briefly appears around the impact area: hand-drawn outlines, flat graphic shapes, and sticker-like motion accents wrap around the garment for a split second. As the cartoon layer snaps away, a short burst of expressive energy radiates outward, visualizing the model’s joy — light motion lines and rhythmic pulses that echo her excitement. The original basic clothing in that area disappears instantly and cleanly. The floating garment seamlessly replaces it, fully integrating into the model’s outfit. Only after this transformation is fully completed does the second floating garment accelerate toward the model. Each garment repeats the same sequence: impact, subtle spatial distortion, brief cartoon overlay, emotional energy pulse, clean replacement. Each transformation happens one by one, never simultaneously. No additional floating garments appear, and the total number of transformations exactly matches the number of floating garments shown in the first uploaded image. After the final garment merges into the model, no clothing remains floating in the air. The model is now fully dressed in the complete outfit formed from the previously floating collage garments. The entire transformation unfolds as a continuous, magical yet realistic physical process, with no cuts, no jumps, no edits, and no camera breaks. The scene then smoothly transitions into the second uploaded image. During the transition, the model poses confidently toward the camera, happily presenting the outfit she is wearing, with joyful expression and natural, lively movement. The full sequence appears as one uninterrupted shot — ultra-smooth, seamless, and believable, like a real-world transformation infused with imagination.

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.

Use the uploaded image as the first frame and only reference. Strictly lock character identity, face, body, skin, hairstyle, outfit, materials, and all accessories. Do not redesign, add, remove, duplicate, or stylize anything. No crown. Cinematic AAA game-CG style. The female character slowly walks forward through shallow water from mid-distance toward camera. Movement is smooth, elegant, confident. Each step creates gentle ripples and splashes. Clothing, hair, and accessories move naturally with walking and water physics. Upon reaching front frame, she stops naturally. Character remains still. Only minimal idle: subtle breathing and soft blink. No pose change, gesture, head turn, or expression change. After stop, water ripples expand and fade naturally. No new splashes; character stays still. Camera at eye level, vertical frame. After stop, very slow 5–10% forward push toward the necklace. Push is smooth and stable, no zoom, shake, focus shift, or cut. Lighting, environment, color, and mood match reference. Maintain golden hour rim light, soft highlights, cinematic contrast, magical game-CG feel. Avoid artifacts: no face/body change, proportion shift, flicker, jitter, melting, stretching, or instability, no extra accessories, no fantasy redesign, no water blocking key details. High-quality, stable, realistic motion with clean anatomy throughout.

Use the provided nano pro generated image as the reference frame and identity anchor. The same female model from the reference image brings the exact product from a slightly lower position up to the center of her chest. The timing of this upward movement is precisely synchronized with the background music beat. The motion is smooth, deliberate, and rhythm-matched, not repetitive. Once the product reaches the chest position, it remains steady and still. Both hands support the product with correct physical contact. The product must remain rigid, undistorted, and unchanged in shape, scale, material, and surface details throughout the shot. Camera: Medium shot, eye-level. Slow, smooth dolly zoom moving forward toward the product. In the final moment, visual emphasis clearly shifts to the product, not the model’s face. No camera shake. Lighting: High-key studio lighting, bright white seamless background, soft controlled reflections on leather, clean highlights, no harsh shadows. Audio: Cool, modern instrumental background music only. Futuristic, high-fashion electronic style. No vocals, no lyrics, no sound effects. Motion constraints: The beat-synced motion occurs only during the product-lift movement toward the chest. No hand tapping or rhythmic motion after the product is in position. No unnecessary body movement. Constraints: Do not morph, bend, or stylize the product. Do not change product design or texture. Do not add text, logos, graphics, or new elements. Maintain full visual consistency with the reference image.

Use the uploaded reference video as motion reference only. Transfer the full body movement, gesture timing, and motion rhythm from the reference video. Apply the motion to the person in the uploaded reference image. The person’s identity, face, body shape, clothing, hairstyle, and overall appearance must remain exactly the same as the reference image. Use the background from the reference image. The background must remain unchanged throughout the video. Do not use or reconstruct the background from the reference video. Only motion is transferred, not appearance or environment. Facial expression should remain neutral and consistent with the reference image. Follow the reference video motion as closely as possible. Do not invent new movements. Single person only. Camera remains stable. Natural and realistic human motion. Commercial-quality result.

