Tutti i video presenti in questa pagina sono stati generati direttamente da Sora senza modifiche.
Stiamo insegnando all’IA a comprendere e simulare il mondo fisico in movimento, con l’obiettivo di addestrare modelli che aiutino le persone a risolvere problemi che richiedono un’interazione con il mondo reale.
Ti presentiamo Sora, il nostro modello di creazione di video da testo. Sora può generare video fino a un minuto di durata, mantenendo la qualità visiva e la coerenza con il prompt fornito dall’utente.
Prompt: A stylish woman walks down a Tokyo street filled with warm glowing neon and animated city signage. She wears a black leather jacket, a long red dress, and black boots, and carries a black purse. She wears sunglasses and red lipstick. She walks confidently and casually. The street is damp and reflective, creating a mirror effect of the colorful lights. Many pedestrians walk about.
Prompt: Several giant wooly mammoths approach treading through a snowy meadow, their long wooly fur lightly blows in the wind as they walk, snow covered trees and dramatic snow capped mountains in the distance, mid afternoon light with wispy clouds and a sun high in the distance creates a warm glow, the low camera view is stunning capturing the large furry mammal with beautiful photography, depth of field.
Prompt: A movie trailer featuring the adventures of the 30 year old space man wearing a red wool knitted motorcycle helmet, blue sky, salt desert, cinematic style, shot on 35mm film, vivid colors.
Prompt: Drone view of waves crashing against the rugged cliffs along Big Sur’s garay point beach. The crashing blue waters create white-tipped waves, while the golden light of the setting sun illuminates the rocky shore. A small island with a lighthouse sits in the distance, and green shrubbery covers the cliff’s edge. The steep drop from the road down to the beach is a dramatic feat, with the cliff’s edges jutting out over the sea. This is a view that captures the raw beauty of the coast and the rugged landscape of the Pacific Coast Highway.
Prompt: Animated scene features a close-up of a short fluffy monster kneeling beside a melting red candle. The art style is 3D and realistic, with a focus on lighting and texture. The mood of the painting is one of wonder and curiosity, as the monster gazes at the flame with wide eyes and open mouth. Its pose and expression convey a sense of innocence and playfulness, as if it is exploring the world around it for the first time. The use of warm colors and dramatic lighting further enhances the cozy atmosphere of the image.
Prompt: A gorgeously rendered papercraft world of a coral reef, rife with colorful fish and sea creatures.
Prompt: This close-up shot of a Victoria crowned pigeon showcases its striking blue plumage and red chest. Its crest is made of delicate, lacy feathers, while its eye is a striking red color. The bird’s head is tilted slightly to the side, giving the impression of it looking regal and majestic. The background is blurred, drawing attention to the bird’s striking appearance.
Prompt: Photorealistic closeup video of two pirate ships battling each other as they sail inside a cup of coffee.
Prompt: A young man at his 20s is sitting on a piece of cloud in the sky, reading a book.
Oggi Sora è disponibile per i red teamer per valutare aree critiche alla ricerca di danni o rischi. Stiamo inoltre dando accesso a un numero selezionato di artisti visivi, designer e filmmaker per raccogliere feedback su come migliorare il modello e renderlo il più utile possibile per i professionisti creativi.
Stiamo condividendo in anticipo i progressi della nostra ricerca per iniziare a collaborare e ricevere feedback da persone esterne a OpenAI, oltre a dare al pubblico un’idea delle potenzialità dell’IA che si profilano all’orizzonte.
Prompt: Historical footage of California during the gold rush.
Prompt: A close up view of a glass sphere that has a zen garden within it. There is a small dwarf in the sphere who is raking the zen garden and creating patterns in the sand.
Prompt: Extreme close up of a 24 year old woman’s eye blinking, standing in Marrakech during magic hour, cinematic film shot in 70mm, depth of field, vivid colors, cinematic
Prompt: A cartoon kangaroo disco dances.
Prompt: A beautiful homemade video showing the people of Lagos, Nigeria in the year 2056. Shot with a mobile phone camera.
Prompt: A petri dish with a bamboo forest growing within it that has tiny red pandas running around.
Prompt: The camera rotates around a large stack of vintage televisions all showing different programs — 1950s sci-fi movies, horror movies, news, static, a 1970s sitcom, etc, set inside a large New York museum gallery.
