Create yours here httpswavespeedairefivanna 1 PROMT...
Reference image from @ivanka_humeniukView Original

Create yours here httpswavespeedairefivanna 1 PROMT

Image-to-Image

Prompt

Create yours here - https://wavespeed.ai/?ref=ivanna 1 . 📌PROMT: (Nano Banana Pro) SHOT: shot_size: Extreme wide top-down aerial covering the entire street, the whole human-mosaic portrait laid flat across the roadway and filling the frame edge to edge, only thin strips of building rooftops and packed sidewalks along the far left and right margins, no horizon and no sky in frame. camera_angle: True nadir bird's-eye, drone directly above the center of the formation pointing straight down at 90 degrees, sensor plane exactly parallel to the flat ground, zero tilt and zero perspective convergence. azimuth: Looking straight down, the portrait oriented upright on the roadway with the top of the head toward the upper frame edge and the chin toward the lower edge. subject_placement: Portrait centered and symmetrical, occupying the full central roadway rectangle, flanked by dense crowds on both sidewalks. focal_anchor: Even razor-sharp focus across the entire flat formation from edge to edge. SUBJECTS: subject_1: description: A single enormous coordinated flashmob of tens of thousands of real Spain football supporters packed across the street, holding up flat colored cards and cloth panels while wearing red, yellow, white and dark clothing, so that seen only from directly overhead their arranged positions and colored material tessellate into one flat legible portrait of Lamine Yamal's face lying completely flat on the road surface like a giant stadium card-stunt tifo. The face is composed exclusively of people and the cards they hold, a two-dimensional mosaic, its likeness coarse up close and clearly readable as Lamine Yamal's face from this height. Individual people remain visible throughout with natural skin texture and realistic gloss, natural glow, skin grain, soft matte finish, no smoothing. asymmetry_mapping: The portrait's natural micro-asymmetry is organic and lifelike, not idealized. wardrobe: Red and yellow striped jerseys, red tees, white and yellow cards and dark cards, their combined luminance forming the light and shadow of the face, matching the red-and-yellow national palette of Spain. mood: Euphoric but tightly coordinated, the formation held steady at the peak of a mass celebration. SCENE: action: The crowd holds the portrait formation steady while flags wave at the outer edges of the street and fine confetti drifts down across the roadway, a real live flashmob moment caught in a single overhead drone frame. props: Thousands of colored hand-held cards forming the mosaic pixels, red and yellow Spanish flags with the coat of arms waving around the perimeter, and a fabric banner stretched across the street near the top of the frame reading ESPANA. location: A wide central avenue in Madrid Spain seen from straight above, the roadway filled by the formation, warm clear midday, only rooftops and top edges of ornate European stone buildings along the extreme left and right margins. LIGHT: key: High overhead midday sun at roughly 5600K casting nearly straight-down soft light that illuminates the flat formation evenly so the mosaic reads by garment and card color rather than by relief. fill: Broad open-sky fill from every direction, minimal directional shadow, keeping the whole ground plane legible. rim: Skip if absent. ambient: Even sky illumination across the roadway with faint warm bounce from the surrounding facades at the frame edges. falloff: Flat and even across the whole formation with no strong gradient. motivated_by: The high midday sun almost directly overhead above the open street. atmosphere: Very light haze at roughly 10 percent, fine confetti particles suspended above the crowd, subtle real-air softness. material_response: Matte cotton and card stock absorb light softly, flag fabric catches a slight sheen at the edges, skin holds natural texture, darker cards and clothing sink to define the features. integration: Soft contact shadows directly beneath each person, confetti casting tiny speckled shadows, the whole formation sitting believably on the real road surface. TEXT_ELEMENTS: visible_text: "ESPANA" (Spanish) typography: Bold condensed sans-serif, dark lettering on a stretched red and yellow fabric banner, slightly weathered. placement: Stretched across the street near the top edge of the frame, seen flat from directly above. rendering_quality: Rippled sunlit fabric with the letters following the folds, integrated with the natural midday light. LOOK: color_grading: Authentic press-drone documentary grade with natural moderate contrast, a dominant red and yellow palette over warm skin midtones, gentle highlight rolloff and naturally lifted shadows, a true-to-life euphoric daylight mood with no stylization or glossy finish. authenticity: Genuine aerial news-photograph realism resolving thousands of distinct individual people, real photographic grain, faithful lens perspective, no CGI smoothness and no cloned repeated figures. style: Photoreal top-down documentary drone photograph, horizontal 16:9 framing, editorial photojournalism aesthetic, a flat human-mosaic card-stunt portrait formed by a real street crowd. 