Maintain the consistency of the characters, keep the fixed shot. Only the person within the Instagram3d frame smiles and waves to the camera. After the woman on the right side continues to type on the keyboard, the "193 likes" in the lower left corner of the frame changes to "999 likes". From the computer screen, the like icon rises upwards. The person on the right side looks up and claps with the character in the frame. There is no change in the text.

Maintain the consistency of the characters. The two people's heads are close together, they have a gentle kiss, the scene freezes the moment of the kiss. The camera slowly pulls to a wide-angle long-distance shot. The couple stands embracing in the water, with the background being the sea and the sky blending into one color. The picture gradually slows down and freezes. The water surface is covered with dense deep red rose petals that float with the movements of the two people. The balloons slowly sway with the wind.

Maintain the original black and white faded texture of the old photo, without complementary colors or sharpening. The subject only made very slight breathing fluctuations in the original posture (chest 1 cm, slight eye movement), and at the same time, Subject A and Subject B naturally exchanged a glance (only made a very small eye contact, with the head almost still). The lens simulates the gentle shake of an old handheld camera: amplitude < 2°, frequency 0.5Hz, particle noise and scratches are retained. No editing, no special effects, no coloring.

The two were very close and quickly turned their heads to look at each other. One of them raised one hand and gently stroked the other's cheek, his movements natural. The two then kissed, their lips touching and remaining together for a few seconds. The camera slowly zooms in, focusing on intimate details. The scene is realistic and romantic, with intense emotions

{ "duration": "8s", "camera": "Medium shot, eye-level, slightly zoom in/out, stable handheld style", "lighting": "Warm softbox lighting, high-key, with red gradient light gently flowing from edges to center", "subject": "Use the two people from the uploaded nano pro image, with face identity and hair color locked. Both characters wear festive red Hanfu, holding Spring Festival couplets.", "motion": "Both subjects slightly sway their hands left and right while holding the red couplets. They turn slightly towards each other and share a happy, joyful smile. Then both turn to look at the camera and say 'Happy Chinese New Year' together.", "expressions": "Joyful, festive, natural smiles. Expressions evolve from subtle happiness during hand sway to cheerful laughter when looking at each other, ending with warm smiles to the camera.", "props_effects": "Red couplets move slightly in sync with hand sways, sleeves gently sway as if in light breeze.", "background_effects": "Red gradient light flows slowly from the edges toward the center. Optional: subtle floating golden particles to enhance New Year atmosphere.", "audio": "Background music: cheerful and lively pure instrumental music, upbeat and festive, without vocals.", "framing": "Centered full-body view, ensuring both characters are fully visible, balanced composition." }

The two were very close and quickly turned their heads to look at each other. The two then engaged in a passionate French kiss, with their mouths open and their tongues interwoven inside. They kissed for a long time, their movements natural. The camera slowly zooms in, focusing on intimate details. The scene is realistic and romantic, with intense emotions and an ambiguous atmosphere.

Using the uploaded image as the first frame. The selfie subject remains the same person and appearance. The person is extremely excited and energetic, jumping lightly in place while recording a selfie video. They wave their free hand enthusiastically, shake their head to the rhythm, and move their shoulders and upper body with joyful carnival energy. Their facial expression is vivid and expressive, with wide smiles, laughter, and visible excitement. The phone is held with a single visible arm in a realistic selfie position. As the person jumps and moves, the camera naturally bounces and sways left and right around the person’s body axis, creating an authentic handheld selfie motion. Correct anatomy and proportions at all times, no extra arms, no duplicate hands, no additional phones. In the background, Brazilian Carnival dancers and spectators jump, dance, and celebrate wildly. Colorful confetti and streamers fly through the air, filling the sky with motion. Bright daylight, vibrant saturated colors, intense festive atmosphere, explosive Carnival energy. The selfie subject stays in the foreground and in focus, while the background motion enhances depth and immersion.

0.0-1.0 second still original image; Within 1.0 to 2.0 seconds, a young member of the opposite sex naturally enters the frame from the left side and steps in front. For 2.0 to 4.0 seconds, the two people gently touch each other's foreheads and then kiss tenderly (only touching the lips lightly). Keep the kiss frozen for 4.0 to 5.0 seconds. Shapes, light and shadow, and expressions are smoothly aligned frame by frame, without any flash white or jump cuts. The background is clean and free of text.

