MediaTek’s Text-to-Image AI tool is MIND BLOWING (Hands-On)

It’s been a week since MWC 2024 concluded, and while there were a lot of interesting products and innovations on the showfloor this year, it’s impossible to cover them all in one go. However, one demo that left me jaw-dropped (and has stayed on my mind since the last day of the show) is the MediaTek’s Text-to-AI Image generation tool showcased at their booth.

At MWC, MediaTek demonstrated their SDXL Turbo AI engine, which transforms text into images. While AI models converting text to images aren’t new, what’s remarkable about this tool is that this engine operates offline and on-device. The engine shown in the video below is running on a prototype device with the Dimensity 9300 chipset at its heart and the device isn’t connected to the internet.

The AI engine is so powerful that it can turn text into images almost in real-time (with a response time of less than 1 second for each prompt and text input). In the video, the initial image generated from my prompt was already impressive, showing a cat wearing a hat while eating cheese. What’s even more surprising is how quickly the image changes as I alter the prompt.

This is something that not even powerful online tools are able to do. Popular AI services like ChatGPT and Google Gemini also offer text-to-image tools, but MediaTek goes a step further by providing the tool on its chipset, and it works offline. While it’s not flawless — for example, it struggles with prompts containing more than two characters — the engine shows promise.

Now, before you get too excited, it’s important to note that this is just a demo for now, and MediaTek hasn’t mentioned if or when it’ll be available on smartphones with the Dimensity 9300 chip. We’ll keep you posted as we learn more. In the meantime, we’d love to hear your thoughts on MediaTek’s text-to-image tool. How do you think it could be useful in your daily life? Share your thoughts in the comments below!