{"id":46926,"date":"2022-08-16T10:41:41","date_gmt":"2022-08-16T10:41:41","guid":{"rendered":"https:\/\/harchi90.com\/tiktok-rolls-out-a-basic-in-app-text-to-image-ai-generator-techcrunch\/"},"modified":"2022-08-16T10:41:41","modified_gmt":"2022-08-16T10:41:41","slug":"tiktok-rolls-out-a-basic-in-app-text-to-image-ai-generator-techcrunch","status":"publish","type":"post","link":"https:\/\/harchi90.com\/tiktok-rolls-out-a-basic-in-app-text-to-image-ai-generator-techcrunch\/","title":{"rendered":"TikTok rolls out a basic in-app, text-to-image AI generator \u2013 TechCrunch"},"content":{"rendered":"
\n
\n\t\t\t\n\t\t<\/div>\n<\/p><\/div>\n
\n

TikTok has rolled a new in-app text-to-image AI generator that lets users type in a prompt and receive an image that can be used as the background in their videos. The effect is called \u201cAI greenscreen\u201d and can be accessed via the short-form video app’s camera screen. The new effect was first spotted by The Verge.<\/p>\n

The launch of the new filter comes as text-to-image AI generators are becoming increasingly popular, especially with the launch of OpenAI’s DALL-E 2. It’s worth noting that the images that TikTok’s AI generator produces are quite basic when compared to the output from notable text-to-image models, including DALL-E 2 and Google’s Imagen. TikTok’s model produces abstract imagery, whereas DALL-E 2 and Imagen are able to create photorealistic imagery.<\/p>\n

\"TikTok's<\/p>\n

Image Credits:<\/strong> Screenshots\/TechCrunch<\/p>\n<\/div>\n

It’s possible that TikTok may have intentionally limited its model in order to ensure that the content it creates adheres to the app’s community guidelines, including those around nudity and violent imagery. If TikTok’s model was as complex and photorealistic as DALL-E 2 or Imagen, it would surely be used by some users to create disturbing content. TikTok may have opted for an abstract model to avoid such issues.<\/p>\n

TikTok has a number of suggested prompts that appear when you select the effect, including \u201cSnorkeling in a purple ocean,\u201d \u201cHidden village in the mountains\u201d and \u201cErupting rainbow volcano.\u201d These prompts visualize TikTok’s focus on abstract imagery for its text-to-image AI generator. You can play around with your own prompts to get similar abstract imagery.<\/p>\n

\"TikTok's<\/p>\n

Image Credits:<\/strong> Screenshots\/TechCrunch<\/p>\n<\/div>\n

However, if your prompt includes nudity or violent wording, you’ll see that the model will output abstract imagery with appropriate colors and themes, but nothing clear enough to warrant censorship due to the app’s community guidelines.<\/p>\n

As of now, the filter is being used for a few TikTok trends, including one where you enter your name into the generator to see what your \u201caesthetic\u201d looks like. Another trend sees users entering their birthday into the generator. And of course, some users are unsuccessfully looking to see if the generator will recreate specific body parts.<\/p>\n

Since the new filter puts a text-to-image AI generator in the hands of millions of users, it’s not exactly surprising that it has limitations. The company seems to be positioning it as a fun way to create backgrounds for your TikToks, as it could be a useful tool for creators. Given that DALL-E 2 and Imagen aren’t widely available yet, TikTok’s new effect offers an alternative for users who are looking to have a little fun with text-to-image AI generators.<\/p>\n<\/p><\/div>\n","protected":false},"excerpt":{"rendered":"

TikTok has rolled a new in-app text-to-image AI generator that lets users type in a prompt and receive an image that can be used as the background in their videos. The effect is called \u201cAI greenscreen\u201d and can be accessed via the short-form video app’s camera screen. The new effect was first spotted by The …<\/p>\n

