AI Image Prompts

A social media call-to-action graphic with a blurred portrait background of a young woman in dark clothing, overlaid with large Spanish text inviting viewers to comment a keyword in exchange for receiving the prompts used. In the center, there is a screenshot of an Instagram profile card, with arrows and additional text promoting free resources available through the profile link. The design uses bold white lettering with green highlight accents and a dark, blurred creator-style background.

GLOBAL LOCK: vertical prompt-demo social post with split layout, top half showing a moonlit cedar forest training scene outside Nara at genuine midnight, bottom half a persistent black prompt card with yellow-white text and bright yellow CTA reading 'Comment AI for prompts'. Top sequence uses only real full-moon illumination through tall cedar trunks, cool blue-black shadows, strong 1970s Japanese cinema mood. Main subject is a brown tabby cat in black training clothes performing strikes against tree trunks and moving through patches of moonlight. Secondary subject is a 50-year-old Japanese trainer wrapped in a dark blanket sitting cross-legged on a broad flat boulder, holding a small oil lamp with the wick turned very low. No artificial light, only moonlight and the tiny lamp glow.
[00:00-00:04] Establish the genuine midnight cedar forest with full moon visible through the canopy, then reveal the tabby cat in dark training clothes darting among the trunks and striking bark in a fast, disciplined martial-arts rhythm above the static prompt card.
[00:04-00:08] Cut to the older Japanese trainer seated on a flat stone wrapped in a blanket, small lamp glowing beside him, posture calm and observant, deep forest blackness behind, prompt text fixed below.
[00:08-00:12] The cat returns into frame near the trainer, tail raised, movement slowed after practice, moonlit fur flickering as clouds pass the moon, the trainer remains still and silent, bottom prompt panel unchanged.
[00:12-00:15] Final hold on the quiet aftermath: trainer on the boulder, tabby settling beside him in the cedar darkness, moonlight and tiny lamp providing the only illumination while the prompt card and comment CTA remain visible until the end.

GLOBAL LOCK: A vertical 9:16 AI-creator tutorial reel arguing that conversational agents are replacing manual prompt engineering. The video alternates between premium stylized campaign images, oversized typography, and a minimal dark chat interface that feels like talking naturally to an AI assistant. The visual examples should look like modern fashion and beauty advertising: surreal editorial portraits, glossy skin, bold colors, high-contrast studio backgrounds, and one sunscreen-style product campaign that can be revised without losing the same product identity or lighting logic. The tone is provocative, future-facing, and persuasive, with the visual goal of making “just talk to the AI” feel easier and more powerful than writing prompts from scratch.

[00:00-00:12] Open with striking stylized campaign visuals and large text claiming that prompting is outdated. Show editorial fashion portraits such as a woman in a sparkling pink outfit riding a white horse against a cloud-filled sky, then a seated model against a saturated red background with a laptop and statement styling. These images should look intentionally aesthetic-first, designed to stop the scroll while the text makes a contrarian claim.

[00:12-00:20] Transition into the mechanism. Cut to a dark chat interface with a simple user message like “Bro lets make a sunscreen” or similarly casual natural-language phrasing. The interface should feel conversational, not technical, reinforcing that the creator is speaking to an agent rather than building a detailed prompt manually. The idea is that the AI asks follow-up questions, understands the style, and handles the image construction.

[00:20-00:28] Show the resulting sunscreen campaign visuals. Use beauty-ad framing with glossy skin, bright sky or concrete backdrop, strong makeup styling, and a product held close to the camera. One shot should make the consistency benefit explicit with messaging like “no starting over,” implying that revisions keep the same product and same lighting. The campaign should feel premium and coherent, not like disconnected images.

[00:28-00:32] End on the thesis frame. Show another surreal editorial portrait with text emphasizing that the future is conversation, not prompt engineering. The final CTA should invite viewers to comment “AGENT” if they are done rewriting prompts from scratch. Leave the viewer with the sense that AI creation is becoming more like directing a collaborator than operating a text box.