2 . 📌PROMT: (Nano Banana Pro) SHOT: shot_size: Extreme wide top-down aerial covering the entire street, the full flag mosaic laid flat across the roadway and filling the frame edge to edge, only thin strips of building rooftops and packed sidewalks along the far left and right margins, no horizon and no sky in frame. camera_angle: True nadir bird's-eye, drone directly above the center of the formation pointing straight down at 90 degrees, sensor plane exactly parallel to the flat ground, zero tilt and zero perspective convergence. azimuth: Looking straight down, the flag oriented upright on the roadway, the banner at the top edge of the frame. subject_placement: Flag mosaic centered and symmetrical, filling the entire central roadway rectangle as one clean upright rectangle, flanked by dense crowds on both sidewalks. focal_anchor: Even razor-sharp focus across the entire flat formation from edge to edge. ACTIVE_REFERENCE: lock: Identical to the attached reference image in every element, the same street in Spain, the same crowds lining both sidewalks, the same ESPANA banner, the same framing, confetti, light and grade. The only change is the central roadway mosaic, now a complete Spanish flag instead of the portrait. SUBJECTS: subject_1: description: A single enormous coordinated flashmob of tens of thousands of real people packed across the street, holding up flat colored cards so that seen only from directly overhead their material forms one complete flat mosaic of the Spanish national flag as a perfect upright rectangle covering the whole roadway from just below the banner to the bottom edge of the frame. The flag is exactly three horizontal stripes stacked top to bottom and spanning the full width, each a straight horizontal band with clean horizontal edges. Top stripe red, occupying the upper quarter. Middle stripe yellow, twice as tall as each red stripe, occupying the central half. Bottom stripe red, occupying the lower quarter. The coat of arms sits on the yellow middle stripe slightly left of center, rendered in small cards. The whole rectangle contains only red and yellow arranged as these three flat parallel horizontal bands, filling every part uniformly with no darker regions, no curved rings, no concentric arcs, no dark mass at the bottom. Coarse mosaic tiles up close, cleanly readable as the red-yellow-red flag from this height. Individual people remain visible throughout with natural skin texture and realistic gloss, natural glow, skin grain, soft matte finish, no smoothing. wardrobe: Held cards strictly in two colors only, red and golden yellow, and nothing else, no black cards, no navy, no charcoal, no brown anywhere in the mosaic; the surrounding sidewalk people in red and yellow jerseys. mood: Euphoric but tightly coordinated, the formation held steady at the peak of a mass celebration. SCENE: action: The crowd holds the complete flag formation steady while flags wave at the outer edges of the street and fine confetti drifts down across the roadway, a real live flashmob moment caught in a single overhead drone frame. props: Thousands of colored hand-held cards forming the mosaic pixels of the three flag bands, red and yellow Spanish flags waving around the perimeter, and the fabric ESPANA banner stretched across the street near the top of the frame. location: A wide central avenue in Madrid Spain seen from straight above, the roadway fully covered by the flag formation, warm clear midday, only rooftops and top edges of ornate European stone buildings along the extreme left and right margins. LIGHT: key: High overhead midday sun at roughly 5600K casting nearly straight-down soft light that illuminates the flat formation evenly so the flag reads by card color rather than by relief. fill: Broad open-sky fill from every direction, minimal directional shadow, keeping the whole ground plane legible. rim: Skip if absent. ambient: Even sky illumination across the roadway with faint warm bounce from the surrounding facades at the frame