The camera follows the movement of the aircraft, focusing on the plane. A wide-body passenger aircraft, entirely in bright red color, is flying smoothly at low altitude, with red-wrapped boxes hanging beneath it. The box is opened from below, and a large number of huge red heart-shaped aluminum foil balloons are released from below and fall downward, covering the entire city. The action is smooth and natural, with cinematic quality and 8K resolution.

The camera slowly pans forward. The protagonist smiles and gently waves at the camera, introducing the pop-up store and the figurines beside it. Her hand naturally rests on the figurine. Voiceover: 안녕하세요, 여러분! 내 첫 번째 팝업 스토어 'Angel' 오픈했어요! 오늘 같이 둘러볼까요?\n입구에 저랑 똑같이 옷 입은 인형이 있잖아요? 너무 귀여워서 미치겠어요!” Background music: Cheerful and sweet K-pop pure music Maintain the consistency of the characters. The protagonist's face does not undergo any change.

[ { "shot": "Shot_0", "duration": "2s", "camera": "Static, medium shot, eye-level", "lighting": "Bright, festive high-key lighting", "subject": "Initial character from first_image_url, standing naturally", "motion": "Red silk ribbons or red envelopes gently fall from top to cover the screen; as they cover, the character smoothly transitions into the new outfit and environment from tail_frame_image_url", "visual_effects": [ "Red silk ribbons and/or red envelopes falling", "Soft reveal of the new outfit as ribbons clear", "Subtle particle glow to enhance festive atmosphere" ], "audio": { "background_music": "Festive Chinese New Year music" } }, { "shot": "Shot_1", "duration": "2s", "camera": "Static, medium shot, eye-level", "lighting": "Bright, high-key, even studio lighting", "subject": "The person and background from the nano pro generated image, face and hair color locked, hairstyle, makeup, and expression flexible; standing with festive decorations in the background (lanterns, flowers, gold ingots, etc.)", "motion": "Subject performs a cupped-fist salute: cups one fist inside the other hand and raises them to the chest in a greeting gesture while bowing head slightly, saying 'Happy Chinese New Year'", "audio": { "dialogue": "Happy Chinese New Year", "background_music": "Festive Chinese New Year music" } } ]

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.

Use the image as the first frame reference. The couple stands very close to each other in the center of the frame. They suddenly turn their heads and look directly into each other’s eyes. Their expressions are joyful, happy, and full of excitement. One of them slowly raises a hand and gently caresses the other’s cheek, the motion soft, intimate, and natural. Immediately after, they lean in and kiss. Their lips meet and stay together for a few seconds, creating a strong sense of intimacy and emotional connection. The camera slowly pushes in, gradually zooming closer to focus on the intimate details of their faces and the kiss. The overall movement is smooth and cinematic, enhancing a realistic and romantic feeling with intense emotion. In the background, fireworks continue to bloom in the night sky, lighting the scene with warm, colorful flashes. The surrounding crowd remains in the background, moving subtly and naturally, adding life without distracting from the couple. The atmosphere feels real, romantic, and emotionally powerful.

Use the uploaded image as the main character reference. The subject is the same female Carnival samba dancer shown in the image. Do not change her identity, face, or hair color. Keep the same costume, body proportions, and overall appearance. The body movement must remain anatomically consistent with the reference image. Duration: 10 seconds. Camera: Medium shot at eye level, tracking the subject smoothly as she dances. Slight zoom in and zoom out during the movement. Stable handheld style, no shaking, cinematic but realistic. Lighting: Bright artificial stadium floodlights at night, high contrast lighting. Strong sparkling reflections on crystals, rhinestones, and oiled skin. Nighttime carnival atmosphere. Motion: Energetic samba dancing. Rapid and precise footwork. Fast hip isolations with strong rhythm. The dancer briefly crouches down low while intensely shaking her hips, then rises back up smoothly, extending and gesturing with her arms. She appears joyful and fully immersed, subtly singing along to the music while dancing. Style: Realistic, high-energy carnival performance. Natural body motion, fluid transitions, no exaggerated or cartoonish movement.

