OpenAI imzalı Sora ile oluşturulmuş yeni videolar paylaşıldı. Sistem halen mükemmel değil ancak nefes kesmeye devam ediyor.
OpenAI, eğer kaçırdıysanız geçtiğimiz ay içinde yazılanları görsel hale getiren DALL-E sonrasında video üretimi tarafına da el attı. Firmanın yeni yapay zeka modeli “Sora”, yazılanlardan 60 saniyelik videolar üretebiliyor ve çok ama çok iyi sonuçlar ortaya koyuyor. Bu alana biraz geç giriş yapan ancak çok iddialı bir altyapı hazırlayan firma, Sora’nın olası güvenlik risklerine karşı ilk aşamada belirli kişilere açılacağını belirtiyor. Sistemin kötüye kullanımını engellemek adına herkese açık genel çıkışı daha sonra yapacaklarını söyleyen firma, Sora’nın çok sayıda karaktere / insana / canlıya / objeye sahip kompleks sahneler üretebildiğini belirtiyor, gösterilen ilk örnekler de bunu doğruluyor. Kişilerin isteklerini fiziksel gerçeklik ile harmanlayan sistem, henüz mükemmel değil ve OpenAI da bunu kabul ederek bazı zayıf yanların olduğunu açık olarak belirtiyor. Elbette DALL-E gibi zaman içerisinde daha iyi hale getirilecek Sora, daha şimdiden çok büyük bir gelecek potansiyeli ortaya koyuyor ve sistemin video kolajları oluşturabildiği de belirtiliyor. Sistemi bugün gündeme getiren ise paylaşılan yeni videolar oldu. Sora’yı deneme şansı elde eden ünlü YouTuber Marques Brownlee, hemen aşağıdaki örnekleri paylaştı:
Prompt 1: A medium sized friendly looking dog walks through an industrial parking lot. The environment is foggy and cloudy. Shot on 35mm film, vivid colors. pic.twitter.com/gs4Mi3idZT
— Marques Brownlee (@MKBHD) February 29, 2024
Prompt 2: A timelapse closeup of a 3D printer printing a small red cube in an office with dim lighting. pic.twitter.com/bczuoOnrK6
— Marques Brownlee (@MKBHD) February 29, 2024
Prompt 3: A young professional product reviewer in a well lit video studio is surrounded by gadgets and technology, sitting in front of a computer with two displays. He's holding a cinema camera as he ponders what video to make next. He is in focus, while the background is… pic.twitter.com/0sPC2UgFsv
— Marques Brownlee (@MKBHD) February 29, 2024
Ellerde ve insan hareketlerinde halen sorunlar yaşadığı görülen ancak genel olarak çok gerçekçi sonuçlar ortaya koyan ve Marques Brownlee tarafından özellikle ışıklandırma konusunda çok beğenilen sistem için OpenAI kendisi de örnekler paylaşmaya devam ediyor. Firmanın buradaki resmi TikTok hesabından her gün Sora ile üretilmiş “şaka gibi” videolar paylaşılıyor. Teknolojik ürünleri ya da otomobilleri hemen tanınabilecek spesifik modeller olarak üretmediği de aktarılan Sora, 1-2 yıl içinde yapay zeka üretimi olduğu kesinlikle anlaşılmayan içerikler ortaya koyacak gibi duruyor.
Sora can generate multiple videos side-by-side simultaneously.
This is a single video sample from Sora. We didn't stitch this together; Sora decided it wanted to have five different viewpoints all at once! pic.twitter.com/hGae80tM5a
— Bill Peebles (@billpeeb) February 17, 2024
Sistem ile hazırlanan diğer dikkat çekici örnekler:
"a green blob and an orange blob are in love and dancing together"
Video generated by Sora
the video you generate for your partner when you dont make it home from office on valentines day #Sora pic.twitter.com/i28Ar3Ex6H
— Tim Brooks (@_tim_brooks) February 17, 2024
"a spooky haunted mansion, with friendly jack o lanterns and ghost characters welcoming trick or treaters to the entrance, tilt shift photography"
Video generated by Sora. pic.twitter.com/gwLnPCh4Qb
— Bill Peebles (@billpeeb) February 17, 2024
"a giant cathedral is completely filled with cats. there are cats everywhere you look. a man enters the cathedral and bows before the giant cat king sitting on a throne."
