Shengshu Technology has revealed its latest AI model, the Vidu 1.5. The company aims to venture into the domain of text-to-video and image-to-video generation, bringing a new competitor into the market to compete against the likes of OpenAI Sora, which was announced earlier this year. For someone who is not aware of Shengshu Technology, it’s an emerging AI company that was founded last year in March 2023.
The company’s new AI model is pretty much similar to OpenAI’s Sora, albeit with some tweaks. The Vidu 1.5 has the capability to generate videos up to eight seconds in length from images as well as textual prompts. The AI model uses its in-house multiple-entity consistency feature to seamlessly splice people, objects, and environments while generating a video from user prompts.
There’s also a thing that Vidu called multiple-angle consistency, which allows users to either generate videos using any inputted images or by uploading three photos of a single subject. The AI firm further states that the AI model utilizes advanced control features for adding better motion and detailed backgrounds in the generated output. According to the model maker, you can generate a eight-second video in under 30 seconds.
Vidu has also provided several demonstrations generated by the Vidu 1.5 model. The results are impressive, from a luxury car running through fiery roads to an animated scene of a cute little dragon looking at an apple, the generated videos showcase how Vidu 1.5 brings textual prompts to life. But the catch is that you can only create a maximum of eight-second videos, while its direct competitor, the Sora model, allows you to produce videos up to a minute in length.
Regarding video resolution, Vidu 1.5 boasts the capability to produce videos at a maximum of 1080p resolution. The model has its own imperfections, though. For example, some AI-generated videos lack minor details and reveal some unrealistic movements, such as in a car scene where flames pass through the middle of the car. Although these are not major flaws and not even noticeable until you watch them closely,.
The Vidu 1.5 multimodal AI operates on a freemium model. The free version lets you generate a 4-second clip with speed resolution, while the premium version, which sets you back $9.99/month, allows you to generate 8-second video at up to 1080p resolution. The Vidu 1.5 is now available for everyone via its official website.