OpenAI Unveils Sora: AI Model for Text-to-Video

OpenAI introduces Sora, an AI model for creating videos from text, joining the race with ByteDance and Meta in generative AI video production.

On Monday, it said it had started giving the public access to an AI model that can make videos from text prompts. This puts the company among the many attempting to transform the production of films and TV shows through generative AI.

OpenAI’s Sora, launched earlier this year, will compete with the Firefly Video Model technology. As of late, ByteDance, the company that owns TikTok and Meta Platforms have both announced their video tools.

Adobe has bet its future on training models with data it owns, so the results can be legally used in business. This is because Adobe has much bigger competitors. Based in San Jose, California Adobe didn’t say when the tool would be available for everyone. They did say that people on a waiting list would be able to start using it.

PepsiCo’s Gatorade will use Adobe’s image generation model for a website where customers can order customized bottles, the company announced on Monday. Mattel has also been using Adobe tools to help design the boxes for its Barbie dolls.

Adobe’s CTO Highlights User-Friendly Video Tools

Ely Greenfield, the chief technology officer for digital media at Adobe, stated that the company designs its video tools to be user-friendly for video editors and creators daily. They have put a lot of thought into how to make the footage look like regular footage.

“We focus on fine-grain control, teaching the model the concepts that video editors and videographers use things like camera position, camera angle, and camera motion,” Greenfield told Reuters in a chat.