Grok AI will bring generative image feature confirms xAI

A number of new changes are coming to xAI’s Grok Large Language Model (LLM) including the generative image feature. This capability is now popularized in generative AI platforms with increasing accuracy.

xAI team member Toby Pohlen shared new updates on Grok LLM and its future developments. An X social media user @Alice_Team9 asked “Would be amazing to have an ability to generate images with Grok inside the X app. Do you plan to implement that?” Pohlen replied “Yes”. That’s a brief answer and confirms that Grok could have this feature onboard. However, there’s no release data available.

Generative AI image generation technology relies on machine learning. It uses algorithms to learn patterns from image data and create new images based on those learned patterns. Through a UI, the AI Image generation tool allows users to enter an image description and generate images.

This field is currently dominated by two companies – OpenAI and Midjourney. OpenAI has its Dall-E tool and Midjourney goes by the same name. Both of these have generative Image creation features. Other companies are also catching up including Google but its recent experiment with Gemini started generating incorrect images. The company has yet to fix and resume this feature for public users.

Grok, on the other hand, is in the initial stage of building image data comprehension. In April, xAI announced Grok-1.5V, its first-gen multimodal model. It can process a range of visual information including documents, diagrams, charts, screenshots, and photographs.

Grok-1.5V will allow users to ask for a description of these properties (above mentioned) by just pasting an image or related files. This multimodal will also help expand Grok’s image data comprehensive capability and lead it to create images in the near future.

Grok 1.5V is currently under testing by some partners and xAI is developing a conversational UI for this model. A release date is yet to be decided.