Prompt: 3D animation of a small, round, fluffy creature with big, expressive eyes explores a vibrant, enchanted forest. The creature, a whimsical blend of a rabbit and a squirrel, has soft blue fur and a bushy, striped tail. It hops along a sparkling stream, its eyes wide with wonder. The forest is alive with magical elements: flowers that glow and change colors, trees with leaves in shades of purple and silver, and small floating lights that resemble fireflies. The creature stops to interact playfully with a group of tiny, fairy-like beings dancing around a mushroom ring. The creature looks up in awe at a large, glowing tree that seems to be the heart of the forest.
Sora è in grado di generare scene complesse con più personaggi, tipi di movimento specifici e dettagli accurati del soggetto e dello sfondo. Il modello comprende non solo ciò che l’utente ha richiesto nel prompt, ma anche come questi elementi esistono nel mondo fisico.
Prompt: The camera follows behind a white vintage SUV with a black roof rack as it speeds up a steep dirt road surrounded by pine trees on a steep mountain slope, dust kicks up from it’s tires, the sunlight shines on the SUV as it speeds along the dirt road, casting a warm glow over the scene. The dirt road curves gently into the distance, with no other cars or vehicles in sight. The trees on either side of the road are redwoods, with patches of greenery scattered throughout. The car is seen from the rear following the curve with ease, making it seem as if it is on a rugged drive through the rugged terrain. The dirt road itself is surrounded by steep hills and mountains, with a clear blue sky above with wispy clouds.
Prompt: Reflections in the window of a train traveling through the Tokyo suburbs.
Prompt: A drone camera circles around a beautiful historic church built on a rocky outcropping along the Amalfi Coast, the view showcases historic and magnificent architectural details and tiered pathways and patios, waves are seen crashing against the rocks below as the view overlooks the horizon of the coastal waters and hilly landscapes of the Amalfi Coast Italy, several distant people are seen walking and enjoying vistas on patios of the dramatic ocean views, the warm glow of the afternoon sun creates a magical and romantic feeling to the scene, the view is stunning captured with beautiful photography.
Prompt: A large orange octopus is seen resting on the bottom of the ocean floor, blending in with the sandy and rocky terrain. Its tentacles are spread out around its body, and its eyes are closed. The octopus is unaware of a king crab that is crawling towards it from behind a rock, its claws raised and ready to attack. The crab is brown and spiny, with long legs and antennae. The scene is captured from a wide angle, showing the vastness and depth of the ocean. The water is clear and blue, with rays of sunlight filtering through. The shot is sharp and crisp, with a high dynamic range. The octopus and the crab are in focus, while the background is slightly blurred, creating a depth of field effect.
Prompt: A flock of paper airplanes flutters through a dense jungle, weaving around trees as if they were migrating birds.
Prompt: A cat waking up its sleeping owner demanding breakfast. The owner tries to ignore the cat, but the cat tries new tactics and finally the owner pulls out a secret stash of treats from under the pillow to hold the cat off a little longer.
Prompt: Borneo wildlife on the Kinabatangan River
Prompt: A Chinese Lunar New Year celebration video with Chinese Dragon.
Il modello possiede una profonda comprensione del linguaggio, che gli consente di interpretare con precisione i prompt e generare personaggi coinvolgenti che esprimono emozioni vivide. Sora può anche creare più inquadrature all’interno di un singolo video generato, mantenendo fedelmente i personaggi e lo stile visivo.
Prompt: Tour of an art gallery with many beautiful works of art in different styles.
Prompt: Beautiful, snowy Tokyo city is bustling. The camera moves through the bustling city street, following several people enjoying the beautiful snowy weather and shopping at nearby stalls. Gorgeous sakura petals are flying through the wind along with snowflakes.
Prompt: A stop motion animation of a flower growing out of the windowsill of a suburban house.
Prompt: The story of a robot’s life in a cyberpunk setting.
Prompt: An extreme close-up of an gray-haired man with a beard in his 60s, he is deep in thought pondering the history of the universe as he sits at a cafe in Paris, his eyes focus on people offscreen as they walk as he sits mostly motionless, he is dressed in a wool coat suit coat with a button-down shirt , he wears a brown beret and glasses and has a very professorial appearance, and the end he offers a subtle closed-mouth smile as if he found the answer to the mystery of life, the lighting is very cinematic with the golden light and the Parisian streets and city in the background, depth of field, cinematic 35mm film.
