You might want to open TikTok if you’re still on the waiting list to sample DALL-E and want a short glimpse at the kind of technology that makes it possible.
Although TikTok’s most recent filter has been available for a few days, we only recently became aware of its new A.I. on Sunday, a text-to-image generating filter. Its name is AI Greenscreen, and it creates visuals in a painterly style from the words you enter. Additionally, the graphics you create could be used as a green screen for the background of your TikTok films.
But the similarities between DALL-E and TikTok’s AI Greenscreen filter end at the ability to enter words to create art. The latter does produce art, but it is nowhere close to the same level of superiority as DALL-E. If you appreciate watercolor-y, Impressionist-style art, the images produced by TikTok’s filter are still reasonably aesthetically beautiful. However, they don’t always provide clear graphics that exactly match your words.
The introduction of the new filter coincides with the rise in popularity of text-to-image AI generators, particularly since the release of OpenAI’s DALL-E 2. It’s important to note that the images TikTok’s AI generator generates pale in comparison to the results of well-known text-to-image models like Google’s Imagen and DALL-E 2. While DALL-E 2 and Imagen can produce photorealistic visuals, TikTok’s model only creates abstract images.
It is indeed likely that TikTok purposely constrained its model to ensure that the material it produces complies with the community standards for the app, such as those concerning nudity and graphic content. If the model utilized by TikTok were as intricate and photorealistic as those used by DALL-E 2 or Imagen, some people would undoubtedly use it to produce unsettling stuff. To prevent these problems, TikTok might have chosen an abstract model.
When you choose the effect, TikTok offers several suggested prompts, such as “Snorkeling in a purple ocean,” “Hidden village in the mountains,” and “Erupting rainbow volcano,” which illustrate the app’s emphasis on abstract imagery for its text-to-image AI generator. You can experiment with your own questions to generate comparable ambiguous visuals.
Here’s a guide on how to generate it:
Step 1: First, launch the TikTok app and click the plus symbol.
Step 2: The Effects icon may be found to the left of the sizable red record button .
Step 3: Select the purple AI symbol from the Effects menu. The magnifying glass icon can also be used to locate the effect. Use the search term “AI Greenscreen” after that.
Step 4: Here on AI Greenscreen effect screen, in the text box below the phrase Enter a few phrases, type the words you wish to use to create art. Alternately, you might make use of any of the phrases TikTok suggests in that text field. Simply choose the To produce knob if you choose the latter. Enter your phrase and select the To generate knob if you choose the first option.
Step 5: After the image has loaded for a little while, you may use it as a green screen backdrop for a TikTok video.