edges. falloff: Flat and even across the whole formation with no strong gradient. motivated_by: The high midday sun almost directly overhead above the open street. atmosphere: Very light haze at roughly 10 percent, fine confetti particles suspended above the crowd, subtle real-air softness. material_response: Matte card stock absorbs light softly, flag fabric catches a slight sheen at the edges, the red and yellow bands staying flat and even so the band boundaries read as clean straight horizontal lines. integration: Soft contact shadows directly beneath each person at the perimeter, confetti casting tiny speckled shadows, the whole formation sitting believably on the real road surface. TEXT_ELEMENTS: visible_text: "ESPANA" (Spanish) typography: Bold condensed sans-serif, dark lettering on a stretched red and yellow fabric banner, slightly weathered. placement: Stretched across the street near the top edge of the frame, seen flat from directly above. rendering_quality: Rippled sunlit fabric with the letters following the folds, integrated with the natural midday light. LOOK: color_grading: Authentic press-drone documentary grade with natural moderate contrast, a dominant red and yellow palette, gentle highlight rolloff and naturally lifted shadows, a true-to-life euphoric daylight mood with no stylization or glossy finish. authenticity: Genuine aerial news-photograph realism resolving thousands of distinct individual people, real photographic grain, faithful lens perspective with no exaggeration, no CGI smoothness and no cloned repeated figures. style: Photoreal top-down documentary drone photograph, horizontal 16:9 framing, editorial photojournalism aesthetic, a flat human-mosaic card-stunt of the complete Spanish flag formed by a real street crowd. 3. 📌PROMT: (Seedance 2.0) SCENE CONTEXT A World Cup street celebration in central Madrid, Spain. A giant human-mosaic portrait made of a packed crowd holding colored cards fills the avenue; the crowd flips their cards in a travelling wave and the portrait transforms into the full Spanish flag; the camera then swoops down over the roaring fans and lands among real supporters crying and embracing with joy. One continuous 15-second celebration. ACTIVE REFERENCES @image1: the giant flat human-mosaic portrait formed by the street crowd holding colored cards, seen straight down from above. 100% matches the reference. Present in the first beat and as the starting state of the card-flip wave. @image2: the giant flat human-mosaic of the Spanish flag, three horizontal bands red then a taller yellow then red with the coat of arms on the yellow band, seen straight down. 100% matches the reference. It is the ending state of the card-flip wave. LOCATION MAP Foreground: dense celebrating crowd and colored cards covering the roadway. Midground: the mosaic formation, red and yellow flags waving along both sidewalks, confetti in the air. Background: ornate stone Madrid facades with flags on the balconies and an ESPANA fabric banner across the top of the street. High midday sun almost straight overhead. Camera begins far above the street center looking straight down, later swoops down and forward into the crowd. FIRST FRAME / BLOCKING Open already on the finished mosaic portrait from @image1 filling the frame from directly overhead, cards held up, flags rippling at the edges, confetti mid-fall. Striking non-empty first frame, portrait centered and symmetrical. FORMAT MODE The portrait-to-flag change is ONE continuous in-camera card-flip wave, the camera does not cut during it. After the flag is complete the sequence uses hard cuts. HARD CUT at 7.0s (aerial flag to descent), HARD CUT at 11.0s (descent to ground embrace), HARD CUT at 13.2s (embrace to shoulder-lift). OPTICS Segment A 0.0-3.3s: 84 degrees FOV, true nadir straight-down, no drift mid-segment. Segment B 3.3-7.0s: 84 degrees FOV, true nadir straight-down, no drift mid-segment. Segment C 7.0-11.0s: 84 degrees FOV wide immersive swoop, no drift mid-segment. Segment D 11.0-13.2s: 29 degrees FOV, eye-level close, no drift mid-segment. Segment E 13.2-15.0s: 47 degrees FOV, low angle looking up, no drift mid-segment. CAMERA Segment A: drone locked directly above the street center at roughly 55 meters pointing straight down, sensor parallel to the ground, extremely slow push down at 3 km/h. Segment B: same nadir position, holding steady with a barely-there push at 3 km/h so the travelling card-flip wave stays perfectly legible from above. Segment C: the drone descends smoothly from 45 meters while pitching up from straight-down to a forward horizon view, decelerating from 18 km/h to 4 km/h, gliding to