ππ Reliving the 90s nostalgia with classic Kung Fu Theatre Γ Wu-Tang Clan.
Kung Fu Theatre and Wu-Tang Clan were two worlds we were lucky enough to experience growing up. They shaped how we think about storytelling, sound, visual culture, and creative identity. Wu-Tang sampled those same kung fu classics to build the foundation of one of the most iconic sounds in hip-hop. For us, those worlds were never separate. They were the same thing.
So we remixed it.
if you grew up on this, you already feel it. π
#WuTang #KungFuTheater #AIVideo #90sNostalgia #Kling3 #Seedance2 #aivideo #aifilmmaking
I always go to Midjourney to build my characters and worlds, evolve them from there and you will have great shots, here are couple examples. I will expand them into nano banana and Photohop to dial them in always.
THE COCK
cinematic film still - three-quarter front view of a large rooster standing tall at the center of a cracked favela street, head turned slightly toward camera, bright red comb and wattle vivid against overcast sky, alert dark eye catching light, rich copper and burnt orange hackle feathers flowing down the neck, deep iridescent navy and teal tail feathers fanning wide and high, dark body plumage with metallic blue-green sheen, scaly grey legs planted on wet dirt beside a small muddy puddle - south american locals on both sides of the street, left side an older woman in a floral house dress leaning in a doorway arms crossed, two young boys sitting on the curb in tank tops and shorts, a man in a faded blue t-shirt standing with hands in pockets watching the bird - right side a teenage girl braiding another girl's hair on a plastic chair, an old man in a straw hat sitting on an overturned crate, a shirtless man leaning against a parked sedan smoking - narrow favela street receding into the background, exposed red brick apartment buildings on both sides, raw cinder block walls, pink and ochre painted facades with peeling plaster, parked older sedans further down the road, tangled electrical wires and power poles, crumbling concrete curb in foreground - Canon 35mm f1.4, low angle from ground level looking slightly up at the rooster making it monumental, shallow DOF with rooster tack sharp, people slightly soft, favela street falling off soft behind - diffused overcast daylight with muted warm tones, soft even illumination with no harsh shadows, faint warm reflected light bouncing off brick walls - individual feather barbs visible, mud splatter on lower legs, grit and small rocks in wet dirt, crumbling concrete curb texture, plastic chair legs scratched, cigarette smoke curling - slight handheld grain, WB neutral with faint warm shift, visible ISO noise in shadow areas
THE ASS
cinematic film still - straight-on frontal shot, flat perspective, eye-level - old south american farmer standing still on the cracked sidewalk at the edge of a dusty favela road, looking directly into the camera with a calm weathered expression, deep wrinkles around eyes, white stubble on jaw, squinting slightly - wearing a faded straw hat with frayed brim, worn light cotton button-up shirt with sweat stains at collar, loose dirt-brown trousers rolled at the ankles, old leather sandals - holding a frayed rope lead attached to a small grey donkey standing beside him also facing the camera head-on, ears forward, dark eyes looking into lens, dusty coat, ribs faintly visible, woven saddlebag draped across its back - a dirt bike rider in black hoodie and black mask blurring past on the road between the camera and the farmer, motion-blurred streak of bike and rider crossing the frame laterally, dust trail hanging behind the bike - wide open favela hillside filling the entire background behind the farmer, dense stacked exposed brick and concrete apartments climbing the hill, raw cinder block walls, corrugated tin rooftops, scattered blue and ochre painted facades, water tanks on roofs, tangled electrical wires, sparse trees - golden hour sunlight raking across the scene from camera left, warm dust haze catching the light, long shadows on the ground, soft atmospheric glow across the favela skyline - Canon 50mm f1.4, straight-on flat perspective perpendicular to subject, shallow DOF with farmer and donkey sharp, hillside softened behind, dirt bike heavily motion-blurred in midground - visible pores, sun damage on hands, cracked fingernails, dry lips, rope fibers fraying, donkey's coarse hair texture, dust particles suspended in golden backlight - slight handheld grain, WB skewed warm golden, visible ISO noise in shadow areas
Pursuit
Very cool to see how seedance 2 translates prompts, images and video references. This is an edit of the final result.
Prompts and character sheets hared below in the comments π
[@image_1] as the first frame. An old man in a straw hat stands still on a dirt road in a favela holding a donkey by a rope. Warm golden afternoon light, dust haze, brick buildings stacked on the hillside behind him. Camera holds steady on the man at medium shot. Avoid static shots. Generate only sound effects, no music. Generate video without subtitles.
