OpenAI unveils its text-to-video generator called ‘Sora’
We’ve gotten to the point where AI can create entire productions without any human intervention. If you thought things were looking realistic before, just wait until you see what OpenAI just unveiled. According to sources, OpenAI just showed off a new text-to-video generator called Sora, and it may fool some people.
AI technology seems to be taking major steps, as Google just unveiled its new model called Gemini 1.5. This is the new model from the company that improves upon Gemini 1.0 in several ways. It greatly increased the context window along with improvements. It’s currently rolling out for early testing.
OpenAI unveiled its text-to-video generator called Sora
You’ve probably already seen the video of a young couple walking along a snowy path in Japan. Only, there’s no couple and there’s no snowy path. Every frame of this video was generated by AI. To the average Joe, this would look like a typical drone video. Everything in it is extremely realistic.
This is called Sora, and it’s set to take AI video generation to the next level. It’s able to take text-based prompts and convert them into videos up to one minute long. The output looks hyper-realistic, albeit with several instances of AI jankiness. However, the jankiness is so minimal that you’ll need to scrutinize just about every detail in order to spot it. It’s not like the famous Will Smith Eating Spaghetti video that surfaced last year.
In case you’re wondering, no, you can’t get your hands on it and start popping out videos. Right now, Sora is only available to a set of red-teamers within the company, so it’s not available to the public. The company is planning on distributing this tool to artists, filmmakers, and designers for feedback. We’re not sure when OpenAI is going to bring this tool to the public.
The threat is obvious
Many of the examples that are shown off on the OpenAI site have some sort of AI tell like hands deforming, objects disappearing, and whatever the heck is going on with the example of a team of people digging up a chair.
Obviously, this poses a huge threat to filmmakers. The site has a section talking about how the company plans to use this technology safely, but it’s hard to take any AI company at its word with all that’s happened so far. It’s tough to know how many filmmakers are going to lose their jobs or how much misinformation is going to float around after this. We’re just going to have to wait and see.
We’ve gotten to the point where AI can create entire productions without any human intervention. If you thought things were looking realistic before, just wait until you see what OpenAI just unveiled. According to sources, OpenAI just showed off a new text-to-video generator called Sora, and it may fool some people.
AI technology seems to be taking major steps, as Google just unveiled its new model called Gemini 1.5. This is the new model from the company that improves upon Gemini 1.0 in several ways. It greatly increased the context window along with improvements. It’s currently rolling out for early testing.
OpenAI unveiled its text-to-video generator called Sora
You’ve probably already seen the video of a young couple walking along a snowy path in Japan. Only, there’s no couple and there’s no snowy path. Every frame of this video was generated by AI. To the average Joe, this would look like a typical drone video. Everything in it is extremely realistic.
This is called Sora, and it’s set to take AI video generation to the next level. It’s able to take text-based prompts and convert them into videos up to one minute long. The output looks hyper-realistic, albeit with several instances of AI jankiness. However, the jankiness is so minimal that you’ll need to scrutinize just about every detail in order to spot it. It’s not like the famous Will Smith Eating Spaghetti video that surfaced last year.
In case you’re wondering, no, you can’t get your hands on it and start popping out videos. Right now, Sora is only available to a set of red-teamers within the company, so it’s not available to the public. The company is planning on distributing this tool to artists, filmmakers, and designers for feedback. We’re not sure when OpenAI is going to bring this tool to the public.
The threat is obvious
Many of the examples that are shown off on the OpenAI site have some sort of AI tell like hands deforming, objects disappearing, and whatever the heck is going on with the example of a team of people digging up a chair.
Obviously, this poses a huge threat to filmmakers. The site has a section talking about how the company plans to use this technology safely, but it’s hard to take any AI company at its word with all that’s happened so far. It’s tough to know how many filmmakers are going to lose their jobs or how much misinformation is going to float around after this. We’re just going to have to wait and see.
Denial of responsibility! Techno Blender is an automatic aggregator of the all world’s media. In each content, the hyperlink to the primary source is specified. All trademarks belong to their rightful owners, all materials to their authors. If you are the owner of the content and do not want us to publish your materials, please contact us by email – [email protected]. The content will be deleted within 24 hours.