NEGATIVE PROMPT: clunky prompt-box tutorial aesthetic, generic stock beauty ad, inconsistent product between revisions, flat lighting, overexplained UI, low-detail fashion imagery, awkward skin texture, random composition changes, amateur text placement, robotic tone.

SHOT PROMPTS: prompting is outdated reel; editorial horse fashion portrait; red backdrop laptop model; conversational AI chat for sunscreen campaign; beauty product ad with same lighting; no starting over product consistency; future is conversation text frame; Hedra Agent CTA.

SPEECH PACK: If voice is implied, it should sound casual, provocative, and creator-native, as if exposing a workflow shortcut. Emphasize “talk to it,” “same product,” “same lighting,” and “comment AGENT.”

[Subject] A high-contrast black-and-white editorial portrait of a curly-haired man with light stubble wearing a plain black t-shirt, posed with one hand reaching toward the camera in extreme foreground blur while his head tilts downward in a concentrated, introspective expression. The figure should feel like a fashion-model or actor study captured mid-gesture, with the outstretched hand creating depth and immediacy while the face remains the emotional anchor.

[Environment] The background is a simple studio or seamless backdrop with no environmental clutter, allowing the portrait, gesture, and typography to dominate. The image is framed inside a visible analog film-border treatment reminiscent of Kodak negative edges, adding an archival and cinematic reference layer. Over the portrait sits bold Portuguese display text reading “Prompts para retrato editorial,” integrated like an Instagram educational cover slide.

[Composition/Camera] Vertical cover-image composition. The subject occupies most of the frame from chest upward, with the blurred foreground hand entering from the lower-left area and moving toward the viewer. The face sits in the upper-right region, looking downward rather than directly into camera, creating tension between distance and introspection. The composition should feel like a fashion-editorial photograph repurposed into a social-media title card.

[Lighting] Soft but directional studio lighting in monochrome, with strong tonal separation between hair, skin, and black shirt. The lighting should sculpt the cheekbones, nose bridge, curls, and beard texture while keeping the background clean and unobtrusive. Contrast should be crisp without losing detail in hair or shadow-side facial planes.

[Style/Rendering] Premium black-and-white editorial portraiture, analog-film-inspired border treatment, shallow depth of field, fashion-magazine realism, subtle grain possibility, and educational social-post overlay design. The result should feel like a cross between a Vogue test shoot, a Kodak contact-sheet frame, and an Instagram carousel cover for portrait prompts.

[Detail constraints] Preserve the curly hair, downcast gaze, plain black t-shirt, and the strong blur of the reaching hand. Keep the background minimal. Maintain the large text overlay as part of the design and retain the film-border edges. Avoid turning the portrait into cinematic action or adding irrelevant props. The mood should remain restrained, stylish, and intellectually serious.

Negative prompt: extra fingers, malformed hand blur, distorted face, cheesy glam lighting, cluttered background, colorful wardrobe, low-detail curls, cartoon rendering, heavy HDR, random props, overdone skin smoothing, missing film border, unreadable text, watermark, logo overload, action-pose exaggeration, busy set design.

Suggested parameters: ar 4:5, black-and-white editorial portrait, shallow depth of field, film-border frame, high contrast, soft studio light, fashion realism, social-cover composition.

Delta prompt strategy: If the portrait loses depth, add “foreground hand reaching toward camera in heavy blur, face sharp behind it.” If the face becomes generic, add “angular male editorial portrait with curly hair, stubble, and focused downward gaze.” If the monochrome feels weak, add “rich black-and-white tonal separation with clean studio contrast.” If the image turns too cinematic, add “minimal fashion-editorial studio portrait, not movie still.” If the text overlay disappears, add “large Portuguese title text integrated across the center like a carousel cover.” If the film reference gets lost, add “visible Kodak-style film border framing the entire image.” If the shirt gains detail, add “plain fitted black t-shirt with no logo or pattern.” If the hand deforms, add “natural realistic hand gesture with intentional lens blur rather than anatomy error.” If the image feels empty, add “editorial cover design energy with portrait plus educational headline.” If the mood loses seriousness, add “restrained, intelligent, moody fashion-study tone.”

