|
Listen to this story
|
Social media platform TikTok has recently added an “AI greenscreen” feature that renders text prompts into images. This tool will now enable creators to use abstract images as backgrounds in their videos.
The feature is not yet as sophisticated as other text-to-image applications—for example, Imagen and Midjourney—which are able to render strikingly detailed creations in comparison.
With TikTok’s ever increasing popularity as a social media platform, the use of vague AI-generated images is likely to be seen favourably by its large user base. It is widely believed that the choice to make ‘AI Greenscreen’ simple and surreal is a matter of corporate safety, since TikTok has over a billion users.
TikTok’s adoption of ‘AI Greenscreen’ marks a significant step forward for text-to-image in mainstream media. The latest development for text-to-image AI arguably began in 2021, with the original release of DALL-E by OpenAI. In less than two years, millions of people have gained access to this technology through apps like TikTok.
Experts believe that TikTok’s limitations may require advanced models with greater computing power—which could simultaneously prove expensive and resource-intensive for the company to implement. Moreover, with over a billion users, the tool to create photorealistic images of anything would almost certainly lead to troubling results.