Prompt: A beautiful silhouette animation shows a wolf howling at the moon, feeling lonely, until it finds its pack.
Prompt: New York City submerged like Atlantis. Fish, whales, sea turtles and sharks swim through the streets of New York.
Prompt: A litter of golden retriever puppies playing in the snow. Their heads pop out of the snow, covered in.
Il modello attuale presenta ancora margini di miglioramento. Potrebbe avere difficoltà a simulare la fisica di una scena complessa e potrebbe non comprendere istanze specifiche di causa-effetto (ad esempio, un biscotto potrebbe non mostrare alcun segno dopo che un personaggio lo ha morso). Il modello potrebbe anche confondere i dettagli spaziali inclusi in un prompt, ad esempio non distinguendo la sinistra dalla destra, o avere difficoltà con descrizioni precise di eventi che si svolgono nel tempo, come specifiche traiettorie di una telecamera.
Prompt: Step-printing scene of a person running, cinematic film shot in 35mm.
Punto debole: a volte Sora crea movimenti fisicamente improbabili.
Prompt: Five gray wolf pups frolicking and chasing each other around a remote gravel road, surrounded by grass. The pups run and leap, chasing each other, and nipping at each other, playing.
Punto debole: animali o persone possono apparire spontaneamente, soprattutto in scene contenenti molte entità.
Prompt: Basketball through hoop then explodes.
Punto debole: un esempio di modellazione fisica imprecisa e di “morphing” innaturale degli oggetti.
Prompt: Archeologists discover a generic plastic chair in the desert, excavating and dusting it with great care.
Punto debole: in questo esempio, Sora non riesce a modellare la sedia come un oggetto rigido, causando interazioni fisiche imprecise.
Prompt: A grandmother with neatly combed grey hair stands behind a colorful birthday cake with numerous candles at a wood dining room table, expression is one of pure joy and happiness, with a happy glow in her eye. She leans forward and blows out the candles with a gentle puff, the cake has pink frosting and sprinkles and the candles cease to flicker, the grandmother wears a light blue blouse adorned with floral patterns, several happy friends and family sitting at the table can be seen celebrating, out of focus. The scene is beautifully captured, cinematic, showing a 3/4 view of the grandmother and the dining room. Warm color tones and soft lighting enhance the mood..
Punto debole: simulare interazioni complesse tra oggetti e più personaggi risulta spesso una sfida per il modello, generando a volte risultati comici.
Adotteremo diverse e importanti misure di sicurezza prima di rendere Sora disponibile nei prodotti OpenAI. Stiamo collaborando con red teamer, esperti in settori come disinformazione, contenuti d’odio e pregiudizi, che testeranno il modello in modo antagonistico.
Stiamo anche sviluppando strumenti per rilevare contenuti fuorvianti, come un classificatore in grado di stabilire quando un video è stato generato da Sora. Prevediamo di includere metadati C2PA(si apre in una nuova finestra) in futuro, se il modello verrà implementato in un prodotto OpenAI.
Oltre a sviluppare nuove tecniche per prepararci all’implementazione, stiamo sfruttando i metodi di sicurezza esistenti(si apre in una nuova finestra) che abbiamo sviluppato per i nostri prodotti basati su DALL·E 3, applicabili anche a Sora.
Ad esempio, una volta integrato in un prodotto OpenAI, il nostro classificatore testuale controllerà e rifiuterà i prompt di testo che violano le nostre politiche di utilizzo, come richieste di violenza estrema, contenuti sessuali, immagini d’odio, immagini di celebrità o proprietà intellettuali di terzi. Abbiamo inoltre sviluppato solidi classificatori di immagini che esaminano i fotogrammi di ogni video generato, per garantire che rispettino le nostre politiche di utilizzo prima di essere mostrati all’utente.