TikTok rolls out a basic in-app, text-to-image AI generator \u2013 TechCrunch<\/span> Read More »<\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"site-sidebar-layout":"default","site-content-layout":"default","ast-global-header-display":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","theme-transparent-header-meta":"","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","spay_email":"","jetpack_publicize_message":"","jetpack_is_tweetstorm":false,"jetpack_publicize_feature_enabled":true},"categories":[4],"tags":[],"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack-related-posts":[{"id":46817,"url":"https:\/\/harchi90.com\/tiktok-now-offers-a-very-basic-text-to-image-ai-generator-directly-in-the-app\/","url_meta":{"origin":46926,"position":0},"title":"TikTok now offers a very basic text-to-image AI generator directly in the app","date":"August 16, 2022","format":false,"excerpt":"Text-to-image AI systems are booming in both ability and popularity right now, and what better proof than their appearance in the world's hottest app: TikTok. The video platform recently added a new effect it calls \u201cAI greenscreen\u201d that allows users to type in a text prompt that the software will\u2026","rel":"","context":"In "Technology"","img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":41101,"url":"https:\/\/harchi90.com\/how-to-create-synthetic-ai-art-with-midjourney\/","url_meta":{"origin":46926,"position":1},"title":"How to Create Synthetic AI Art With Midjourney","date":"August 10, 2022","format":false,"excerpt":"Midjourney \/ Benj Edwards AI-based image generators like DALL-E 2 have boomed in popularity. People love to enter bizarre prompts and see what gets spit out. Midjourney is one of the more advanced tools for this, and you can try it now. What Is Midjourney? Before we talk about Midjourney,\u2026","rel":"","context":"In "Technology"","img":{"alt_text":"A wizard in a hall of computers.","src":"https:\/\/i0.wp.com\/www.howtogeek.com\/wp-content\/uploads\/2022\/08\/MidJourney-wizard-hall.jpg?resize=350%2C200&ssl=1","width":350,"height":200},"classes":[]},{"id":21202,"url":"https:\/\/harchi90.com\/ai-image-generator-dall-e-is-now-available-in-beta\/","url_meta":{"origin":46926,"position":2},"title":"AI Image Generator DALL-E is Now Available in Beta","date":"July 21, 2022","format":false,"excerpt":"SpongeBob's House created by DALL-E OpenAI has made DALL-E, the artificial intelligence (AI) image generator, available as a beta and also unveiled the tool's pricing structure. The company has announced that the AI \u200b\u200bsystem, which can create realistic images and art from a text prompt, will soon be available to\u2026","rel":"","context":"In "Technology"","img":{"alt_text":"DALLE2 images","src":"https:\/\/i0.wp.com\/petapixel.com\/assets\/uploads\/2022\/07\/DALLEcopy-800x420.jpg?resize=350%2C200&ssl=1","width":350,"height":200},"classes":[]},{"id":29542,"url":"https:\/\/harchi90.com\/creepy-dall-e-ai-asked-to-predict-last-selfie-taken-on-earth-and-its-horrifying\/","url_meta":{"origin":46926,"position":3},"title":"Creepy DALL-E AI asked to predict last selfie taken on Earth and it’s horrifying","date":"July 29, 2022","format":false,"excerpt":"A TIKTOK account dedicated to asking artificial intelligence disturbing questions revealed what DALL-E AI thinks the last selfie on Earth would look like. Aptly named \"Robot Overloards\" the TikTok account promises \"daily disturbing AI-generated images\". 2DALL-E AI predictions for the last selfie ever taken are horrifyingCredits: TikTok 2Each generated image\u2026","rel":"","context":"In "Technology"","img":{"alt_text":"DALL-E AI predictions for the last selfie ever taken are horrifying","src":"https:\/\/i0.wp.com\/www.the-sun.com\/wp-content\/uploads\/sites\/6\/2022\/07\/NINTCHDBPICT000750103513.jpg?resize=350%2C200&ssl=1","width":350,"height":200},"classes":[]},{"id":45867,"url":"https:\/\/harchi90.com\/open-source-rival-for-openais-dall-e-runs-on-your-graphics-card\/","url_meta":{"origin":46926,"position":4},"title":"Open-source rival for OpenAI’s DALL-E runs on your graphics card","date":"August 15, 2022","format":false,"excerpt":"Image: Stable Diffusion Der Artikel kann nur mit aktiviertem JavaScript dargestellt werden. Bitte aktiviere JavaScript in deinem Browser und lade die Seite neu. OpenAI's DALL-E 2 is getting free competition. Behind it is an AI open-source movement and the startup Stability AI. Artificial intelligence that can generate images from text\u2026","rel":"","context":"In "Technology"","img":{"alt_text":"","src":"https:\/\/i0.wp.com\/mixed-news.com\/en\/wp-content\/uploads\/2022\/08\/Stable-Diffusion-V1-Merged-Title-860x344.jpg?resize=350%2C200&ssl=1","width":350,"height":200},"classes":[]}],"fifu_image_url":"https:\/\/techcrunch.com\/wp-content\/uploads\/2022\/04\/GettyImages-1231203702.jpeg?w=600","_links":{"self":[{"href":"https:\/\/harchi90.com\/wp-json\/wp\/v2\/posts\/46926"}],"collection":[{"href":"https:\/\/harchi90.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/harchi90.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/harchi90.com\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/harchi90.com\/wp-json\/wp\/v2\/comments?post=46926"}],"version-history":[{"count":0,"href":"https:\/\/harchi90.com\/wp-json\/wp\/v2\/posts\/46926\/revisions"}],"wp:attachment":[{"href":"https:\/\/harchi90.com\/wp-json\/wp\/v2\/media?parent=46926"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/harchi90.com\/wp-json\/wp\/v2\/categories?post=46926"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/harchi90.com\/wp-json\/wp\/v2\/tags?post=46926"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}