Kreiranje videa iz teksta
Sve video-snimke na ovoj stranici generisala je direktno Sora bez izmena.
Učimo AI da razume i simulira fizički svet u pokretu, sa ciljem da obučimo modele koji pomažu ljudima da rešavaju probleme koji zahtevaju interakciju sa stvarnim svetom.
Predstavljamo Sora, naš model za generisanje videa iz teksta. Sora može da generiše video-snimke do jednog minuta uz očuvanje vizuelnog kvaliteta i usklađenosti sa korisnikovom instrukcijom.
Instrukcija: Elegantna žena hoda tokijskom ulicom ispunjenom toplim sjajem neona i animiranim gradskim natpisima. Nosi crnu kožnu jaknu, dugu crvenu haljinu i crne čizme, a sa sobom nosi crnu tašnu. Nosi naočare za sunce i crveni ruž. Hoda samouvereno i opušteno. Ulica je vlažna i reflektujuća, stvarajući efekat ogledala od šarenih svetala. Mnogi pešaci prolaze unaokolo.
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.
Instrukcija: Snimak dronom talasa koji udaraju o surove litice duž plaže Garay Point u Big Suru. Uzburkana plava voda stvara talase sa belim vrhovima, dok zlatna svetlost zalazećeg sunca obasjava stenovitu obalu. Malo ostrvo sa svetionikom nalazi se u daljini, a zeleno rastinje prekriva ivicu litice. Strm pad sa puta do plaže izgleda dramatično, sa ivicama litice koje štrče nad morem. Ovo je prizor koji hvata sirovu lepotu obale i surovi pejzaž autoputa 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.
Danas Sora postaje dostupna red teamerima kako bi procenili kritične oblasti mogućih šteta i rizika. Takođe odobravamo pristup određenom broju vizuelnih umetnika, dizajnera i filmskih stvaralaca kako bismo dobili povratne informacije o tome kako da unapredimo model da bude što korisniji kreativnim profesionalcima.
Rano delimo napredak našeg istraživanja kako bismo počeli da radimo sa ljudima van OpenAI-ja i dobijamo njihove povratne informacije, kao i da javnosti damo predstavu o AI mogućnostima koje se naziru na horizontu.
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 može da generiše složene scene sa više karaktera, specifičnim vrstama kretanja i preciznim detaljima subjekta i pozadine. Model razume ne samo ono što je korisnik tražio u instrukciji, već i kako te stvari postoje u fizičkom svetu.
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.
Model ima duboko razumevanje jezika, što mu omogućava da tačno tumači instrukcije i generiše upečatljive karaktere koji izražavaju živopisne emocije. Sora takođe može da kreira više kadrova unutar jednog generisanog videa uz dosledno očuvanje karaktera i vizuelnog stila.
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.
Trenutni model i dalje ima prostora za unapređenje. Može imati poteškoća sa simuliranjem fizike složene scene i možda neće razumeti specifične primere uzroka i posledice (na primer: kolačić možda neće pokazati trag nakon što ga Karakter zagrize). Model takođe može pomešati prostorne detalje navedene u instrukciji, kao što je razlikovanje leve od desne strane, ili imati poteškoća sa preciznim opisima događaja koji se odvijaju tokom vremena, poput određenih putanja kamere.
Prompt: Step-printing scene of a person running, cinematic film shot in 35mm.
Weakness: Sora sometimes creates physically implausible motion.
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.
Weakness: Animals or people can spontaneously appear, especially in scenes containing many entities.
Prompt: Basketball through hoop then explodes.Prompt: Basketball through hoop then explodes.
Weakness: An example of inaccurate physical modeling and unnatural object “morphing.”
Prompt: Archeologists discover a generic plastic chair in the desert, excavating and dusting it with great care.
Weakness: In this example, Sora fails to model the chair as a rigid object, leading to inaccurate physical interactions.
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..