GLOBAL LOCK: cinematic martial-arts sparring scene on a minimal indoor training mat with dark background; young woman with long dark hair in a rust-orange jacket facing an older bald bearded male opponent in dark blue-gray clothing; controlled hand-to-hand choreography, blocks, strikes, and defensive movements; grounded action realism; moody studio lighting; intimate fight-camera framing; no text overlays, no logos, no crowd, no weapons, no fantasy effects.

00:00-00:03
Open with low and medium angles on a sparse training space, establishing two barefoot fighters squared off on a warm-toned mat. The female fighter in rust-orange takes focus while the male opponent waits in guard stance.

00:03-00:07
The camera moves into tighter single and over-the-shoulder views as the woman advances. Both fighters exchange measured blocks and feints, keeping the action sharp, disciplined, and highly readable.

00:07-00:11
The sparring intensifies into close-range hand combat. Arms snap into frame for parries, palm checks, and compact strikes, with the camera alternating between profile and frontal confrontation angles.

00:11-00:15
The duel resolves in a tense face-to-face exchange, both fighters still in guard, preserving the feeling of a choreographed martial-arts prompt demo rather than a chaotic brawl.

NEGATIVE PROMPT:
crowded arena, bright daylight dojo, swords, guns, fantasy magic, exaggerated wire-fu flips, comedy reactions, blood, broken anatomy, extra fighters, text banners, UI panels, low-resolution motion smear, superhero costumes

GLOBAL LOCK: The video consists of a series of "impossible POV" shots where the camera is placed inside objects. The visual style is consistently cinematic, photorealistic, and high-detail. Lighting is motivated by the environment, often warm and soft. The camera uses macro or wide-angle lenses depending on the internal space. Textures like skin, metal, and liquid are hyper-detailed.

[00:00–00:02]
Subject: A young Caucasian girl with light brown hair, wearing a dark blue hoodie.
Environment: Viewed from inside an open human mouth. The camera is placed on the tongue.
Action: The girl leans forward toward the camera as if to kiss it or look closely.
Framing: Extreme macro. The upper and lower rows of teeth and pink gums frame the top and bottom of the image.
Lighting: Soft, natural light coming from behind the girl, creating a slight rim light on her hair.
Motion: Subtle movement of the girl's head and the camera's slight handheld shake.

[00:03–00:06]
Subject: A mailman in a blue uniform and gloves.
Environment: Viewed from inside a dark metal mailbox looking out onto a city street. A brown UPS truck is parked in the background.
Action: The mailman opens the door and slides a stack of white envelopes into the mailbox toward the camera.
Framing: Wide-angle POV. The dark interior of the mailbox frames the street scene.
Lighting: Bright, overcast daylight outside; the interior of the box is in deep shadow.
Motion: Fast motion of the mail being inserted.

[00:07–00:10]
Subject: A person's fingers (macro skin texture).
Environment: Viewed from inside the eye of a large sewing needle.
Action: A thick, blue-colored thread is being pushed through the eye of the needle toward the camera.
Framing: Microscopic macro. The scratched, silver metallic edges of the needle eye dominate the frame.
Lighting: Harsh, direct studio lighting highlighting the metallic texture and skin pores.
Motion: Slow, deliberate threading motion.

[00:11–00:15]
Subject: A man's eye and forehead.
Environment: Viewed from inside an antique brass clock mechanism.
Action: A man stares through a circular opening in the clock face, his eye moving as he inspects the gears.
Framing: Close-up. Large, out-of-focus brass gears and springs frame the circular opening.
Lighting: Warm, golden light reflecting off the brass components.
Motion: Rotating gears in the foreground; the man's eye blinks and shifts.

[00:16–00:19]
Subject: Carbonated dark liquid (cola).
Environment: Viewed from the bottom of a metallic soda can, looking upward toward the opening.
Action: Dark liquid rushes into the can, creating violent streams and a mass of dense, fizzy bubbles that explode toward the lens.
Framing: Dynamic POV. The circular opening of the can is at the top of the frame.
Lighting: Backlit through the can opening, creating high-contrast highlights on the bubbles.
Motion: Fast, turbulent fluid dynamics.

