Fun Prompt! I tweaked a few things, and added different stunts to make it unique to me. I just love the look of anguish after he falls. All credit to @techhalla for the original prompt.
Here’s my tweaked prompt below 👇
Authentic 1980s Japanese television game show broadcast footage, realistic recreation of vintage Japanese obstacle-course variety show ENG camera footage, natural handheld camera with subtle shake and imperfect tracking, broadcast video noise, analog grain, limited dynamic range, muted era-accurate color saturation, slight color bleeding on highlights, chaotic crowd energy, comedic danger mixed with mythic ninja adventure.
0-3s: [Wide handheld tracking shot from the side] A determined young Japanese ninja in his mid-20s, athletic build, wearing a soaked-looking matte black shinobi outfit, wrapped forearms, tabi boots, and a dark headband, bursts from a wooden starting gate into a muddy temple-themed obstacle course. Ahead of him, a sacred golden amulet hangs from a red shrine arch on the far platform. He sprints across a row of uneven floating stepping stones shaped like old roof tiles, each one wobbling separately under his weight. The camera tracks beside him with rough ENG movement as muddy water splashes between the stones.
3-6s: [Dynamic medium tracking shot moving alongside] The ninja jumps onto a narrow rotating bamboo bridge suspended just above the pond. As he lands, the bamboo cylinder rolls beneath his feet, forcing him into a frantic sideways shuffle. He lowers his center of gravity like a trained shinobi, arms extended for balance, but the slick bamboo twists faster than expected. His focused expression cracks into panic as the bridge rolls him toward the edge.
6-9s: [Closer three-quarter action shot with motion blur] He barely escapes the bamboo bridge by diving forward onto a swinging rope net hanging between two wooden posts. The net sags and swings wildly over the murky water. He crawls across on elbows and knees while the whole net sways side to side, his black sleeves dragging through puddles caught in the rope. The sacred amulet glows faintly in the background, just beyond reach, while the handheld camera struggles to keep him centered.
9-12s: [Dynamic frontal tracking shot from the far platform] The ninja drops from the rope net onto a final set of tilting red shrine planks. Each plank flips downward when he steps on it, forcing him to hop quickly from one to the next. He stretches one hand toward the golden amulet hanging from the shrine arch, fingers nearly brushing it. At the last second, the final plank collapses under his foot, throwing his body off balance as his arms windmill dramatically.
12-15s: [Impact focused shot with water dynamics] The ninja misses the amulet by inches and tumbles sideways into the pond with a huge muddy splash, disappearing beneath the water. He resurfaces gasping, headband crooked, black outfit clinging to him, one hand still reaching uselessly toward the untouched amulet. The red shrine arch and glowing charm remain in the background as the crowd reacts with chaotic game-show laughter and applause. His expression is heroic failure turned deadpan humiliation.
High fidelity recreation of 1980s analog Japanese broadcast video, visible natural grain and broadcast noise, realistic motion characteristics of old ENG cameras, coherent but slightly imperfect physical movement, era-accurate color response and limited dynamic range, stable character identity with natural analog imperfections, no modern digital sharpness, no clean cinematic polish, no fantasy CGI overload, no modern action-movie grading, no digital artifacts.
#aivideo #seedance
Seedance 2.0 Takeshi's Castle (Roller Game version) prompt 🎎
Authentic 1980s Japanese television game show broadcast footage, realistic recreation of original Takeshi's Castle ENG camera footage, natural handheld camera with subtle shake and tracking, broadcast video noise, analog grain, limited dynamic range and color saturation of the era, slight color bleeding on highlights, chaotic energetic atmosphere of the original show.
No reference images provided. Generate the entire scene from the text description.
0-3s: [Wide handheld tracking shot from the side] A determined young Japanese male contestant in his mid-20s, short black hair, wearing a bright orange tracksuit with white stripes, white sneakers and a white headband, sprints confidently from the wooden starting platform onto the first of several large spinning cylindrical logs floating over a murky pond. He runs with pumping arms and focused expression as the log begins to rotate slowly beneath his feet, causing his body to wobble slightly. Water ripples and splashes lightly around the base of the logs.
3-6s: [Dynamic medium tracking shot moving alongside] He leaps to the second spinning log at a slightly higher level, landing with bent knees to absorb the impact. The faster-rotating drum spins his feet out from under him; he flails his arms dramatically to regain balance, torso leaning left then right, face shifting from concentration to surprise. The log's wet surface glistens as he struggles to stay upright.
6-9s: [Closer side profile action shot with motion blur] Pushing forward to the third log, his right foot slips on the spinning wet wood. He lurches forward violently, arms windmilling, body twisting as he tries to recover by crouching low. His left leg dips into the water creating a splash, but he pulls it out and continues with desperate momentum, the rotating cylinder throwing off his rhythm.
