Gumagawa ng video mula sa text
Direktang binuo ng Sora ang lahat ng video sa page na ito nang walang binago.
Tinuturuan namin ang AI na maunawaan at i-simulate ang pisikal na mundo na gumagalaw, na may layuning magsanay ng mga modelo na tutulong sa mga tao na lutasin ang mga problemang nangangailangan ng interaction sa totoong mundo.
Ipinapakilala ang Sora, ang aming text-to-video na modelo. Kayang bumuo ng Sora ng mga video na hanggang isang minuto habang pinapanatili ang visual na kalidad at sumusunod sa prompt ng user.
Prompt: Isang stylish na babaeng naglalakad sa isang kalye sa Tokyo na puno ng warm at glowing na neon at animated na karatula sa lungsod. Nakasuot siya ng itim na leather jacket, mahabang pulang bestida, at itim na boots, at may dala siyang itim na pitaka. Nakasuot siya ng sunglasses at may pulang lipstick. Naglalakad siya nang may kumpiyansa at nang hindi nagmamadali. Mamasa-masa at reflective ang kalye, kaya may mirror effect ang makukulay na ilaw. Maraming pedestrian ang naglalakad-lakad.
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 ng mga alon na humahampas sa mababatong dalisdis sa garay point beach ng Big Sur. Gumagawa ang mga humahampas na asul na tubig ng mga alon na may puting tuktok, habang nagliliwanag ang mabatong dalampasigan sa ginintuang liwanag ng lumulubog na araw. May matatanaw na maliit na isla na may parola, at may mga berdeng halaman na bumabalot sa gilid ng talampas. Napakaganda ng matarik na daan mula sa kalsada papunta sa dalampasigan, at nakausli ang mga gilid ng dalisdis sa dagat. Isa itong tanawin na sumasalamin sa likas na kagandahan ng baybayin at mabatong landscape ng 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.
Ngayon, magiging available na ang Sora sa mga red teamer para masuri ang mga kritikal na bahagi para sa mga pinsala o panganib. Bibigyan din namin ng access ang ilang visual artist, designer at filmmaker para makakuha ng feedback sa kung paano pagandahin ang modelo para lubos na maging kapaki-pakinabang sa mga creative professional.
Ibabahagi namin nang maaga ang aming progreso sa pananaliksik para magsimulang makipagtulungan sa at makakuha ng feedback mula sa mga taong hindi bahagi ng OpenAI, at para bigyan ang publiko ng ideya kung ano ang mga kakayahan ng AI na paparating.
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.
Kayang bumuo ng Sora ng mga kumplikadong eksena na may maraming character, mga partikular na uri ng galaw, at mga tumpak na detalye ng subject at background. Nauunawaan ng modelo hindi lang ang hinihiling ng user sa prompt, kundi pati na rin kung paano umiiral ang mga bagay na iyon sa pisikal na mundo.
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.
May malalim na pag-unawa sa wika ang modelo, kaya tumpak nitong nabibigyang-kahulugan ang mga prompt at nakakabuo ito ng mga nakakaengganyong character na nagpapahayag ng mga buhay na buhay na damdamin. Puwede ring gumawa ang Sora ng maraming shot sa loob ng isang nabuong video na tumpak na naipapakita ang mga character at visual style.
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.
Puwede pang pagandahin ang kasalukuyang modelo. Maaaring mahirapan itong i-simulate ang physics ng isang kumplikadong eksena, at maaaring hindi nito maunawaan ang mga partikular na pagkakataon ng sanhi at epekto (halimbawa: maaaring hindi magkaroon ng kagat ang isang cookie pagkatapos itong kagatan ng isang character). Maaari ding malito ang modelo sa mga detalye ng espasyo na kasama sa isang prompt, tulad ng pagtukoy sa kaliwa mula sa kanan, o maaari itong mahirapan sa mga tumpak na paglalarawan ng mga event na nangyayari sa paglipas ng panahon, tulad ng mga partikular na trajectory ng camera.
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.
May gagawin kaming ilang mahalagang hakbang para sa kaligtasan bago gawing available ang Sora sa mga produkto ng OpenAI. Nakikipagtulungan kami sa mga red teamer — mga eksperto sa domain sa mga larangan tulad ng maling impormasyon, mapoot na content, at bias — na susubok sa modelo bilang adversary.