0-2s: The man and donkey stand calmly on the dirt road, a faint engine sound grows louder from the right side.
2-4s: A rider in a black hoodie [@image2] on a dark blue dirt bike speeds past from right to left in front of the man, kicking up a cloud of dust behind him, the man's head turns left following the bike, the donkey flinches and steps sideways.
4-5s: The man stares left at the settling dust cloud, his expression stunned, the donkey brays and pulls the rope, dust drifts slowly through the warm light. Maintain face and clothing consistency, no distortion. Natural and smooth movements.
[@image1] as the first frame. A large rooster with dark iridescent feathers and a bright red comb stands on a concrete curb on a muddy favela street. Warm golden hour light from behind casting long shadows, puddles reflecting the sky, pink and green concrete buildings on both sides. Smooth slow dolly-in from medium shot to close-up over 5 seconds. Avoid static shots. Generate only sound effects, no music. Generate video without subtitles.
0-2s: The rooster stands tall and alert, feathers catching golden backlight with blue and copper shimmer, head facing right down the street. 2-3s: The rooster turns its head sharply toward the camera and stares directly into the lens for one second, one eye locked on camera.
3-4s: The rooster's head snaps back to the right, its body tenses, feathers puff up.
4-5s: The rooster panics and leaps into the air flapping its wings wildly, feathers scattering, it scrambles off the curb out of frame to the left. Maintain consistency, no distortion. Natural and smooth movements.
When you extend a video based on the platform. There is a common Seedance extension issue. When you say "extend," it's reading the final frames of your clip and interpreting the motion vectors. If the previous ended mid-air or mid-jump, the model wants to continue that trajectory.
You need to pick a cleaner bridge frame. Don't extend from a clip that ends mid-stunt or in a dust cloud. Scrub to a frame where the rider is clearly moving forward on flat ground with the road visible ahead.
Extend [@video_1] by 5 seconds.
VISUAL STYLE: Kodak Vision3 500T 35mm film stock, 50mm lens, f/2.8, visible grain, atmospheric dust, teal and orange grade, shadows cyan-teal, highlights amber-gold, saturation 115%, golden sun ahead
CHARACTER: Dirt bike rider in black hoodie racing forward, matte-black SUV chasing directly behind him
STAGE: Narrow dusty favela street, concrete buildings on both sides, parked cars lining curbs, power lines overhead, golden dust haze
CAMERA: Wide side-tracking shot from the right sidewalk, non-fixed, both vehicles moving left to right through frame
SFX: Generate only sound effects, no music. Generate video without subtitles.
STRUCTURE: Nonstop forward chase, no pauses, constant acceleration
INTERACTION RULE: Both vehicles always moving in the same direction left to right through frame, SUV destroying everything the bike slips past
SEQUENCE:
0-1.5s: Wide side-tracking shot from the right sidewalk, the dirt bike races left to right through frame at high speed followed closely by the matte-black SUV with chrome bull bar three car-lengths behind, both vehicles moving in the same direction, dust behind the SUV, bystanders pressing against walls.
1.5-3s: The bike weaves between parked cars, the SUV continues on the road without slowing.
3-4s: Camera shifts to tracking shot behind both vehicles at ground level, the SUV filling most of the frame with the bike visible just ahead of it, the rear passenger window is down and a gloved hand extends gripping a black pistol, the rider on the bike continues to accelerate faster.
4-5s: Multiple muzzle flashes erupt from the SUV window at the rider, the rider swerves right then accelerates hard pulling away slightly, the SUV accelerates to match.
FINAL SHOT: Both vehicles racing forward down the narrow street.
4K, Ultra HD, Rich details, Sharp clarity, Cinematic texture, Natural colors, No blur, No ghosting, No flickering, Stable picture. Maintain face and clothing consistency, no distortion, high detail. Character face stable without deformation, normal human structure, natural and smooth movements.
I experimented with the prompts and found out it depends on the platform you're using.
Shot 1
[@image_1 ]as the first frame. Two riders in black hoodies on dirt bikes popping wheelies side by side racing toward the camera on a narrow dusty favela street, bystanders lining both sides watching, children sitting on the curb. Scene references [@image_1]'s environment of pink concrete buildings, tangled power lines, golden afternoon haze. Kodak Vision3 500T 35mm, 35mm lens, f/2.8, camera non-fixed. Teal and orange grade, shadows cyan-teal, highlights amber-gold, visible grain, atmospheric dust in backlight. Generate only sound effects, no music. Generate video without subtitles.
