sb.scorecardresearch

Published 16:07 IST, December 11th 2024

OpenAI’s Sora Text-to-Video Generator Based on Feedback From Indian Artists

The new Sora model enables users to generate videos up to 1,080 pixel resolution, up to 20 seconds long, and in widescreen, vertical or square aspect ratios.

Follow: Google News Icon
  • share
OpenAI Sora
OpenAI has released the Sora model for public use. | Image: Image: OpenAI

Artificial intelligence major OpenAI used feedback from artists and creatives globally, including Indians, to develop its text-to-realistic video generation platform Sora, the company said on Wednesday.

OpenAI has rolled out Sora, which can generate realistic video from text, across majority of markets, including India.

"Since sharing our research preview of Sora earlier this year, we've worked with artists and creatives worldwide, including in India, drawing on their feedback to develop a new and significantly faster version of the model.  India has a world-famous community of creatives, artists, and filmmakers, and we're excited to see the new ways they create using Sora," an OpenAI spokesperson said.

The model enables users to generate videos up to 1,080 pixel resolution, up to 20 seconds long, and in widescreen, vertical or square aspect ratios.

OpenAI is offering Sora as part of ChatGPT Plus account at no additional cost.

"You can generate up to 50 videos at 480p resolution or fewer videos at 720p each month. For those who want more Sora, the Pro plan includes 10x more usage, higher resolutions, and longer durations. We're working on tailored pricing for different types of users, which we plan to make available early next year," OpenAI said in a blog.

OpenAI has blocked use of Sora for damaging forms of abuse, including child sexual abuse materials and other sexual deepfakes.

"We are blocking particularly damaging forms of abuse, such as child sexual abuse materials and sexual deepfakes. Uploads of people will be limited at launch, but we intend to roll the feature out to more users as we refine our deepfake mitigations," the blog said.

The AI platform has embedded technology in Sora to identify if a video is coming from Sora to provide transparency and it can be also used to verify the origin, the blog said.

"While imperfect, we have added safeguards like visible watermarks by default, and built an internal search tool that uses technical attributes of generations to help verify if content came from Sora," the blog said. 

Updated 16:07 IST, December 11th 2024