9-12s: [Dynamic tracking shot from a three-quarter angle] He attempts a running jump to the next log but the combined spin and his forward speed causes him to lose all balance. His body tilts backward sharply, legs kicking in the air, arms reaching out for nothing as he begins to fall off the side of the log.
12-15s: [Impact focused shot with water dynamics] The contestant falls backward off the spinning log into the pond with a huge explosive splash, water shooting up around his body. He submerges briefly, then resurfaces gasping and flailing, completely soaked, as the logs continue their relentless spinning in the background. His expression is one of shocked defeat mixed with the show's signature comedic failure.
High fidelity recreation of 1980s analog broadcast video, visible natural grain and broadcast noise, realistic motion characteristics of old ENG cameras, coherent but slightly imperfect physics and movement as seen in original Takeshi's Castle episodes, era-accurate color response and limited dynamic range, stable character with the natural imperfections of analog footage, no modern digital sharpness or artifacts.
Agreed! The amount of things I’ve learned from creating with AI have be amazing. Things from lighting references to camera angles to editing techniques. It’s so much more to it than typing a few words and pressing a button.
☁️ Red Skies & Luxury 💎
Model: Midjourney
Pastel purgatory: A waiting terminal full of teal seats, koi drifting through a flooded white hallway, arcade cabinets drowning politely in fog, a movie theater where the screen has been replaced by a cloud formation.
It takes places we half-remember, malls, airports, arcades, pools, theaters, then removes the people, buffs the surfaces, floods the floor, and locks the sky at permanent synthetic sunset.
#aiart #midjourney
Neon Speed: Midnight Edition 🏁
Models: GPT Image-2 + Seedance 2.0
I believe is my first attempt at a POV race scene. The consistency of Seedance from shot to shot is impressive. There’s no way I could pull this off with Midjourney. As soon as an object leaves the shot it comes back in nearly unrecognizable if at all
#aiart #seedance
Prompt Battle ⚔️
4 Models 1 Prompt
The Models Grom To Left to Bottom Right: Midjourney, Meta, GPT Image-2, Nano Banana
The Prompt: Mysterious hooded figure, chest-up portrait, wrapped in layered charcoal-black draped fabric, faceless head replaced by a glowing cosmic void filled with planets, stars, nebula light, radiant orbs in yellow, red, blue, and orange, painterly textured robe with subtle colorful specks, central composition, surreal mystical presence, dreamy cosmic background with swirling nebula clouds, celestial haze, faint galaxies, glowing mist, soft stardust, ethereal atmosphere, luminous ambient glow, fine-art painting, rich texture, moody and magical, high contrast between dark robes and radiant face.
My Winner: GPT Image-2
What it gets right:
* Mysterious hooded figure: immediately readable, strong silhouette, properly ominous without tipping into costume-shop melodrama.
* Chest-up portrait: cleanly framed and centered.
* Layered charcoal-black draped fabric: the robe has real depth and convincing folds, plus that painterly texture you asked for.
* Faceless head replaced by a glowing cosmic void: this is the big one, and Image 3 absolutely delivers. The face area feels like an actual portal or contained universe, not just a decorative galaxy sticker.
* Planets, stars, nebula light, radiant orbs: present and integrated well.
* Dreamy cosmic background: swirling clouds, celestial haze, faint galaxies, luminous mist, all there.
* High contrast between dark robes and radiant face: probably the strongest contrast of the set, which gives it the most visual impact.
Why the others don’t quite take it
Midjourney
Very strong runner-up. The background is gorgeous, and the robe texture is excellent. But the “face” reads more like abstract glowing dots than a fully realized cosmic void with planets and structure. Beautiful, just a little less precise.
Meta
This one is elegant and restrained, almost monastic. The problem is that it undershoots the prompt’s more luminous, magical, nebula-heavy qualities. It has the concept, but not enough spectacle.
Nano Banana
Probably the softest and dreamiest of the bunch. Nice atmosphere, but it feels less moody and less high-contrast than the prompt asks for. The face is also more galaxy-swirl than “cosmic void filled with planets, stars, nebula light, radiant orb
#AIart️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️
Isometric Worlds 🌍
Models: GPT-Image 2 + Seedance 2.0
Candy towns with licorice dragons, underwater train stations with functioning public transit (the real fantasy), forest schools run by woodland creatures, and a robot workshop packed into a suitcase like someone gave a toybox a civic planning degree.
The whole thing is basically a “Where’s Waldo?” book raised on mobile games, hidden-object puzzles, and one very sincere belief: the background characters deserve lives too. No grand plot. No boss fight. Just four tiny ecosystems
#aiart #seedance