OpenAI releases Sora 2 video model with improved realism and sound effects | Infinium-tech

Openai announced Sora – its video and audio generation model announced. Openai is now presenting the first major update with Sora 2, which can generate more realistic and physically accurate videos with better user control and editing capabilities.

https://www.youtube.com/watch?v=lecg6aj6dvy

Described as “GPT 3.5-Moment”, Sora 2 also brings better sound output with synchronized dialogue and sound effects. Sora 2 is capable of avoiding general problems associated with a pre -video generation model, such as morphing objects and distorting physical reality to meet a signal.

The videos generated will also follow multi-shot instructions and maintain stability in various scenes. Sora 2 supports several video generation styles, including cinematic, realistic and anime.

Openai is also launching a standalone Sora iOS app With an inviting-cavalry system. Sora 2 has several safety measures, including restrictions on using public data in the video generation. Openai also confirmed that users could allow others to create a “cameo” with their equality, but can be canceled by the user at any time in the future.

The initial rollout of Sora 2 begins today and will be limited to the US and Canada. For pricing, Openai confirmed that Sora 2 would initially be independent with “generous boundary” so that the users could detect their abilities.

https://www.youtube.com/watch?v=1paowkvcjp0

Chatgpt Pro Subscribers are getting access to a high-quality Sora 2 Pro model. Openai soon confirmed its plans to release Sora 2 API.

Source