a stop at head height about 2 meters above the upraised hands of the crowd, the standing fans and the road always remaining below the lens. Segment D: handheld at eye level, a slow 2 km/h arc around two embracing fans, tiny 1 cm handheld tremor, warm and intimate. Segment E: handheld low angle looking up at a fan hoisted on shoulders, the camera bobs and lifts with the crowd. ACTION 0.0-3.3s: the mosaic portrait from @image1 is alive, thousands of held cards shimmer with micro-adjustments, red and yellow flags whip along the sidewalks, confetti drifts down; camera eases down. 3.3-7.0s: a coordinated card-flip wave runs as a clearly visible line sweeping from the top edge of the mosaic down to the bottom over about three seconds; as the flip-line passes each row the people flip their two-sided cards and that row changes color, so the giant portrait dissolves row by row and reforms into the clean red-yellow-red Spanish flag with the coat of arms from @image2, the moving flip-line plainly travelling across the formation, flags waving and confetti falling throughout. 7.0s HARD CUT: the camera swoops down over the celebrating crowd, faces and flags rising toward the lens as it levels out among them. 11.0s HARD CUT: eye level in the crowd, two fans in red Spain national-team jerseys throw their arms around each other, one with tears streaming down his face, both breaking into open-mouthed roars of joy, a Spanish flag over their shoulders. 13.2s HARD CUT: a young fan in the red jersey is lifted onto shoulders, arms flung wide, screaming with elation, red and yellow flags and confetti bursting around, the crowd bouncing and roaring. PERFORMANCE Ground fans show sincere joy only, read through muscle: eyes glistening and brimming with real tears, cheeks lifted hard, wide genuine open-mouthed smiles, brows raised, chests heaving, tight real embraces. Pore-level skin with natural texture and realistic gloss, natural glow, skin grain, soft matte finish, capillary flush on the cheeks, catchlights and living moisture in the eyes, individual distinct human faces with natural micro-asymmetry, anatomically correct hands with five fingers and natural body proportions. Clearly football supporters in red Spain national-team jerseys, scarves and face paint in red and yellow. PHYSICS Confetti falls and tumbles under gravity, settling on hair and shoulders. Flags ripple and snap with real fabric weight. Held cards flip in the travelling wave with real paper mass. Bodies press, bounce and sway with real inertia, soft contact shadows beneath every person, the lifted fan carries real weight on the shoulders below. LIGHTING High midday sun at 5600K almost directly overhead, even and bright across the formation so the mosaic and the card-flip wave read by card color. At ground level the same warm sun keys the faces from above with soft open-sky fill lifting the shadows and warm bounce off pale facades wrapping the skin. Fog density 8 percent, fine confetti suspended in the air. COLOR GRADE Naturalistic press-documentary grade, moderate contrast, dominant red and yellow palette over warm skin midtones, gentle highlight rolloff on the sunlit crowd, naturally lifted shadows, euphoric true-to-life daylight mood with no stylization. AUDIO Continuous across all 15 seconds as one unbroken wall of sound: a massive stadium-style crowd roar with a rhythmic football chant of "Espana! Espana!", thousands of voices, bouncing drums, whistles and an air horn, flags snapping in the wind, confetti cannons popping, the raw ambient hum of a real on-location field recording, no music. STYLE Photoreal ultra-detailed authentic footage, aerial drone realism for the overhead beats and handheld documentary realism for the ground beats, thousands of distinct real individuals, fine natural film grain, faithful lens perspective, genuine on-the-street news-capture look. OUTPUT SETTINGS 16:9 horizontal, real-time speed from start to finish across every segment, high resolution maximum detail. POSITIVE LOCKS The portrait-to-flag change is a visible travelling card-flip wave, a smooth continuous transformation with the flip-line moving across the crowd. The camera descent stays above the standing fans and levels at head height, the people and the road remaining below the lens throughout. Every face is a real distinct human with natural asymmetry, matte lifelike skin and correct anatomy, hands with five fingers, coherent bodies. Ground fans are clearly football supporters in red Spain national-team jerseys. Emotions stay sincere joy only. The crowd cheers and chants from the very first frame. Real-time throughout with relentless energy.