Gumagawa rin kami ng mga tool na nakakatulong sa pag-detect ng mapanlinlang na content, tulad ng detection classifier na matutukoy kung binuo ng Sora ang isang video. Pinaplano naming isama ang metadata ng C2PA(magbubukas sa bagong window) sa hinaharap kung ide-deploy namin ang modelo sa produkto ng OpenAI.
Bukod sa pagbuo namin ng mga bagong technique para maghanda para sa pag-deploy, gagamitin din namin ang mga kasalukuyang pamamaraan sa kaligtasan(magbubukas sa bagong window) na binuo namin para sa aming mga produkto na gumagamit ng DALL·E 3, na naaangkop din sa Sora.
Halimbawa, kapag nasa isang produkto na ng OpenAI, susuriin at tatanggihan ng aming classifier ng text ang mga text input prompt na lumalabag sa aming mga patakaran sa paggamit, tulad ng mga humihiling ng matinding karahasan, sekswal na content, mapoot na imagery, likeness ng celebrity, o IP ng iba. Bumuo rin kami ng mahuhusay na classifier ng larawan na ginagamit upang suriin ang mga frame ng bawat video na binuo upang matiyak na sumusunod ito sa aming mga patakaran sa paggamit, bago ito ipakita sa user.
Makikipagtulungan kami sa mga tagapagbatas, tagapagturo, at mga artist sa buong mundo upang maunawaan ang kanilang mga alalahanin at matukoy ang mga positibong use case para sa bagong teknolohiyang ito. Sa kabila ng malawak na pananaliksik at pagsubok, hindi namin matutukoy ang lahat ng kapaki-pakinabang na paraan kung paano gagamitin ng mga tao ang aming teknolohiya, o ang lahat ng paraan kung paano ito aabusuhin ng mga tao. Iyon ang dahilan kung bakit naniniwala kami na mahalagang bahagi ng paggawa at pag-release ng mga mas ligtas na AI system ang pagkatuto mula sa paggamit sa totoong buhay sa paglipas ng panahon.
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.
Ang Sora ay isang diffusion model, na bumubuo ng video sa pamamagitan ng pagsisimula sa isang video na mukhang static noise at unti-unti nito itong binabago sa pamamagitan ng pag-alis ng noise sa maraming hakbang.
Kayang bumuo ng Sora ng mga buong video nang sabay-sabay o palawigin ang mga nabuong video upang pahabain ang mga ito. Sa pamamagitan ng pagbibigay sa modelo ng kakayahang makita ang maraming frame nang sabay-sabay, nalutas namin ang mahirap na problema ng pagtiyak na hindi magbabago ang subject kahit na pansamantala itong mawala sa view.
Katulad ng mga modelo ng GPT, gumagamit ang Sora ng transformer architecture, na nagbibigay ng mahusay na performance sa pag-scale.
Inilalarawan namin ang mga video at larawan bilang mga koleksyon ng maliliit na unit ng data na tinatawag na mga patch, at katulad ng token sa GPT ang bawat isa sa mga ito. Dahil pinag-isa ang paraan ng paglalarawan sa data, puwede nating sanayin ang mga diffusion transformer sa mas malawak na hanay ng visual data kaysa dati, na sumasaklaw sa iba't ibang tagal, resolution, at mga aspect ratio.
Ang Sora ay nakabatay sa nakaraang pananaliksik sa mga modelo ng DALL·E at GPT. Ginagamit nito ang technique sa recaptioning mula sa DALL·E 3, kung saan bumubuo ng mga lubos na mapaglarawang caption para sa visual data ng pagsasanay. Dahil dito, mas tapat na nasusunod ng modelo ang mga text na tagubilin ng user sa nabuong video.
Bukod sa kakayahang bumuo ng video mula lang sa mga text na tagubilin, kaya rin ng modelo na kumuha ng still image na mayroon na at bumuo ng video mula rito, at ia-animate nito ang mga content ng larawan nang may katumpakan at pagtuon sa maliliit na detalye. Kaya rin ng modelo na kumuha ng video na mayroon na at palawakin ito o punan ang mga nawawalang frame. Matuto pa sa aming teknikal na ulat.
Ang Sora ay nagsisilbing pundasyon para sa mga modelo na kayang maunawaan at i-simulate ang totoong mundo, na isang kakayahan na sa palagay namin ay magiging mahalagang milestone para sa pagkamit ng AGI.