Video generated by Sora. pic.twitter.com/bkNqCnckUo
— Bill Peebles (@billpeeb) February 17, 2024
"realistic video of people relaxing at beach, then a shark jumps out of the water halfway through and surprises everyone"
Video generated by Sora pic.twitter.com/WRVnrguCif
— Tim Brooks (@_tim_brooks) February 17, 2024
"a walking figure made out of water tours an art gallery with many beautiful works of art in different styles"
Video generated by Sora
Sora has object permanence – the paintings stay consistent before and after the water man walks in front pic.twitter.com/lQgmlhHbir
— Tim Brooks (@_tim_brooks) February 17, 2024
"a giant duck walks through the streets in Boston"
Video generated by Sora pic.twitter.com/ogMLcefR1h
— Tim Brooks (@_tim_brooks) February 17, 2024
"a photorealistic video of a butterfly that can swim navigating underwater through a beautiful coral reef"
Video generated by Sora pic.twitter.com/nebCKLa09U
— Tim Brooks (@_tim_brooks) February 17, 2024
Sora can also generate stories involving a sequence of events, although it's far from perfect.
For this video, I asked that a golden retriever and samoyed should walk through NYC, then a taxi should stop to let the dogs pass a crosswalk, then they should walk past a pretzel and… pic.twitter.com/OhqVFqR5vA
— Bill Peebles (@billpeeb) February 17, 2024
"The camera lowers and widens to a grand panoramic view overlooking the beautiful ocean and the historical buildings along the a stunning coastal picturesque town perched on the cliffs…"
Video generated by Sora. pic.twitter.com/d35Zebo4vc
— Bill Peebles (@billpeeb) February 17, 2024
someone plz adopt this cat 😭
"a white and orange tabby alley cat is seen darting across a back street alley in a heavy rain, looking for shelter…" (prompt by Chad Nelson)
Video generated by Sora pic.twitter.com/u0U8nfqcQP
— Tim Brooks (@_tim_brooks) February 17, 2024
"macro shot of a leaf showing tiny trains moving through its veins"
Video generated by Sora pic.twitter.com/dT3AMrkWoV
— Aditya Ramesh (@model_mechanic) February 17, 2024
"pov footage of an ant navigating the inside of an ant nest"
Video generated by Sora pic.twitter.com/N3Ik9QBinU
— Aditya Ramesh (@model_mechanic) February 18, 2024
"this close-up shot of a futuristic cybernetic german shepherd showcases its striking brown and black fur…"
Video generated by Sora. pic.twitter.com/Bopbl0yv0Y
— Bill Peebles (@billpeeb) February 18, 2024
"minecraft with the most gorgeous high res 8k texture pack ever"
Video generated by Sora pic.twitter.com/KbFdjh0LDA
— Tim Brooks (@_tim_brooks) February 18, 2024
— Sam Altman (@sama) February 15, 2024
1) What https://t.co/w6b9T1WWue
— Sam Altman (@sama) February 15, 2024
https://t.co/qbj02M4ng8 pic.twitter.com/EvngqF2ZIX
— Sam Altman (@sama) February 15, 2024
https://t.co/rmk9zI0oqO pic.twitter.com/WanFKOzdIw
— Sam Altman (@sama) February 15, 2024
https://t.co/uCuhUPv51N pic.twitter.com/nej4TIwgaP
— Sam Altman (@sama) February 15, 2024
https://t.co/P26vJHlw06 pic.twitter.com/AW9TfYBu3b
— Sam Altman (@sama) February 15, 2024
here is a better one: https://t.co/WJQCMEH9QG pic.twitter.com/oymtmHVmZN
— Sam Altman (@sama) February 15, 2024
https://t.co/rPqToLo6J3 pic.twitter.com/nPPH2bP6IZ
— Sam Altman (@sama) February 15, 2024
https://t.co/WJQCMEH9QG pic.twitter.com/Qa51e18Vph
— Sam Altman (@sama) February 15, 2024
https://t.co/SOUoXiSMBY pic.twitter.com/JB4zOjmbTp
— Sam Altman (@sama) February 15, 2024
Bunlar da OpenAI’ın X hesabına eklenen bazı çok iyi örnekler:
Introducing Sora, our text-to-video model.
Sora can create videos of up to 60 seconds featuring highly detailed scenes, complex camera motion, and multiple characters with vibrant emotions. https://t.co/7j2JN27M3W
Prompt: “Beautiful, snowy… pic.twitter.com/ruTEWn87vf
— OpenAI (@OpenAI) February 15, 2024
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… pic.twitter.com/Um5CWI18nS
— OpenAI (@OpenAI) February 15, 2024
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.” pic.twitter.com/0JzpwPUGPB
— OpenAI (@OpenAI) February 15, 2024
Prompt: “A gorgeously rendered papercraft world of a coral reef, rife with colorful fish and sea creatures.” pic.twitter.com/gzEE8SwP81
— OpenAI (@OpenAI) February 15, 2024
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… pic.twitter.com/aLMgJPI0y6
— OpenAI (@OpenAI) February 15, 2024
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.… pic.twitter.com/cjIdgYFaWq
— OpenAI (@OpenAI) February 15, 2024