[00:20–00:23]
Subject: A coastal landscape with a lighthouse.
Environment: Viewed from deep within the cranial cavity of a weathered, sun-bleached skull resting on a beach.
Action: Static landscape shot.
Framing: The two eye sockets and nasal cavity of the skull frame the ocean and lighthouse in the distance. Cobwebs are visible inside the skull.
Lighting: Natural, diffused daylight.
Motion: Subtle waves in the background; slight camera drift.

[00:24–00:28]
Subject: The internal anatomy of a flower.
Environment: Viewed from the center of a blooming tulip or lily.
Action: Looking outward from the base of the pistil.
Framing: Large, yellow stamens with pollen grains tower like pillars around the frame; soft pink/orange petals form the "walls."
Lighting: Bright, ethereal sunlight filtering through the translucent petals.
Motion: Pollen particles floating in the air; gentle swaying of the petals.

[00:29–00:33]
Subject: A girl blowing out a candle.
Environment: A birthday cake with colorful blue and yellow frosting.
Action: The camera is placed low in the frosting. A girl leans down into the frame and blows toward a single lit candle.
Framing: Low-angle macro. Swirls of frosting frame the bottom and sides.
Lighting: Warm, flickering candlelight; soft bokeh of party lights in the background.
Motion: The flame flickering and then being extinguished; smoke rising.

[00:34–00:38]
Subject: Text on black background.
Action: "COMMENT 'ARCADS' FOR THE PROMPTS" appears in bold white and yellow font.

NEGATIVE PROMPT: blurry, low resolution, distorted anatomy, extra fingers, cartoonish, 2D, flat lighting, watermark, text (except for the intended overlays), shaky camera, glitchy transitions, unrealistic physics.

SPEECH PACK:
[00:00–00:33] No speech, only background music.
[00:34–00:38] Text-to-speech or silent CTA.
Transcript: "Comment 'ARCADS' for the prompts."
TAKE_A: (Energetic) Comment ARCADS for the prompts!
TAKE_B: (Direct) Just comment ARCADS and I'll send you the prompts.
TAKE_C: (Casual) Want these? Comment ARCADS.

GLOBAL LOCK: Cinematic photorealistic style, urban apocalypse setting, golden hour/dusk lighting, high contrast, wet reflective surfaces, high-octane action. Subject is a male in his late 20s, athletic build, wearing a blue short-sleeved button-down shirt and dark trousers. Environment is a modern city under destruction. Consistent warm color grade with deep shadows and glowing orange highlights.

[00:00–00:01]
Close-up macro shot of a single light-colored wooden domino with four black pips standing vertically on a dark, wet, reflective rooftop. The domino tips over and falls flat onto the surface. Warm golden sunlight creates a rim light effect. Background is a soft-focus urban skyline at dusk.

[00:01–00:04]
Wide aerial drone shot of a dense modern city. In the far background, a massive volcanic eruption sends a colossal, textured plume of dark ash and smoke into the sky. The city is being engulfed by a rolling cloud of dust. The lighting is dramatic, with the sun obscured by smoke.

[00:04–00:08]
Third-person follow shot from behind the man in the blue shirt. He is sprinting fast across a wet, dark rooftop. His forearms and hands glow with intense, internal orange molten energy, casting light onto his clothes. The camera moves rapidly with him, creating cinematic motion blur.

[00:08–00:12]
The man continues running through the chaos. Small explosions and fire erupt on the rooftop around him. The ground is glossy with rain/water, reflecting the orange glow of his arms and the fires. The camera maintains a dynamic tracking movement.

[00:12–00:15]
A black SUV/truck speeds past the man from right to left as he continues his sprint. More explosions occur in the background buildings. The scene is filled with smoke, flying debris, and high-intensity action. The camera follows the man's stride closely.

NEGATIVE PROMPT: static camera, cartoonish, low resolution, dry surfaces, bright daylight, calm environment, inconsistent character clothing, robotic movement, flickering lights, distorted limbs, blurry face, text, logos, watermark.

