Graphic design platform Canva has introduced an AI-powered feature to generate images based on a text query.
Text to Image is based on the open source Stable Diffusion text-to-image model. The developers have added several additional security filters and a customizable interface.
To use the function, you need to describe the desired image and select one of the styles. At the output, the model will produce a grid of four pictures and add them to the design canvas.
Users can also complain about images that contain violence, nudity, hate speech, and “biased or stereotypical” content.
The feature is available for all plans, including the free one. Users can create up to 100 images per day.
“We strive to present [сообществу] this technology because it’s an emerging field,” Canva co-founder and product director Cameron Adams said in an interview with The Verge.
According to him, the tool is already being used in many areas.
“One of my favorite ways is how students use it to visualize their stories. […]. We also saw him [инструмент] creates images for presentations, flyers and t-shirts that they [пользователи] can print with Canva.” Adams said.
He also noted that the company is investigating copyright issues for images generated by artificial intelligence:
“To some extent, AI products can be considered fair use, and this will vary from country to country. We are closely monitoring the situation.”
Canva launched a beta test of the tool in September 2022. Now the function is available to all 100 million users of the platform.
Recall that in November, the PhotoRoom photo editor learned how to change the background in images using AI.
In October, Shutterstock expanded its partnership with OpenAI to sell stock images generated by the DALL-E 2 model.
Subscribe to Cryplogger news in Telegram: Cryplogger AI – all the news from the world of AI!
Found a mistake in the text? Select it and press CTRL+ENTER
Graphic design platform Canva has introduced an AI-powered feature to generate images based on a text query.
Text to Image is based on the open source Stable Diffusion text-to-image model. The developers have added several additional security filters and a customizable interface.
To use the function, you need to describe the desired image and select one of the styles. At the output, the model will produce a grid of four pictures and add them to the design canvas.
Users can also complain about images that contain violence, nudity, hate speech, and “biased or stereotypical” content.
The feature is available for all plans, including the free one. Users can create up to 100 images per day.
“We strive to present [сообществу] this technology because it’s an emerging field,” Canva co-founder and product director Cameron Adams said in an interview with The Verge.
According to him, the tool is already being used in many areas.
“One of my favorite ways is how students use it to visualize their stories. […]. We also saw him [инструмент] creates images for presentations, flyers and t-shirts that they [пользователи] can print with Canva.” Adams said.
He also noted that the company is investigating copyright issues for images generated by artificial intelligence:
“To some extent, AI products can be considered fair use, and this will vary from country to country. We are closely monitoring the situation.”
Canva launched a beta test of the tool in September 2022. Now the function is available to all 100 million users of the platform.
Recall that in November, the PhotoRoom photo editor learned how to change the background in images using AI.
In October, Shutterstock expanded its partnership with OpenAI to sell stock images generated by the DALL-E 2 model.
Subscribe to Cryplogger news in Telegram: Cryplogger AI – all the news from the world of AI!
Found a mistake in the text? Select it and press CTRL+ENTER