Coinvolgeremo decisori politici, educatori e artisti di tutto il mondo per comprendere le loro preoccupazioni e identificare casi d’uso positivi per questa nuova tecnologia. Nonostante ricerche e test approfonditi, non possiamo prevedere tutti i modi vantaggiosi in cui le persone utilizzeranno la nostra tecnologia, né tutti i modi in cui ne abuseranno. Per questo riteniamo che imparare dall’uso nel mondo reale sia un elemento cruciale per creare e distribuire nel tempo sistemi di IA sempre più sicuri.
Prompt: The camera directly faces colorful buildings in Burano Italy. An adorable dalmation looks through a window on a building on the ground floor. Many people are walking and cycling along the canal streets in front of the buildings.
Prompt: An adorable happy otter confidently stands on a surfboard wearing a yellow lifejacket, riding along turquoise tropical waters near lush tropical islands, 3D digital render art style.
Prompt: This close-up shot of a chameleon showcases its striking color changing capabilities. The background is blurred, drawing attention to the animal’s striking appearance.
Prompt: A corgi vlogging itself in tropical Maui.
Prompt: A white and orange tabby cat is seen happily darting through a dense garden, as if chasing something. Its eyes are wide and happy as it jogs forward, scanning the branches, flowers, and leaves as it walks. The path is narrow as it makes its way between all the plants. the scene is captured from a ground-level angle, following the cat closely, giving a low and intimate perspective. The image is cinematic with warm tones and a grainy texture. The scattered daylight between the leaves and plants above creates a warm contrast, accentuating the cat’s orange fur. The shot is clear and sharp, with a shallow depth of field.
Prompt: Aerial view of Santorini during the blue hour, showcasing the stunning architecture of white Cycladic buildings with blue domes. The caldera views are breathtaking, and the lighting creates a beautiful, serene atmosphere.
Prompt: Tiltshift of a construction site filled with workers, equipment, and heavy machinery.
Prompt: A giant, towering cloud in the shape of a man looms over the earth. The cloud man shoots lighting bolts down to the earth.
Prompt: A Samoyed and a Golden Retriever dog are playfully romping through a futuristic neon city at night. The neon lights emitted from the nearby buildings glistens off of their fur.
Prompt: The Glenfinnan Viaduct is a historic railway bridge in Scotland, UK, that crosses over the west highland line between the towns of Mallaig and Fort William. It is a stunning sight as a steam train leaves the bridge, traveling over the arch-covered viaduct. The landscape is dotted with lush greenery and rocky mountains, creating a picturesque backdrop for the train journey. The sky is blue and the sun is shining, making for a beautiful day to explore this majestic spot.
Sora è un modello di diffusione, che genera un video partendo da uno che sembra rumore statico e lo trasforma gradualmente rimuovendo il rumore attraverso vari passaggi.
Sora è in grado di generare interi video in una sola volta o di estendere i video generati per renderli più lunghi. Fornendo al modello la visione anticipata di molti fotogrammi alla volta, abbiamo risolto una sfida importante: mantenere la coerenza del soggetto anche quando esce temporaneamente dal campo visivo.
Similmente ai modelli GPT, Sora utilizza un’architettura transformer, che consente prestazioni di scalabilità superiori.
Rappresentiamo video e immagini come raccolte di unità di dati più piccole chiamate patch, ognuna delle quali è simile a un token nei modelli GPT. Unificando il modo in cui rappresentiamo i dati, possiamo addestrare i transformer di distribuzione su una gamma più ampia di dati visivi rispetto a prima, coprendo diverse durate, risoluzioni e proporzioni.
Sora si basa su ricerche precedenti sui modelli DALL·E e GPT. Utilizza la tecnica di recaptioning di DALL·E 3, che prevede la generazione di didascalie altamente descrittive per i dati visivi usati durante l’addestramento. Di conseguenza, il modello è in grado di seguire più fedelmente le istruzioni testuali fornite dall’utente nel video generato.
Oltre a poter generare un video esclusivamente a partire da istruzioni testuali, il modello è in grado di acquisire un’immagine statica esistente e di generare un video a partire da essa, animandone il contenuto con precisione e attenzione ai minimi dettagli. Il modello può anche acquisire un video esistente ed estenderlo o riempire i fotogrammi mancanti. Scopri di più nel nostro report tecnico.
Sora funge da base per modelli in grado di comprendere e simulare il mondo reale, una capacità che riteniamo sarà una tappa fondamentale per il raggiungimento dell’AGI.