SPEECH PACK:
(No speech present in the video. The audio consists of cinematic sound effects and music.)
[00:00-00:01] Sound: Soft wooden click of domino falling.
[00:01-00:04] Sound: Deep, low-frequency rumble of eruption.
[00:04-00:15] Sound: Rhythmic heavy breathing, fast footsteps on wet ground, distant explosions, engine roar of SUV.

A bold social-cover image featuring a pale blonde woman centered in the frame, staring directly at the viewer with a neutral expression inside a rustic interior. She wears a brown leather jacket over a cream sweater, while behind her stands a lineup of realistic puppet- or clay-like versions of SpongeBob SquarePants characters, including SpongeBob, Patrick, Squidward, Sandy, and Mr. Krabs. The image should feel slightly uncanny but still polished, mixing grounded portrait photography with nostalgic cartoon characters reimagined as tactile practical-creature figures. Large high-impact cover text reading “NANOBANANA PROMPTS” should dominate the lower half in bold yellow and white lettering, giving the composition a clear tutorial-thumbnail or promo-cover look.

GLOBAL LOCK: vertical split-layout promo card for an AI prompt series, top half showing a fantasy cat duel in shallow water among ancient stone ruins, bottom half a persistent black title block with huge glowing yellow text reading 'SEEDANCE 2.0 PROMPTS' and smaller '(PART-9)'. Main combatant is a Siamese cat with bright blue eyes, cream coat and dark face mask, front paws wrapped in vivid orange fire, mouth open in a snarling aggressive expression. Opponent is a large white long-haired cat with icy blue glow around the chest or forepaws, hissing back in the water. Setting is moody temple-ruin columns and misty stone architecture, cinematic fantasy lighting, water reflections, elemental contrast of fire versus ice.
[00:00-00:04] Open on the Siamese cat in shallow water facing camera, both front paws burning bright orange, blue eyes fixed forward, ancient stone columns and cool mist behind, the lower half already occupied by the bold yellow 'SEEDANCE 2.0 PROMPTS (PART-9)' title block.
[00:04-00:08] Cut to side-facing confrontation as the white cat enters frame, larger and colder in tone, snarling with icy blue energy around its chest or paws while the Siamese turns toward it, fire reflecting across the water surface above the fixed title card.
[00:08-00:12] The cats clash in close and medium views, water splashing, fire and icy light colliding, Siamese lunging low while the white cat hisses and pushes back, ancient ruin background remaining dark and atmospheric, title block unchanged below.
[00:12-00:15] Final wide or medium hold on the elemental duel with opposing streams of orange flame and pale blue energy meeting across the water, then a return to the Siamese hero close-up, all while the lower title card stays readable and dominant.

MASTER PROMPT
GLOBAL LOCK: Vertical cinematic action scene in a flooded gothic hall. Two opposing fantasy sci-fi fighters battle in ankle-deep water inside a vast stone cathedral with arches, mist, and cold gray-blue lighting. One fighter is slimmer and faster, wearing a dark tactical suit with blue energy accents and wielding a long staff. The other is heavier and more armored, carrying a massive hammer-like weapon. Keep the environment stormy, reflective, and dramatic, with water splashes and strong depth. Large bold yellow title text reading SEEDANCE 2.0 PROMPTS PART-7 is baked into the lower half of the frame throughout.

[00:00-00:03] Open on both fighters facing off in the flooded hall. The fast fighter moves low and laterally through the water while the armored fighter squares up with the heavy weapon. Camera remains frontal and slightly wide to show architecture and reflection.

[00:03-00:06] The duel intensifies with splashing footwork and evasive movement. The lighter fighter slides and pivots across frame while the armored fighter advances with force. Mist and backlight deepen the cathedral atmosphere.

[00:06-00:09] Hold the same battle space as the fighters trade position in the water, creating arcs of splash and clear silhouette contrast. Emphasize the difference between speed and power in their choreography.

[00:09-00:12] End on a stronger confrontation beat with both figures still readable in the same flooded arena. Preserve the cold fantasy-action grade, reflective water surface, and monumental stone background.

NEGATIVE PROMPT
Avoid broken anatomy, muddy silhouettes, unreadable action, random extra characters, weak splashes, plastic armor, cheap game UI, jittery weapon motion, or inconsistent title text.