0-1.5s: Both bikes race toward camera on rear wheels, front tires high, dust billowing behind them in golden backlight, engine scream growing louder, bystanders flinch.
1.5-3s: Camera orbits 180 degrees counterclockwise around both riders over 1.5 seconds at constant 6-foot distance swinging from front-facing to rear-follow position, wheels slam down to pavement as the orbit completes, rubber bark on impact.
3-5s: Camera now locked behind at tire level chasing both bikes as they split apart around a parked silver sedan, lead rider frame-left, second rider frame-right, gap closes immediately after the car, dust trail fills the corridor between buildings, engine roar reverberates off concrete walls. 4K, Ultra HD, Rich details, Sharp clarity, Cinematic texture, Natural colors, No blur, No ghosting, No flickering, Stable picture. Maintain face and clothing consistency, no distortion, high detail. Natural and smooth movements.
Character Sheet Prompt for Nano Banana Proβ¨β¨
SUBJECT = Uploaded reference imageβ¨OUTFIT = Describe outfitβ¨STYLE_TYPE = photorealistic studio photography.β¨β¨
DO:β¨
Create a clean, highly structured character sheet for SUBJECT. Render the entire sheet strictly in STYLE_TYPE. Preserve the exact same face, proportions, body structure, colors, and materials across all panels. Arrange a wide 21:9 cinematic layout with evenly spaced grid panels and no overlap. Use a soft neutral studio background with even lighting and minimal shadows. Keep the presentation sharp, readable, and professionally organized. Show a full-body neutral standing pose from the front. Place the label "FRONT VIEW" centered below. Show a full-body neutral standing pose from the back with accurate rear outfit details. Place the label "BACK VIEW" centered below. Show a full-body strict side profile with clean silhouette readability. Place the label "SIDE PROFILE" centered below. Show a dynamic action pose that reflects SUBJECTβs personality. Maintain identity, proportions, and outfit consistency. Place the label "ACTION POSE" centered below. Show a horizontal row of close-up headshots. Include expressions: neutral, angry, happy, sad, focused. Preserve exact facial identity across all expressions. Place the label "FACIAL EXPRESSIONS" centered below. Show isolated accessories clearly. Include weapons, jewelry, tools, or props belonging to SUBJECT. Maintain material and design consistency. Place the label "ACCESSORIES" centered below.β¨β¨STYLE: follows STYLE_TYPE, ultra-detailed, professional character sheet, sharp focus, clean presentationβ¨CAMERA: orthographic feel, full-body framing, close-up for expressionsβ¨MOOD: precise, organized, premiumβ¨β¨RULES:β¨ Same character identity across all panels with no redesign.β¨ Facial features and proportions must remain identical.β¨ STYLE_TYPE must be applied consistently across all panels.β¨ Lighting and color tone must be consistent across the sheet.β¨ Labels must appear only below each panel and be centered.β¨ Layout must be clean, evenly spaced, and easy to read.β¨β¨NO: extra text, background clutter, overlapping panels, inconsistent anatomy, inconsistent face, mixed styles, motion blur, dramatic shadows
Seedance 2.0 Prompt Share
Started testing prompt structures and this one was got some great results, mixing subjects and styles will get you some great great results.
Prompt below, thanks to @aimikoda for sharing insights!
FORMAT: 15s / 145 BPM / 15 SHOTS / beat-synced routine
SUBJECT: [@image1]
WARDROBE: Sleep tee and lounge shorts at home. Tailored jacket, fitted top, trousers, and lace-up shoes outside.
ENVIRONMENT: Tiny apartment, bright fridge glow, rain-dusted hallway, chrome metro, clean office, then a bedroom in cool window light. Everything feels glossy and lived-in.
MOOD: Late-for-work panic, clipped momentum, breathless urgency, then an exhausted exhale.
MUSIC: no music
COLOR LOGIC: Hyperreal Pop Look
STYLE: Hand-drawn cel animation aesthetic. Hard-edged 2-tone cel shading with distinct light and shadow boundaries, no gradient blending. Thick black ink outlines on all subjects. Saturated primary color palette (cyan, magenta, cadmium yellow).
LOGIC RULE: Keep logical consistency in wardrobe, props, locations, and action continuity across all shots.
SHOT 1: ECU, 85mm push-in / 06:50 on the phone screen as it shakes on rumpled sheets. / SFX: alarm, sheet rustle.
