[ad_1]
New Delhi. OpenAI, the company behind ChatGPIT, has launched Sora, a new text-to-video model that can create videos of up to one minute while maintaining visual quality and following user prompts. Sora is a model that takes a video and transforms it by gradually removing noise from the video in several steps. The company said, ‘Sora is capable of creating an entire video at once or lengthening the generated video.’
In addition to being able to produce a video from just text instructions, the model is also able to take an existing still image and combine the image content with accuracy and attention to the smallest details to produce a video.
Also read- Before handing over the phone to children, turn on these settings, they will remain safe online, adult content will not be visible!
Similar to the GPT model, Sora uses a Transformer architecture, which unlocks better scaling performance. The company said it is making Sora available to red teamers (domain experts) to assess critical areas for damage or risk.
OpenAI said in a statement, ‘We are providing access to a number of visual artists, designers and filmmakers to receive feedback on how to advance the model to be most useful to creative professionals.’
Also read: When should the phone be put on charging, at 15%, 30% or 50%? Even those who have been using mobile phones for years have been making mistakes.
Sora will be able to generate complex scenes with multiple characters, a variety of motion, and precise background details. According to OpenAI, ‘The model not only understands what the user asked for in the prompt, but also how those things exist in the physical world.’
Sora can also create multiple shots within a single generated video that accurately maintains the characters and visual style. However, the company admitted that the current model has its own weaknesses. The company said that it will take necessary security steps before making Sora available in open AI products.
The company said, ‘We are working with Red Teamers domain experts in areas like misinformation, hate content and discrimination who will test the model. We’re also building tools to help detect misleading content, such as a detection classifier that can tell when a video was created by Sora.’
,
Tag: Artificial Intelligence, Mobile phone, technology news
first published : February 17, 2024, 13:44 IST
[ad_2]
