Grok, the AI chatbot built into X.com, now offers a feature to analyze images. While it works well, the free account limits users to just three uploads, which can be restrictive.
To use this feature on mobile, open the X app, tap the Grok tab (a square with a line through it), and click the + button to upload an image. On a browser, visit X.com, select Grok from the left menu, and use the paperclip button to attach an image. After uploading, users can ask Grok questions about the image.
Image Analysis with Grok
Grok was tested by uploading a cartoon of Odysseus, the Greek king from the Odyssey. It recognized him accurately from the cartoon’s style and could even recreate the image by following prompts like “redo the image but make it of a cartoon woman instead.”
This ability to analyze and recreate images is useful, but not unique to Grok, as ChatGPT can do something similar. What sets Grok apart is its ability to extract and understand text in images.
Analyzing Text in Images
A flyer for a local fitness class was uploaded to test Grok’s ability to read text. It successfully extracted all the text and even provided clickable links to web addresses, although it missed an Instagram account link, which was also not picked up by ChatGPT.
A timetable for a local martial arts gym was uploaded to check if Grok could identify a BJJ class on Thursdays. Grok responded perfectly: “Yes, there is a BJJ class on Thursday at 7:00 AM (BJJ Gi for Adults & Teens) and at 8:00 PM (BJJ No Gi for Adults & Teens).”
Grok’s ability to interpret and respond to text in images makes it more helpful for people who struggle with processing visual data.
Limitations of Grok
One drawback is that Grok’s free usage limit on image uploads is quickly reached—just three uploads per day. This is also the case with ChatGPT’s free tier. However, Grok shines in areas like analyzing academic text. When a screenshot of a PDF was uploaded and Grok was asked to summarize it, it provided a structured answer with headings like “Research findings” and “Historical context,” offering more detailed insights than ChatGPT’s general summary.
Grok vs ChatGPT
While Grok may be ahead in analyzing text and images in some cases, the limited number of uploads per day on the free tier makes it less practical for frequent use. Still, Grok is a powerful tool for analyzing images, and its ability to extract and interpret text makes it a solid option for those who find this feature useful.