SPEECH PACK
No dialogue required. If audio exists, keep it as cinematic action ambience with water impacts, distant rumble, and large echoing room tone.

GLOBAL LOCK: A vertical prompt-demo social video, approximately 15 seconds, with the upper half showing a cinematic AI-generated biking sequence and the lower half permanently showing the generation prompt in dense yellow text on a black panel, ending with the CTA line “Comment AI for prompts.” The story follows a man in his 30s with Chilean heritage cues and dark curly hair, wearing a deep burgundy technical cycling jacket with a shearling collar, dark slim trousers, and suede desert boots, riding a raw titanium-finish gravel bicycle through Santiago’s historic center at golden hour. The visual world is warm amber late sunlight, narrow cobblestone streets, colonial facades, wide stone stairs at a government building, rooftop edges, and the Andes visible through atmospheric haze. The narrative escalates from street riding to stair climbing to rooftop speed to a dramatic airborne jump across the city. The upper video should feel like premium cinematic sports travel imagery; the lower prompt panel must remain readable and clearly instructional throughout. No dialogue.

[00:00-00:04] Open with the cyclist riding through Santiago’s historic center on a narrow cobblestone street in warm golden-hour light. Colonial facades, stone sidewalks, and long shadows frame the path. The rider is seen from behind or a slight rear angle, pedaling steadily uphill. The lower panel shows the prompt text block and the “Comment AI for prompts” CTA.

[00:04-00:08] Transition to the rider taking a broad staircase on the bike, climbing step by step in front of a grand historic building with columns and balustrades. The titanium gravel frame catches the warm sunlight. The prompt panel below remains fixed and legible, reinforcing that this is a prompt-engineering showcase.

[00:08-00:12] Move onto a rooftop or elevated terrace at golden hour. The cyclist accelerates toward the edge while historic domes, lamp posts, and the Andes range sit in hazy background layers. The mood shifts from exploratory urban riding into a more daring cinematic setup.

[00:12-00:15] End on the payoff shot: the cyclist launches off the rooftop parapet and becomes airborne above the colonial streets below, framed against the warm sky and distant Andes. The moment should feel impossible but graceful, like a dream version of urban gravel riding. Keep the prompt panel and CTA visible below for the entire final beat.

NEGATIVE PROMPT: avoid downhill mountain-bike styling, avoid modern neon city aesthetics, avoid unreadable prompt text, avoid wrong jacket color, avoid road bike instead of gravel bike, avoid broken wheel geometry, avoid unrealistic body posture on the stairs, avoid duplicated buildings, avoid cloudy gray lighting, avoid extra riders, and avoid generic sports-broadcast framing.

Create a funny vertical short-form video about the exact moment your favorite song comes on while you are still in the parking lot and suddenly cannot leave. The scene should take place outdoors between parked SUVs in an everyday lot under soft overcast daylight. Center the video on one expressive plus-size woman who instantly gives in to the music and starts dancing in place with zero self-consciousness. She should wear a playful glam-meets-chaotic outfit: a pale pink faux-fur jacket, a fitted beige bodysuit, layered jewelry, and slightly mismatched cozy knee socks. Her hair should be pulled back with visible pink accents, and her makeup should feel bold and exaggerated enough to support comic facial reactions.

The performance should carry the whole clip. Use medium-full framing so her arm swings, hip movements, shoulder pops, and dramatic lip-sync expressions all read clearly. Let her cycle through smug, surprised, pouty, and delighted expressions as if the song has completely taken over her body before she even made it to the car. Keep the camera fixed or lightly stabilized, like a social-media phone capture that happens to be unusually clean. The humor should come from her total commitment, the contrast between the ordinary parking lot and the oversized reaction, and the instantly relatable idea of a private music moment becoming a full public performance.

The final result should feel like a meme-ready dance reaction reel built for short-form social media: simple setup, recognizable situation, strong personality, and motion big enough to trigger shares, tags, and “this is literally me” comments.

