Move оver, Hollywood: OpenAI’s new AI model, Sora, creates minute-long videos from prompts،
Artificial intelligence is all the rage these days. Major tech giants are in a race to become the best in the AI revolution. Google just released its latest and greatest AI model, the Gemini Ultra 1.0, and rolled out a new Google One AI Premium. Now its main rival, Microsoft-backed OpenAI, is ready to fight back. OpenAI introduces a new video generation model called Sora. According to the company blog post (via Reuters), Sora”can create realistic and imaginative scenes from text instructions.” This new text-to-video conversion template allows users to create photorealistic videos up to one minute long, all based on written prompts.
According to OpenAI, Sora is capable of creating:
Complex scenes with multiple characters, specific movement types, and precise subject and background details. The model includes not only what the user asked in the prompt, but also how those things exist in the physical world.
The model can even produce a video from a single still image, and it is capable of filling in missing frames in an existing video or extending its duration. OpenAI recognizes that the model “may struggle to accurately simulate the physics of a complex scene“, but the results presented are quite impressive. You can check out the shared videos to see for yourself.
Prompt: “A trailer featuring the adventures of the 30-year-old spaceman wearing a red wool knitted motorcycle helmet, blue sky, salt desert, cinematic style, shot on 35mm film , bright colors.” pic.twitter.com/0JzpwPUGPB
-OpenAI (@OpenAI) February 15, 2024
Earlier this month, OpenAI revealed plans to add watermarks to its DALL-E 3 text-to-image conversion tool. However, it mentioned that these watermarks can be easily removed. Like its other AI products, OpenAI will have to deal with the potential repercussions of fake, photorealistic AI-generated videos being mistaken for authentic content.
The company says it is developing tools to identify misleading content, including a detection classifier that can recognize videos generated by Sora.
Not long ago, social media giant Meta improved its Emu image generation model by adding two AI-based features. These features can also edit and create videos from text prompts. It seems the future of AI-generated reels and short videos is getting closer than expected.
