{ "layout_specifications": { "dimensions": "Vertical (9:16 aspect ratio)", "composition": "Close-up portrait, three-quarter view, subject off-center to the left", "color_palette": ["Matte Black", "Dusty Rose/Terracotta", "Champagne Gold", "Ivory Skin Tones"] }, "subject_details": { "model": "Use the person from the user-uploaded image as the main subject in the foreground, lock face + lock hair color + lock hairstyle, do not lock makeup or expression", "expression": "Serene, direct gaze towards the camera", "hair": "Keep exactly the same hair color and hairstyle as the user-uploaded image", "makeup": "Dewy skin finish, defined eyebrows, and bold matte red/terracotta lipstick (modifiable, not locked)", "attire": "Sleeveless terracotta or coral-colored dress with side cut-out detailing", "accessories": "Large, ornate silver/white gold chandelier earrings with a leaf or petal motif" }, "typography_and_text": { "main_title": { "text": "COVER",

The image is very bright with an off-white background. The figure is at the visual center. She has exquisite makeup with rich retro red lipstick, wearing a black dome hat and black round metal-frame sunglasses whose lenses reflect urban buildings. She is dressed in a khaki trench coat with a black-and-white striped crew neck top underneath. She holds the hat gently with both hands, looking confident and dynamic. At the top of the image is the huge black serif font "Quality". On the lower-left side, small black sans-serif English texts are arranged vertically: "Every boring hour in life is unique" and "Don’t Study me You won’t Graduate".

A full-frame VOGUE magazine cover filling the entire image, presented edge-to-edge. The cover is in high-fashion black-and-white with a refined female portrait; only her lips remain vividly red and glossy. The top displays the bold title “VOGUE.” At the center of the magazine, a vertical tear splits the cover open. The tear’s edges are extremely rough, jagged, and uneven, with thick fibers, torn layers, and irregular contours — the look of paper violently hand-ripped, not cleanly cut. The opening tightly hugs the shape of the lipstick, but remains chaotic and organically torn. From this vertical tear, an oversized, dramatically large version of the reference lipstick bursts outward. The lipstick does not obey realistic scale — it is intentionally huge, dominating the frame. Give the lipstick strong perspective, with the tip angled forward like a bullet head shooting at a slight upward angle toward the viewer. Half of the lipstick remains inside the dark, deep shadowed tear; the other half explodes outward, creating powerful momentum and visual impact. Emphasize the contrast between the elegant fashion cover and the brutally torn rupture with a massive, forward-thrusting lipstick breaking through it.

Use the uploaded portrait as the central subject in a vertical 9:16 aspect ratio canvas, designed as a high-end fashion magazine cover: the subject is captured in a tight chest-up close-up, with her head slightly tilted forward, facing the camera directly with a sharp, fierce, and penetrating gaze, her lips closed firmly in a calm, confident, and cool expression that combines sharpness and subtle sweetness, featuring polished, refined makeup with prominent eye makeup and clean, elegant lip makeup, and wearing a sleek, glossy black satin top that drapes smoothly over her shoulders, exuding elegance and sophistication, set against a deep, matte black background that is clean and uncluttered to keep the focus firmly on the subject. Layer the text elements in a modern editorial layout: at the top left, the word "FASHION" is displayed in a large, neat, minimalist white geometric sans-serif font; on the left side, three lines of small, clean white geometric sans-serif text are stacked vertically in a stepped, cascading layout where each subsequent line is slightly longer and extends further to the right, reading "LOVE IS WHAT CALLED A FASHION ICON", "STYLE FADE, FASHION ETERNAL", and "IT'S NOT MY ATTITUDE IT'S MY STYLE"; at the bottom left, two lines of white geometric sans-serif text appear, with "FASHION" in bold style above "JUST FOUND ME" in regular weight, all text is crisp white, creating a stark, high-contrast against the dark background, and arranged to frame the central subject, ensuring she remains the clear focal point while maintaining a polished, modern fashion magazine cover aesthetic.

Fixed shot. All elements in the frame except for the chair remain stationary, while only the chair itself is in motion. The chair rotates 360 degrees in place. Maintain consistency of the main subject. The angle of the chair in the last frame is the same as that in the first frame.