SHOT 2: WS, 35mm handheld jolt / Rhythmic cut into her jolting upright through side light, throwing the blanket aside, and planting her feet on the floor in one rushed motion, still in a soft sleep tee and lounge shorts. / SFX: mattress bounce, blanket whip, sharp breath.
SHOT 3: MCU, 50mm slide / Cut on action into face wash at the sink, droplets catching the top light. / SFX: faucet rush, water slap.
SHOT 4: Insert shot, 85mm rack focus / Match cut into the toothbrush held at a natural forward brushing angle against the front teeth, hand relaxed and upright, mint foam and mirror eye. / SFX: bristle scrape, sink drip.
SHOT 5: Interior fridge view, 24mm wide / Object pass into the camera inside the fridge looking out as the door snaps open and her hand darts in, blue fridge light framing a hurried grab for breakfast ingredients. / SFX: fridge hum, bottle clink, shelf rattle.
SHOT 6: Insert shot, 50mm handheld / Rhythmic cut into eggs and toast hitting the pan under warm practical light. / SFX: butter sizzle, chop tap.
SHOT 7: MCU, centered 50mm push-in / Match cut into one rushed bite, a quick clock glance, and an immediate rise from the chair. / SFX: crunch, ceramic clink, chair scrape.
SHOT 8: Bird's-eye insert, 35mm overhead / Cut on action into striped socks snapping on. / SFX: fabric stretch, heel tap.
SHOT 9: MS, 35mm pivot / Camera wipe into a rushed outfit change as the sleep tee disappears under a fitted top and tailored jacket, then her tote, keys, and transit card get scooped up in one messy grab. / SFX: fabric whip, key jingle, zipper pull, bag rustle.
SHOT 10: Insert shot, 50mm overhead / Match cut into lace-up shoes slamming on as the laces yank tight in one impatient pull. / SFX: sole thump, lace tug, short breath.
SHOT 11: WS, 24mm parallax / Whip pan transition into her, now in the tailored outside outfit, rushing through the apartment door into corridor light without breaking stride. / SFX: latch click, rapid footsteps, hallway air.
SHOT 12: MS to CU, 35mm glide into 85mm push-in / Sound bridge into the metro car interior only as she grips the pole, shifts with the carriage sway, checks the passing station lights, and snaps a tense glance toward the closing doors, reflected chrome streaking around her and the city smearing outside the window. / SFX: rail clatter, carriage screech, door warning chime, tight breath.
SHOT 13: Insert to MCU, 50mm snap zoom / Smash cut to the office entrance as her access card hits the reader, the glass door unlocks, and she slips through fast before the chair roll and laptop open. / SFX: badge beep, door click, laptop chime.
SHOT 14: OTS, 35mm handheld / Rhythmic cut into fingers racing across keys, chat windows blinking, coffee by the trackpad, and notifications stacking faster than she clears them. / SFX: keyboard burst, notification ticks, mouse click.
SHOT 15: WS, 50mm pull-out / L-cut with a match from laptop close to apartment re-entry as the jacket drops, work clothes peel away, and she changes back into sleepwear before collapsing into bed in the opening frame shape. / SFX: door shut, bag drop, fabric rustle, blanket rustle, room tone.
@PJaccetturo Agree, I still love doing all the concept art in Midjourney and expanding it from there, so many talented people in the space creating amazing worlds and characters.
BURN
Seedance 2.0 changed the game for me. The motion feels cinematic, characters stay consistent from shot to shot, and the tool actually understands how a scene should breathe. This is the first time I've been able to direct AI video the way I'd direct a real shoot.
#Seedance2 #AIFilmmaking #AIVideoGeneration #CreativeAI
90s Throwback, Lived it first hand, Taco Bell, Wu-Tang, Robocop, Kung Fu Theatre and multiple other tapes that we have forgotten. If this doesn't hit you in the chest, you didn't live it.
Made with AI. Every detail engineered by design not trends.
AI was the only way I could do this but I HAVE CONTROL. This is the beginning...
#AIVideo #PromptEngineering #90sNostalgia #90smusic
Every deck tells a story. The best one is Bicycle.
Made this cinematic spec commercial for @bicyclecards using AI.
Took the face cards everyone knows and let them loose. Six characters, each with their own voice and energy, breaking out of the card and commanding the screen.
π¬ @Kling_ai 3.0 / πΈ @higgsfield@HFcollaborators / π @elevenlabs / π΅ @sunomusic / βοΈ @AdobeVideo
The vision is human. The tools are AI.
#AIVideo #BicycleCards #KlingAI #AIFilmmaking #SpecAd #CreativeAI #GenerativeAI