How This Prompt Works

Create yours here - 1 . 📌PROMT: SHOT: shot_size: Extreme wide top-down aerial covering the entire street, the whole human-mosaic portrait laid flat...

Use a clean reference image with obvious subject edges and readable facial or product details before you start changing the styling. Keep the generator on 16:9 for the closest match. The mood is anchored by individual people remain visible throughout with natural skin texture and realistic gloss, natural glow, skin...

Best Settings

Recommended Aspect Ratio
16:9
Recommended Style
Scale-Play, Editorial, 35mm Film, Photorealistic
Negative Prompt
ugly, deformed, low quality, blurry, text, watermark, worst quality, low res
Recommended Model
Nano Banana Pro

What to Change First

  • ✓
    Change the subject block first: Create yours here - 1 .
  • ✓
    Adjust the mood through light and backdrop cues: Individual people remain visible throughout with natural skin texture and realistic gloss, natural glow, skin grain,...
  • ✓
    Keep the finish constraints aligned while you test variants: focal_anchor: Even razor-sharp focus across the entire flat formation from edge to edge.

Before You Generate

Note 1

Start with a sharp reference image. This prompt is written to preserve source identity, silhouette, or product structure before stylization.

Note 2

Use 16:9 on the first run, then test alternate crops after the base composition is working.

Note 3

This prompt suppresses text or logos. Remove that constraint before asking for branded packaging, typography, or visible watermarks.

Best For

  • Portrait studies, beauty concepts, and tightly framed editorial references.
  • Reference-image workflows where identity, product shape, or silhouette should survive the restyle.
  • Cinematic, mood-first outputs where light direction carries a lot of the final image quality.

Skip This Prompt If

  • You need a wide environment shot or multiple subjects competing for attention in the same frame.
  • You need to begin with a radically different crop than 16:9 instead of honoring the existing composition hints.
  • Your reference image is low-resolution, badly lit, or cluttered enough to break subject preservation.

Mistakes to Avoid

  • Ignoring the recommended 16:9 crop on the first run. The prompt's composition cues were written for that frame.
  • Using a muddy reference image and expecting the prompt to repair identity, silhouette, or packaging structure on its own.
  • Asking for readable type, logos, or packaging text without first removing the no-text constraint.

3 Ways to Adapt This Prompt

Use these as safe starting edits so you keep the prompt's structure while still making it your own.

Swap the subject, keep the frame

Replace create yours here - 1 . with your own subject while leaving the camera and composition cues intact.

Retune the mood, not the structure

Keep the subject block, then rewrite individual people remain visible throughout with natural skin texture and realistic... to move the image into a new lighting setup.

Push the restyle with a cleaner reference

Start from a sharper or more contrasty source image, then edit finish descriptors only after subject preservation is stable.

Generate This Image

Use our professional tools to tweak this prompt and generate your own version in seconds.

GPT Image 2 Generator

GPT Image 2 Generator
Reference Image(0/9)
18564 / 8000Prompt is too long, please delete some content
Cost 4 creditsRemaining 0 credits
Image Preview

No Images Generated