A full-frame VOGUE magazine cover filling the entire image, presented edge-to-edge. The cover is in high-fashion black-and-white with a refined female portrait; only her lips remain vividly red and glossy. The top displays the bold title “VOGUE.” At the center of the magazine, a vertical tear splits the cover open. The tear’s edges are extremely rough, jagged, and uneven, with thick fibers, torn layers, and irregular contours — the look of paper violently hand-ripped, not cleanly cut. The opening tightly hugs the shape of the lipstick, but remains chaotic and organically torn. From this vertical tear, an oversized, dramatically large version of the reference lipstick bursts outward. The lipstick does not obey realistic scale — it is intentionally huge, dominating the frame. Give the lipstick strong perspective, with the tip angled forward like a bullet head shooting at a slight upward angle toward the viewer. Half of the lipstick remains inside the dark, deep shadowed tear; the other half explodes outward, creating powerful momentum and visual impact. Emphasize the contrast between the elegant fashion cover and the brutally torn rupture with a massive, forward-thrusting lipstick breaking through it.

Background music: Rhythmic beats, cool and premium style.

Action:Unscrew the perfume bottle cap, press the nozzle on the top of the bottle, spray a small amount onto the inside of your wrist, and then tighten the cap.

EVERYTHING 50% OFF!

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.

{ "scene_sequence": [ { "source_image": "User-uploaded image 1", "description": "A young woman lying on the ground, in the exact pose from the uploaded image. Face, hair, hairstyle, and makeup locked. Wearing the hat from the uploaded image." }, { "action": "A massive, extremely heavy hat, identical in shape, size, color, and pattern to the hat on the model's head, falls rapidly from above. The hat lands on the model with force, instantly pressing her fully to the ground in a single impact, creating a realistic compression effect. The model's face shows a terrified, shocked expression." }, { "transition_to_image": "User-uploaded image 2", "description": "As the scene transitions seamlessly to the second uploaded image, the giant hat settles slightly with a subtle sway due to inertia. The model struggles with her limbs, arms and legs moving dramatically, exaggerating the comedic and surreal effect while maintaining realistic physics." } ], "motion_properties": { "continuity": "No cuts or jumps, a continuous single shot", "realism": "Physics-based motion for hat and body; heavy impact from the start", "smoothness": "Ultra-smooth transitions between actions and scenes", "scale": "Hat is massive (approx. 15–20x human size) but maintains visual realism", "timing": "Hat falls rapidly and compresses the model in one hit; model reacts immediately with terrified expression and exaggerated struggling motion" }, "visual_style": { "lighting": "Match lighting from uploaded images", "background": "Preserve environment from uploaded images", "detail": "Keep textures, patterns, and colors consistent with the source images" }, "notes": "The animation should feel magical, seamless, and comedic. Emphasize the sudden, heavy impact and the model's terrified reaction." }

From the uploaded image, the painted person on the white sketchbook page slowly begins to rise and transform into a real person. The colors of the painting turn vivid and lifelike as the texture changes from watercolor to real fabric. The camera moves smoothly from a top-down view to a lower front angle as the white paper surface gradually morphs into a bright white runway. The person continues walking naturally and gracefully as the scene transitions into the second uploaded image. The entire motion is ultra-smooth, seamless, and magical — no cuts, just a continuous realistic transformation.

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.

Street unboxing POV video using the uploaded product. 1. High-angle POV: person walks on rough asphalt in gray sneakers and dark gray pants, holding a camera that follows their steps. Natural daylight, overcast, soft shadows. 2. Eye-level mid shot: a bulging brown paper delivery bag **already resting on the street**, lying alone in the middle of a zebra crossing. **Do not show anyone holding or throwing the bag. The bag is static and was already there when discovered.** 3. Close-up: the bulging bag on the street, camera slowly and dramatically zooms in. 4. Extreme low-angle POV from inside the bag: young handsome Caucasian man looks down into the bag, surprised, mouth open, leaning toward the camera. 5. Extreme low-angle POV from inside the bag: hand enters the bag from **inside the top opening**, grabs the product **from within the bag**, lifts it up, and presents it **coming directly out of the bag** in front of the camera. **Do not take the product from outside the bag.** Ensure smooth motion, realistic lighting, immersive POV, and dramatic focus on the bag and product. Only ambient street sounds, no voiceover or music.

Use the character from the uploaded image exactly as it appears — keep all features, colors, proportions, and style unchanged. Create a four-panel comic/storyboard with each panel showing a different scene of the character. Maintain the same cartoon art style as the reference image. Add speech bubbles/dialogues for the character in each panel, appropriate to the story. Ensure visual continuity: same background style, color palette, and lighting consistent across all panels. Focus on clear composition, expressive poses, and readable dialogue. Output: four distinct panels forming a coherent story.