{ "duration": "5s", "camera": { "type": "medium shot, eye-level", "movement": "slight handheld tracking, subtle zoom following the couple" }, "subjects": [ { "source": "nano_pro_generated_image", "motion": "leaning close to each other, then quickly turning heads to look at each other", "expression": "happy, joyful" }, { "source": "nano_pro_generated_image", "motion": "leaning close to each other, then quickly turning heads to look at each other", "expression": "happy, joyful" } ], "action": { "activity": "waving sparklers", "interaction": "sparklers traces form a heart in the foreground, motion smooth and natural" }, "environment": { "setting": "night beach scene", "background": "distant city lights twinkling, soft waves, romantic atmosphere", "lighting": "warm ambient glow dominated by sparklers" }, "visual_effects": { "bokeh": "soft circular bokeh from sparklers in warm gold and orange tones", "motion_blur": "slight motion blur on sparkler trails for realism" }, "composition": { "framing": "medium close-up, portrait orientation", "style": "realistic romantic scene, emotional intensity, cinematic lighting" } }

The character proudly introduces her own self-portrait behind the scene. The camera slowly moves forward, and the blogger's hand gently touches the edge of the frame. Voiceover: "Welcome back to my channel! Today we are at the gallery for something very special." The blogger steps back a few steps, spreads her arms to showcase the entire painting in a frame with herself in the picture, smiling confidently. Voiceover: "Having my own portrait in a gallery is a total dream come true!"

Use the uploaded lipstick image as the exact product model and final visual reference. A realistic, cinematic car interior scene with a couple exchanging a gift. Camera fixed in the back seat, slightly above eye level, always focused on the gift box and lipstick. Natural opening transition from the first frame. The man in the driver’s seat takes out a small, palm-sized, two-piece rigid gift box and hands it to the woman in the passenger seat. The woman receives the box with both hands. The box has a separate lid and bottom base. The lipstick is placed only inside the bottom base, never in the lid. The woman removes the lid completely and sets it aside (full unboxing, not flipping or tilting). Inside the bottom base, the lipstick sits in the center of pink shredded paper (pink raffia paper). The woman physically picks up the lipstick, lifts it completely out of the box, and holds it separately in her hand. Do NOT display the lipstick while it is still inside the box. Do NOT extend or hand the product toward the camera. Final presentation: After the lipstick is fully removed, the camera slowly pushes in toward the lipstick, ending in a clear close-up while the product remains perfectly stable. During the close-up, the lipstick’s shape, proportions, cap, edges, and surface geometry must remain identical to the uploaded image. No deformation, morphing, stretching, or melting. No faces visible at any time. No background music. Only natural car ambience, subtle packaging interaction sounds, and soft English dialogue. All movements are slow, deliberate, and clearly readable. Do not skip or shortcut any action steps.

Shot_1 = { "duration": "2s", "camera": "Static medium shot, eye-level", "lighting": "Bright studio lighting with a purple and pink gradient background", "subject": { "image_url": "first_image_url" }, "motion": "The right person grabs the left person's right hand with her left hand, they tightly grip hands, then both quickly move outwards toward the edges of the frame and exit, leaving only their tightly held hands with slightly bent arms visible in the center" } Shot_2 = { "duration": "7s", "camera": "Static medium shot, eye-level", "lighting": "Bright studio lighting with a purple and pink gradient background", "subject": { "image_url": "tail_frame_image_url" }, "motion": "Starting from the bent hands left in the center from Shot_1, the two individuals enter the frame from left and right along the arc of the hands, wearing Brazilian Carnival costumes, move to the center, then dance to the beat of the music, swaying their hips and striking poses in rhythm" }

A TikTok-style tech review video with a natural creator tone. A handsome American Black male digital technology blogger is in his esports room introducing a magnetic power bank. The vibe is authentic, conversational, and creator-led — like a real TikTok tech reviewer talking to followers. The camera remains steady and close, vertical format. The creator speaks casually while demonstrating the magnetic attachment and holding the charger in hand. Gestures are relaxed, pacing is natural but still engaging. RGB lighting and gaming setup remain visible but not distracting, reinforcing a real esports creator workspace. No dramatic movements, no exaggerated acting — realistic TikTok tech review energy. The entire line is spoken directly from the man’s mouth, fully synced with his lip movements. There is absolutely no background voiceover. (No subtitles.) Spoken line (delivered on camera): “Are you tired of heavy power banks and tangled charging cables? This magnetic charger FIXES IT—snap on instantly, no more fumbling! grab yours NOW!” If any models appear in the video with their faces visible, they should be handsome American Black male.