城市翼装飞行🫧✨
-
[STYLE + CAMERA + ATMOSPHERE]
Raw handheld 35mm film aesthetic with natural film grain. Harsh direct sunlight creating strong high-contrast shadows across the NYC skyline.
One continuous single-take handheld tracking shot, primarily third-person and over-the-shoulder, no visible cuts.
Strong rooftop wind, realistic high-altitude atmosphere, intense air resistance and believable fabric physics.
Audio: rhythmic breathing, rooftop wind, sudden fabric snap during deployment, powerful high-speed air rush between buildings, near-miss whooshes, landing impact, NYC street ambience, final bite sound.
[CHARACTER REFERENCE]
Use the provided reference image as the strict visual reference for the female character.
Preserve her exact facial identity, hairstyle, hair color, skin tone, body proportions and overall appearance throughout the entire sequence.
She wears a fitted black technical jacket, dark cargo pants, lightweight sneakers and a compact black backpack at the beginning.
Her face, hairstyle and body proportions remain visually consistent throughout the entire video.
[TIMELINE]
0–3s
Handheld medium shot.
The young woman stands calmly at the edge of a Manhattan skyscraper rooftop.
Strong wind blows through her hair and clothing.
She looks directly into the camera with a calm, confident expression.
After a brief pause, she turns toward the skyline, takes two quick steps and launches from the rooftop.
She performs one clean controlled forward rotation as she enters freefall.
3–6s
The camera follows continuously behind her.
She finishes the rotation and drops rapidly toward the city.
Her backpack system deploys into a compact aerodynamic gliding suit.
Fabric unfolds sharply in the wind and becomes fully tensioned.
Her body smoothly transitions from vertical freefall into fast forward flight.
6–13s
Camera stays close behind her.
She accelerates through the Manhattan skyline.
She banks left around one glass tower.
Immediately rolls gently right between two buildings.
Windows, reflections and architectural details rush past.
Her hair, clothing and equipment react naturally to the extreme airflow.
The camera shakes subtly from turbulence while maintaining a readable view of her body.
13–20s
She gradually descends toward street level.
A yellow taxi crosses ahead.
She banks smoothly above it with only a few meters of clearance.
She continues downward through a wide avenue.
A city bus appears ahead.
She shifts sideways and passes beside it at high speed.
Traffic lights, pedestrians and storefronts rush past while maintaining believable scale and spatial relationships.
20–25s
She approaches a relatively clear sidewalk area.
She rapidly reduces speed.
Her body rises slightly as the gliding surface catches more air.
She touches down running.
Three quick steps.
Then one controlled forward roll.
She comes smoothly to a stop.
The camera follows the entire landing without cutting.
25–28s
She stands up.
Slightly out of breath.
She quickly releases the gliding equipment and leaves it beside her.
She walks toward a nearby street food cart.
The vendor casually hands her a freshly prepared hot dog.
28–30s
The camera finally moves around toward her face.
Her hair is messy from the flight.
She looks directly into the lens.
Pauses.
Takes a large bite of the hot dog.
A tiny satisfied smile appears.
The chaotic NYC street continues naturally behind her.
Hold on her expression.
[VISUAL CONSISTENCY]
Highly realistic photography.
Natural 35mm film texture.
Strong daylight and realistic urban reflections.
Consistent facial identity throughout.
Realistic body anatomy.
Natural hair and fabric physics.
Believable gravity, momentum, acceleration and deceleration.
Continuous spatial geography between rooftop, flight path and street.
Natural camera shake caused by wind and speed.
Motion blur only where physically appropriate.
Seedance 2.5 vlog case.
This is so real.
---prompt---
A realistic handheld travel vlog filmed by a friend following the main character throughout the day. Use the woman from the reference image as the main subject. Maintain her exact facial identity, hairstyle, facial features, and body proportions throughout the entire video. The camera feels like a real personal vlog camera, not a commercial production. Natural handheld movement, casual framing, imperfect human camera motion, authentic everyday atmosphere. No scripted acting. The woman behaves naturally, interacting with the environment like a real travel vlog. 0-5s: Morning departure. The woman leaves a cozy apartment with a small backpack. She checks her phone, smiles at the camera, adjusts her hair, and starts walking outside. The camera follows her from behind, slightly shaky like a friend filming. Morning sunlight, quiet neighborhood streets, people starting their day. 5-12s: Exploring the city. The camera follows her walking through local streets. She visits a small cafe, buys a drink, briefly talks to the camera, laughs naturally. She walks through a street market, looks at small shops, takes casual photos. The camera stays close, capturing spontaneous moments. 12-20s: Arriving at the beach. She takes public transportation or walks toward the coast. The environment gradually changes from city streets to a seaside town. Ocean breeze moves her hair. She looks excited when she sees the ocean. The camera follows her walking along the beach. She picks up a seashell, watches waves, and interacts naturally with people nearby. 20-27s: Summer beach afternoon. She meets friends at the beach. Everyone chats, laughs, plays near the water. The camera moves naturally between people, capturing real candid moments. She looks back at the camera and smiles. 27-30s: Ending moment. Golden hour sunset. She sits near the ocean, holding a drink, watching the sunset. The camera slowly moves backward, revealing the beach, waves, and the peaceful evening. A feeling of a real personal travel memory. Visual style: Authentic travel vlog footage. Realistic smartphone or mirrorless camera look. Natural daylight. Casual handheld movement. Slight camera shake. Real human reactions. Documentary realism. No cinematic commercial look. No dramatic posing. No artificial transitions. No text overlays. No logos. No face changes. No identity changes.
Un japonés descubrió antes que nadie cómo aprovechar realmente el potencial de Claude Code.
Instala “Find Skills”, explica lo que quiere lograr y el sistema le sugiere automáticamente las mejores habilidades entre cientos de opciones.
Gracias a eso, su sistema automatizado de YouTube está teniendo un gran éxito.
Ingeniera de Anthropic:
En Anthropic, ya no escribimos prompts. Construimos bucles.
En 45 minutos, ella muestra cómo el equipo de Claude construye bucles que se auto-promptean
Guarda este post antes de que lo pierdes. Es gratis.
To celebrate a week of efficiency and let you run 100'000 Luna threads this weekend... that's right... wait for it... I have reset usage limits for Codex and ChatGPT Work.
Enjoy.
We kept ourselves busy with GPT-5.6 Sol. It's pretty good at things.
Rolling out
- 80% lower prices on Luna
- 20% lower prices on Terra
- faster speeds on GPT-5.6 Sol in /fast mode
- ~ 10X cheaper auto-approve mode ("review for me" in the app), which now uses Luna to prevent many high risk actions from the main agent
Towards intelligence too cheap to meter and many more breakthroughs ahead.