Use the character from the uploaded image exactly as it appears — keep all features, colors, proportions, and style unchanged. Create a four-panel comic/storyboard with each panel showing a different scene of the character. Maintain the same cartoon art style as the reference image. Add speech bubbles/dialogues for the character in each panel, appropriate to the story. Ensure visual continuity: same background style, color palette, and lighting consistent across all panels. Focus on clear composition, expressive poses, and readable dialogue. Output: four distinct panels forming a coherent story.

The image is dominated by black, white and gray, with only the figure retaining color. It combines modern minimalism and collage art, and the frame is divided by geometric color blocks. The photo is a close-up portrait in a 3:4 aspect ratio, taking up 35% of the frame. It is placed on the left side, with equal distance from the top and bottom edges. In the photo, the model has fresh and delicate makeup, with sharp and confident eyes looking directly at the camera. She wears a dark gray thick cable-knit sweater with clear fabric texture, standing sideways with relaxed and natural shoulder lines. The photo has a solid light gray rectangular background. At the top of the image is the large two-tone serif font "STYLE" — "STY" in black and "LE" in white, with the small black sans-serif text "Enjoy time alone" underneath. At the bottom left is the small black sans-serif text "SHOW YOURSELF", extended by a thin white line. On the upper right, the white sans-serif words "CONFIDENCE" and "BEAUTIFUL" are arranged vertically.

Use the uploaded portrait as the central subject in a 9:16 vertical canvas: the subject poses confidently with one hand on hip, head tilted back, gaze to camera, wearing a loose white blazer, black choker, pearl necklace, black satin shoulder ribbon, geometric pearl-accent earrings, and red nail polish. The background is a smooth light gray-to-deep pink gradient overlaid with soft white snowflake bokeh. Layer text elements: large semi-transparent deep red bold sans-serif "SHOP NOW" spans the upper half behind the subject; a glowing deep red rectangular banner in the lower-middle holds bold white sans-serif "A LOVER'S GIFT"; centered white sans-serif text at the bottom reads "Up to 60% OFF on Women's Dress Valentine's Day Promo". Flank the subject with vertical columns of alternating solid/outlined red-pink hearts, and anchor bottom corners with solid/outlined white hearts for a romantic promotional aesthetic.

This is a vertical greeting card with a soft, pale cream-colored background that fills the entire canvas, designed to express love and gratitude to a mother. There is no additional outer border; instead, lush, realistic flowers and plants are placed directly at the outermost edges of the image to form a natural border, with a flat, graphic style that is not colored pencil-like, featuring a variety of green leaves in different shades—from deep emerald to bright lime—and diverse shapes, including broad rounded tropical leaves, elongated fern-like fronds, and delicate serrated foliage, creating a vibrant natural frame. Scattered among the green leaves are three prominent pink flowers with layered petals and yellow centers (resembling camellias), along with small clusters of bright red berries and tiny green leaf accents, adding pops of color and detail to the border. Centered horizontally in the middle of the card is the heartfelt text: "THANK YOU\nFOR ALWAYS BEING\nTHERE FOR ME,\nMUM,\nI LOVE YOU." The text is rendered in a rich deep chocolate brown color, using a friendly, rounded handwritten script font with a casual, warm, and slightly playful appearance, with each line evenly spaced to create a balanced, inviting composition that draws the viewer’s eye to the affectionate message. The overall aesthetic is cozy, tender, and naturally fresh, with the botanical elements at the edges framing the central text to convey sincere love and gratitude to a mother.

A racing movie poster design called "CHARGE". It depicts a dilapidated racing car speeding in the desert with flying dust behind it.

A movie poster titled "Interstellar" features an astronaut as the subject and the Earth in the background

Keep the main body of the hamburger. Generate 1 product marketing poster and let your creativity run wild

A movie poster called "Daydreamer", a picture of an old lady and an old man supporting each other

A family movie poster called "ORDINARY WARMTH" with the subtitle "HAPPINESS COMES LIKE A GIFT DIRECTOR AND ACFORS" depicts a couple sitting on the beach with their children, and a puppy playing next to them, creating a warm and cozy atmosphere.

Refer to the color matching, composition and flower elements in Figure 2. Make significant changes to Figure 1, but do not alter the product