With Google upscaling its game with its new AI model Gemini, ChatGPT maker OpenAI is looking to maintain its lead and itself announced a new text-to-video model. After excelling in creating a successful generative AI model with ChatGPT and entering the AI image generation race with DALL-E, CEO Sam Altman has now also stepped into the AI video generation market with Sora. This tool can generate minute-long videos with a simple text prompt empowering users to tap into their creativity. Know all about OpenAI Sora here.
Sora is a new AI model which in Japanese means “sky.” The tool is capable of generating realistic videos with the help of descriptive text prompts. The AI generation video tool is said to create videos of up to 60 seconds enabling users to bring their imagination into reality with just a prompt. OpenAI said, “Sora can generate videos up to a minute long while maintaining visual quality and adherence to the user's prompt.” The Sora website has various examples of the video created by Sora. One of the prompts included a “Photorealistic closeup video of two pirate ships battling each other as they sail inside a cup of coffee.” And Sora created a mesmerizing image of the ships.
We are on WhatsApp Channels. Click to join.
Open AI claims that Sora can create “multiple characters, specific types of motion, and accurate details of the subject and background.” It is designed to understand the difference between what the user has provided and what really exists in the real world.
Sora will be made available to red teamers and visual artists, designers, and filmmakers to assess risk and provide feedback on improving or advancing the AI model. Additionally, OpenAI highlighted that “The current model has weaknesses,” therefore it may struggle to generate a few prompts.
The company is also working on developing safety measures before Sora is available to other OpenAI products. The company will be working closely with experts to create strict guidelines for
Read more on tech.hindustantimes.com