Sora- OpenAI’s video generation model

Source-This post on Sora- OpenAI’s video generation model is based on the article “OpenAI launches Sora: How AI can create videos from a text prompt” published in “The Indian Express” on 17th February 2024.

Why in the News?

OpenAI recently unveiled Sora, an AI model that can produce realistic videos based on text instructions, with a duration of up to one minute. It is a generative artificial intelligence (GenAI) model.

About new OpenAI model Sora

1. Text to Video– The Sora model is capable of producing videos up to one minute in length, ensuring high visual quality and adherence as per the user’s instructions.

2. Generate complex scenes– Sora can generate intricate scenes featuring multiple characters, various types of motion, and precise details of both the subject and the background.

3. Dynamic Impressions- It can understand how objects function in reality, interpret prompts accurately. It can generate engaging characters that convey lively emotions.

4. Multishot Avatar- Sora can also produce multiple shots within a single generated video that accurately persist characters and visual style.

Note– Currently, the Sora model is not available in OpenAI’s products. It will be accessible after all safety checks are completed.

Which other companies have also entered this field?

1. Google’s Lumiere, launched recently , can generate five-second videos based on provided prompts, whether text- or image-based.

2. Additionally, companies like Runway and Pika also have showcased their own noteworthy text-to-video models.

What is generative artificial intelligence (GenAI)?

1. Generative AI uses Artificial Intelligence and Machine Learning algorithms to enable machines to generate new content (machine generated).

2. Systems use previously created content, such as text, audio, video, images, and code.

3. The term ‘Generative’ refers to the ability of the models to learn how to create new data rather than simply recognising it. For example, a generative model may learn how to generate images that resemble faces given a set of parameters (such as the eyes, hair, or skin colour etc.).

UPSC Syllabus- Science & Technology