GLOBAL LOCK: A widescreen 16:9 creator tutorial reel that alternates between premium editorial sports-fashion sample footage and clean design-forward teaching slides about prompting Nano Banana 2. The sample footage should feel like luxury golf campaign imagery captured in warm natural sunlight with shallow depth of field, subtle lens compression, and understated cinematic grading. The main male subject is a white man in his 20s with curly blond hair, light skin, athletic build, and a cream polo shirt with tailored beige pants. The main female subject is a slim brunette woman in her 20s with light-to-medium skin, shoulder-length dark hair, a white visor, powder-blue knit top, white pleated skirt, knee-high white socks, and white golf shoes. The environment is a manicured golf course with cut green grass, soft golden-hour sun, scattered golf balls, a golf cart, and affluent leisure-club atmosphere. Intercut white or cobalt-blue title cards with bold red or white typography explaining prompt ingredients like ISO, lens, aperture, white balance, natural imperfections, realism, Nano Banana 2, and color grade. Later show dark UI/tutorial screens and prompt blocks inside a product workspace. The core message is that Nano Banana 2 can create elite editorial-looking imagery only if the prompts specify camera language, realism cues, color grading, and natural imperfection.

[00:00-00:06] Open on a close side-profile shot of the curly-haired blond man on a golf course, lit by warm late-afternoon sun. Bold text appears in staggered words across the frame as he speaks or the edit emphasizes the claim that he spent days testing what works. The shot should feel expensive but natural, not overproduced.

[00:06-00:10] Cut wide to a stylized golf-course tableau: the man crouches beside a woman about to putt. She wears a white visor, blue knit top, and white skirt. The grass is immaculate, several golf balls dot the green, and the composition feels like a luxury fashion editorial rather than ordinary sports coverage.

[00:10-00:14] Move into a seated portrait of the woman in a golf cart, looking directly at the camera. Use natural shadows from the cart roof, shallow depth of field, and subtle skin texture. The visual demonstrates high-end realism and depth.

[00:14-00:18] Break into bold minimalist title-card sections on white and blue backgrounds. Introduce the educational thesis: AI image tools will not do the work for you unless you specify the right visual ingredients. The pacing should feel sharp and contemporary.

[00:18-00:23] Show teaching cards and diagrams naming prompt levers such as ISO, lens, aperture, white balance, time of day, visible pores, light stumble, and natural asymmetry. Present these elements like a design-savvy tutorial rather than a dense software lesson.

[00:23-00:28] Cut to dark UI or dashboard screens where Nano Banana 2 is surfaced as a featured tool among other creative cards. Then show prompt blocks or generation examples in a workspace, implying the creator has documented best-use-case prompts inside a tutorial system.

[00:28-00:34] Return to the golf editorial imagery with side-by-side or repeated frames, emphasizing color grade and image consistency. Use the man and woman near the golf cart as the hero pair while text reinforces that you can also color-grade your images through the prompt itself.

[00:34-00:39] End on the couple beside the white golf cart in a poised editorial pose. Overlay the final CTA that viewers can comment AI to get the Nano Banana 2 prompts or tutorial. The mood is aspirational, precise, and instructional.

NEGATIVE PROMPT: avoid generic stock golf photography, fake studio polish, over-smoothed skin, or fashion-campaign stiffness with no natural imperfection; no broken golf-club anatomy, warped cart geometry, inconsistent wardrobe, or unstable faces between shots; keep sunlight and shadows believable, grass texture crisp, and editorial depth subtle; avoid muddy UI screens, unreadable prompt blocks, or random tool names unrelated to Nano Banana 2 and realism prompting; no hyper-saturated greens or plastic-looking color grade.

Core format and topic lock: a vertical educational screen-recording tutorial explaining how to use Freepik Spaces with Kling 3.0 to generate first-frame / last-frame AI videos. The interface has a dark background with modular creation nodes, a text prompt card on the left, and a generated vertical video preview on the right. The featured example is a young woman taking selfie-style videos inside a NASA-style spacecraft cockpit, sometimes with astronauts behind her and sometimes looking out at the moon. A male creator with shoulder-length brown hair, beard, beige cap, and beige shirt appears in a talking-head webcam box at the bottom, gesturing as he explains the workflow.

