Sora: i migliori video creati con il modello OpenAI

L’ennesima spallata di OpenAI all’ambito dell’intelligenza artificiale è giunta poche ore fa con la presentazione di Sora. Si tratta di un modello text-to-video sulla base del quale sarà possibile generare filmati dalla durata fino a 60 secondi e da un impatto visivo molto convincente. A volte, forse troppo.

IA e text-to-video: Sora mostra i muscoli

Purtroppo (o per fortuna) non si è ancora in grado di mettere alla prova il sistema, né è stata fissata una finestra temporale per il lancio. La sezione dedicata al progetto sul sito ufficiale ospita però già parecchi esempi utili a dimostrarne le potenzialità. Li abbiamo osservati: ecco quelli migliori, e in coda all’articolo i peggiori, accompagnati dai prompt digitati per ottenere i risultati visibili qui sotto, alcuni molto dettagliati. Ce n’è uno che ricostruisce la costiera amalfitana con una ripresa aerea.

Historical footage of California during the gold rush.

A beautiful homemade video showing the people of Lagos, Nigeria in the year 2056. Shot with a mobile phone camera.

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.

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.

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.

A Chinese Lunar New Year celebration video with Chinese Dragon.

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.

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.

Come sottolinea la stessa OpenAI, non sempre tutto va per il verso giusto.

Step-printing scene of a person running, cinematic film shot in 35mm.

Basketball through hoop then explodes.

Intelligenza artificiale e sicurezza

Sarà importante garantire che strumenti di questo tipo non possano essere impiegati con finalità malevole, ad esempio per la creazione di deepfake estremamente convincenti da diffondere per campagna di disinformazione o altro.

Dal canto suo, OpenAI ha messo nero su bianco l’intenzione di lavorare affinché possano essere implementate le necessarie misure di sicurezza prima del lancio ufficiale di Sora. La fase di test coinvolgerà soggetti indipendenti e i contenuti includeranno metadati C2PA (come per quelli creati con DALL·E 3). Al momento non sono stare rese note le tempistiche per il debutto.