Weakness: Simulating complex interactions between objects and multiple characters is often challenging for the model, sometimes resulting in humorous generations.
Pre nego što Sora postane dostupna u OpenAI proizvodima, preduzećemo nekoliko važnih koraka za bezbednost. Sarađujemo sa red teamerima — stručnjacima za oblasti poput dezinformacija, sadržaja mržnje i pristrasnosti — koji će model testirati na adversarijalan način.
Takođe razvijamo alate za otkrivanje obmanjujućeg sadržaja, poput klasifikatora za detekciju koji može da utvrdi kada je video generisala Sora. Planiramo da u budućnosti uključimo C2PA metapodatke(отвара се у новом прозору) ako model uvedemo u neki OpenAI proizvod.
Pored razvoja novih tehnika za pripremu uvođenja, koristimo i postojeće bezbednosne metode(отвара се у новом прозору) koje smo razvili za naše proizvode koji koriste DALL·E 3, a koje su primenljive i na Sora.
Na primer, kada bude deo OpenAI proizvoda, naš klasifikator teksta proveravaće i odbacivati tekstualne instrukcije koje krše naše politike korišćenja, poput onih koje traže ekstremno nasilje, seksualni sadržaj, slike mržnje, lik slavnih osoba ili tuđu intelektualnu svojinu. Razvili smo i robusne klasifikatore slike koji se koriste za pregled kadrova svakog generisanog videa kako bi pomogli da se osigura usklađenost sa našim politikama korišćenja pre nego što video bude prikazan korisniku.
Uključićemo kreatore politika, edukatore i umetnike širom sveta kako bismo razumeli njihove brige i identifikovali pozitivne slučajeve upotrebe ove nove tehnologije. Uprkos opsežnim istraživanjima i testiranju, ne možemo predvideti sve korisne načine na koje će ljudi koristiti našu tehnologiju, niti sve načine na koje će je zloupotrebljavati. Zato verujemo da je učenje iz upotrebe u stvarnom svetu ključna komponenta stvaranja i objavljivanja sve bezbednijih AI sistema tokom vremena.
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 je difuzioni model koji generiše video tako što počinje od onog koji izgleda kao statički šum i postepeno ga transformiše uklanjanjem šuma kroz mnogo koraka.
Sora može da generiše cele video-snimke odjednom ili da produži generisane video-snimke kako bi bili duži. Dajući modelu uvid unapred u mnogo kadrova istovremeno, rešili smo složen problem očuvanja istog subjekta čak i kada privremeno izađe iz kadra.
Slično GPT modelima, Sora koristi arhitekturu transformatora, što omogućava vrhunske performanse skaliranja.
Video-snimke i slike predstavljamo kao zbirke manjih jedinica podataka koje zovemo patch-evi, od kojih je svaki sličan tokenu u GPT‑u. Ujednačavanjem načina na koji predstavljamo podatke, možemo da obučavamo difuzne transformatore na širem spektru vizuelnih podataka nego što je ranije bilo moguće, obuhvatajući različita trajanja, rezolucije i odnose stranica.
Sora se nadovezuje na prethodna istraživanja u DALL·E i GPT modelima. Koristi tehniku ponovnog opisivanja iz DALL·E 3, koja podrazumeva generisanje veoma detaljnih opisa za vizuelne podatke za obuku. Kao rezultat toga, model može vernije da prati korisnikove tekstualne instrukcije u generisanom videu.
Pored toga što može da generiše video isključivo iz tekstualnih instrukcija, model može da primi postojeću statičnu sliku i od nje napravi video, animirajući njen sadržaj precizno i uz pažnju prema sitnim detaljima. Model takođe može da primi postojeći video i da ga produži ili popuni nedostajuće kadrove. Saznajte više u našem tehničkom izveštaju.
Sora služi kao osnova za modele koji mogu da razumeju i simuliraju stvarni svet, sposobnost za koju verujemo da će biti važna prekretnica za dostizanje AGI-ja.