Shot-by-shot reconstruction

0.0s-12.0s
Open on the Freepik Spaces interface. Show a source image card of a woman in a spacecraft on the left and a video output preview on the right labeled as a video generator. The presenter appears in a webcam frame at the bottom, speaking and pointing upward toward the workflow.

12.0s-28.0s
Cycle through several generated outputs: the woman filming herself in the cockpit, astronauts seated behind her, and a variant where she reacts while looking at the moon outside the spacecraft window. The prompt text card remains visible on the left, explaining image guidance and desired scene motion.

28.0s-45.0s
Demonstrate additional variations and show how the creation node, prompt module, and video module connect inside the workflow. Keep the presenter in frame using hand gestures to emphasize key steps while the interface remains the visual focus.

45.0s-60.9s
Zoom attention to the text prompt card and then to a Kling 3.0 first-frame / last-frame setup. Show a loading generation preview and finish on a polished result with astronauts behind the woman in the cockpit. Add a final on-screen CTA inviting the viewer to comment “AI” for the workflow.

Visual style
Clean dark-mode screen tutorial, creator-education vertical social video, crisp UI text boxes, visible node-based workflow, talking-head overlay, modern AI-tool walkthrough, no cinematic camera movement beyond interface navigation and screen emphasis.

Motion notes
Motion should come from interface changes, preview swaps, cursor or focus changes, and the presenter’s webcam gestures. Preserve the same overall UI structure, same creator webcam position, and same spacecraft example theme throughout the tutorial.

Negative prompt
messy desktop, unrelated tabs, low-resolution UI, unreadable text blocks, extra webcam windows, text overlays unrelated to tutorial, watermark, subtitles outside the app content, random scene changes, gaming interface, non-space example footage, glitchy node layout

Speech pack
Presenter-led tutorial voiceover in English. Tone should be practical and instructional. Optional supporting audio: light UI clicks and subtle background room tone.

GLOBAL LOCK: cinematic slow-motion action sequence inside a collapsing industrial or architectural void; lone dark-clad male figure tumbling, diving, and falling through clouds of debris, broken concrete, twisted metal, circular structural elements, and shattered columns; blue-gray disaster palette; dramatic volumetric lighting; intense high-budget blockbuster energy; camera follows the body through chaotic destruction; no text overlays, no logos, no tutorial UI, no extra characters, no color drift.

00:00-00:04
The sequence opens mid-collapse with a single male figure thrown through a wrecked environment of broken columns, metal fragments, and floating rubble. Camera tracks him from oblique angles as he twists through the air in slow motion.

00:04-00:08
The body rotates through tighter pockets of debris and circular industrial forms, narrowly passing concrete chunks and bent structural pieces. Dust, motion blur, and flying fragments heighten the sense of danger and scale.

00:08-00:12
The environment opens into a wider debris field where shattered architecture explodes outward in all directions. The figure continues dropping through the center of the destruction, framed against cold bluish light and swirling particulate matter.

00:12-00:15
The shot resolves into a distant overhead view with the lone figure suspended amid a vortex of rubble and fractured beams, emphasizing vertical fall, chaos, and cinematic spectacle.

NEGATIVE PROMPT:
comedic tone, bright warm colors, stable ground, casual walking, clean room interior, multiple heroes, readable text, UI panels, fantasy creatures, low-detail debris, cartoon rendering, soft romantic lighting, static pose, low-energy motion

A short-form promotional tutorial video for Seedance 2.0 prompt ideas, built around a cinematic rainy-day visual example. The main scene shows a child in a bright yellow raincoat and glossy red rain boots standing and moving through puddles on a wet city street, with shallow depth of field, muted overcast light, reflective pavement, and dramatic water splashes. The camera alternates between close-up shots of the boots in the water, mid shots of the child in the street, and a few tighter face and gesture moments, while large on-screen text reads “SEEDANCE 2.0 PROMPTS (PART-5).” The overall look should feel like a high-impact AI prompt showcase for weather-themed cinematic video generation, emphasizing color contrast, believable rain atmosphere, and tactile puddle-splash motion.