Last month, OpenAI caused a stir worldwide as it revealed the groundbreaking videos produced by Sora, its advanced AI-driven text-to-video generator. While the output was not without flaws, its exceptional quality sparked discussions about the transformative potential of such technologies for creative sectors, including the film industry in Hollywood.
While Sora has not been made available to the public as of yet — an event anticipated to occur later this year — OpenAI takes pleasure in captivating audiences by frequently sharing videos produced by Sora on its social platforms.
OpenAI released new Sora footage on TikTok
One of the recent videos shared appears to depict a scene from a fantasy film, generated from the straightforward text prompt: “An elephant made of leaves running in the jungle.”
@openai Sora Sunday delivery. Prompt: an elephant made of leaves running in the jungle This video was generated by our text-to-video model, Sora, without modification. What would you like to see us make with Sora next? *Sora is not yet available to the public. We’re sharing our research progress early to learn from feedback and give the public a sense of what AI capabilities are on the horizon. #madewithSora #Sora #openai
♬ The Elephant – Sam Fraser
OpenAI has confirmed that Sora autonomously produced the video without any external alterations.
Naturally, any competent video creation tool must excel in producing cat videos. Sora achieved this brilliantly with the prompt: “An adorable kitten pirate riding a robot vacuum around the house.”
@openai Prompt: An adorable kitten pirate riding a robot vacuum around the house This video was generated by our text-to-video model, Sora, without modification. What would you like to see us make with Sora next? *Sora is not yet available to the public. We’re sharing our research progress early to learn from feedback and give the public a sense of what AI capabilities are on the horizon. #madewithSora #Sora #openai
♬ 某 Pirate movie style jingle. – Whistle Grandpa
When given the task to visualize “Niagara Falls with colorful paint,” Sora produced footage that was nothing short of remarkable.
@openai Prompt: niagara falls with colorful paint instead of water This video was generated by our text-to-video model, Sora, without modification. What would you like to see us make with Sora next? *Sora is not yet available to the public. We’re sharing our research progress early to learn from feedback and give the public a sense of what AI capabilities are on the horizon. #madewithSora #Sora #openai
♬ Water of Life – Hariseno
Also, witness this impressive footage created from the prompt: “POV video of a bee as it dives through a beautiful field of flowers.”
@openai Prompt: “POV video of a bee as it dives through a beautiful field of flowers” This video was generated by our text-to-video model, Sora, without modification. *Sora is not yet available to the public. We’re sharing our research progress early to learn from feedback and give the public a sense of what AI capabilities are on the horizon. #madewithSora #Sora #openai
♬ Tchaikovsky “Waltz of the Flowers” (Excerpt C Edition)(1252263) – LEOPARD
Also there’s a very detailed prompt example: “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. Colorful buildings in shades of yellow, orange, pink, and white cascade down the steep slopes of the rugged coastline of Amalfi Coast in Italy. The architecture has a classic European charm, with tiled roofs and ornate details. Several boats and yachts are speckled across the calm waters, implying leisure activities like boating or sightseeing are common here. Lush greenery on the mountainous landscape. The overall image is vibrant, inviting, and bustling with the potential for holiday adventures and relaxation, warm golden light, beautiful high-end travel photography shot on 4K digital cameras.”
@openai Prompt: “POV video of a bee as it dives through a beautiful field of flowers” This video was generated by our text-to-video model, Sora, without modification. *Sora is not yet available to the public. We’re sharing our research progress early to learn from feedback and give the public a sense of what AI capabilities are on the horizon. #madewithSora #Sora #openai
♬ Tchaikovsky “Waltz of the Flowers” (Excerpt C Edition)(1252263) – LEOPARD
Last month, OpenAI revealed that Sora is capable of generating videos up to one minute in length, “while maintaining visual quality and adherence to the user’s prompt.”
The company, backed by Microsoft and known for causing a sensation last year with its AI-driven ChatGPT chatbot, expressed its decision to share its advancements with Sora prematurely to benefit from user feedback and to offer a glimpse into the future possibilities of AI capabilities.
OpenAI faces criticism after CTO’s interview on Sora
Furthermore, OpenAI mentioned its use of both publicly accessible and licensed datasets to develop Sora. The methodology behind training generative AI models remains a contentious issue, with authors and artists calling for compensation when their works are utilized by AI entities like OpenAI. Several legal actions initiated by creators are currently progressing through the legal system, compelling AI companies to negotiate licensing agreements with major media corporations to ensure a smooth training process for AI technologies.
