xAI debuts new AI video generation model, Grok Imagine 1.0 on X

Elon Musk’s xAI has launched a new AI generative video model dubbed Grok Imagine 1.0 on X (formerly Twitter), empowering users to create refined AI videos. The updated video model is said to generate high-quality videos with improved audio output while also being cost-effective. The launch of a new AI video model comes at an odd time, considering the platform is facing backlash for its AI image generator tool.

The Grok Imagine 1.0 will generate AI videos of up to 10 seconds at 720p resolution and audio. The model will enable users to transform text or static images into a dynamic video with motion and visual harmony.  

For audio, it uses multimodal AI to generate and sync native audio automatically. xAI said, “Experience stories that unfold fully. Sharper detail and smoother motion that draws you deeper into the scene. Videos are now longer and higher resolution.” In terms of performance, the company claims that the new video generation model comes with optimised latency, concurrency, and cost.

Alongside the Grok Imagine 1.0 model, the tech giant has also launched the Grok Imagine API that combines the ability of video and audio generation, and video editing. Therefore, users can add, remove, and swap objects seamlessly within a video's frame. It also enables users to adjust scenes, color and objects, and more.

As per the xAI press note, the early benchmarks showcase that the model outperforms competitors like OpenAI's Sora and Google's Veo in processing speed and cost for short-form content.

xAI can integrate Grok Imagine into partnered apps or tools. Developers can also get access to Grok Imagine1.0 and the API directly through xAI’s official API and SDKs.

The new launch comes at a critical juncture for xAI, since its AI image generator is facing public and regulatory scrutiny over safety safeguards. Furthermore, the company remains under investigation by global regulators for the generation of non-consensual deepfakes.