Pinterest has unveiled Canvas AI, an artificial intelligence (AI) project designed to improve product visualization strategies. Specifically, as detailed at the VB Transform conference, it is a new tool that allows brands to change the background of product photos without altering the representation of the product, offering “a unique opportunity to revitalize their marketing strategies.”

Canvas uses AI to integrate products into various digital backgrounds without compromising product integrity, creating a more engaging display. This advancement broadens brands' creative horizons and enhances consumers' overall shopping experience by helping them visualize how the product would fit into different scenarios and backgrounds.

Anthony Suarez, senior director of developer enablement at Pinterest, was on hand to introduce Canvas: “Early on, we assumed that the pace of innovation would require us to adapt and evolve what we build to keep up with a changing landscape,” explained Suarez.

Canvas distinguishes itself from other text-to-image models by enhancing existing images rather than generating new ones from scratch. This approach aligns perfectly with Pinterest's core mission to inspire users through visual discovery. 

The new tool is easy to use, even with basic user commands. In fact, it transforms existing concepts, products, or goods into new insights using Pinterest's extensive database of product images. It aims to engage users by promoting creativity and offering diverse visual experiences.

Canvas uses a segmentation model to generate product masks and identify the foreground from the background.

Pinterest aims at provide a better visual experience 

In addition, it uses visually dominant large language models for full captions and trains all UNet layers using a select set of product images with high user interaction. This improves pattern recognition in user preferences, leading to more dynamic results.

In addition, Canvas uses product-to-plot ratios to guide the distribution of spatial attention. By focusing on meaningful details, this feature increases the system's responsiveness and leads to a more personalized user experience. Continuous learning fed back into the model during iterative system training strengthens the accuracy of product feature identification and improves overall performance and accuracy.

Canvas's primary goal is to repurpose existing Pin images into dynamic backgrounds, giving brands the freedom to choose any aesthetic that aligns with their brand image. Brands can enter descriptors, and the system generates potential backgrounds for their product photos that resonate with those style requirements.

Pinterest expects the successful implementation of this model to diversify Pins images and enhance the appeal of products in various patterns and design styles.

The post Pinterest has unveiled Canvas AI appeared first on Cross-Border Magazine.

OpenAI introduces a Canva plug-in for its popular chatbot, ChatGPT. This integration seeks to improve how users generate images by offering a simplified and easy-to-use approach to digital design.

Previously, using Canva with ChatGPT required manual work, but with the new plug-in, users can generate visualizations with just a few clicks. This makes the design process more efficient.

To access this feature, users must launch ChatGPT in their browser and look for the 'Add-on Store' in the add-on section. Once installed, Canva must be selected from the add-ons section in the main chatbot window. 

ChatGPT AI will help create faster, more accurate images 

In the prompts box, it will be possible to describe the visualization we want to create using prompts such as, "I'm an AI enthusiast active on Twitter. Create a banner for my account." This action generates a list of images from which users can select their preferred option, edit it in Canva, and download it directly. 

This integration is exclusive to ChatGPT Plus subscribers, who pay a monthly fee of $20. In addition to the Canva add-on, users will be able to gain access to the updated GPT-4 large language model, which is proficient in creating long-form content and accepting images as input.

The ‘Anti-Canva’ AI 

Microsoft Design is an online application that allows users to create quick and instant designs based on AI, and it is Microsoft ‘Anti-Canva’ app. The idea is to create the ultimate design tool that won’t require any design knowledge to use it.

The way to use it is straightforward and supports Spanish, French, Italian, and many other languages. We simply enter a "prompt," which describes the type of image we want, how we want it, and the idea we have in our head. The more descriptive this message is, the easier it will be for the AI to understand us and adapt to our tastes and requests. 

Obviously, if we ask for something very generic, it will be less interesting. The good thing is that after the work of the AI, we can customize this creation to our liking through a simple system of adjustments.

The post OpenAI introduces a Canva plug-in appeared first on Cross-Border Magazine.

Canva enters the world of Artificial Intelligence (AI). The simplified graphic design platform has recently held its virtual event Canva Create 2023, where they have presented all the new features it will incorporate. 

The tools that have attracted the most attention are those that use AI to facilitate the work of designs and its new Brand Hub to facilitate the creation of brand designs.

The Canva Visual Suite has transformed; from now on, we will find many more features to facilitate our tasks when designing with the platform. Some of the new features are:

One of the first new features we can see is Assistant, which will be like our personal assistant within the platform, as it will give us quick access to functions and help us find ideas for our designs. The recommendations will be based on our style and existing designs. In addition, it stands out for giving us quick access to AI functions.

Images are a key element in our designs, and Canva wants to make it easier for us to find the perfect photo. Magic Edit (or Magic Editor) allows you to add or replace any element within an image. And with Magic Eraser, you can remove unwanted distractions with a magic brush.

On the other hand, with Magic Design, you can upload an image, and instantly the platform performs a series of designs with it by choosing fonts, photographs, graphics, and styles, to get the perfect design. 

Afterward, the user can choose the design they like the most and download it. It can be used for everything, whether for making billboards or birthday cards. It can also be used to create attractive presentations easily; ask it to create various presentations with an outline and content.

Canva AI for drawing… and writing 

Now you can also use its Draw tool to draw your ideas and sketch your designs. It offers various brushes that allow you to change color and select weight to make the best freehand designs. 

Integrated into this tool is the Shape Assitant solution that will help you perfect your designs. 

Canva will have a translator who can translate a complete design into another language in a few simple steps. You can find more than 100 languages to translate your designs.

Not only have they developed new features for images, AI will also be present in Canvas video editor with its Beat Sync tool that allows you to choose a soundtrack and adapt the video to the rhythm of the music.

Last year Canva launched Magic Write for Canva Docs; seeing the good reception it has had in the community and the use that was being given, have announced that now Magic Write (Magic Writing) can be used throughout the Visual Worksuite, that is, it will be present on websites, presentations, social networks, whiteboards and more, to write texts easily and quickly. 

For example, you can ask it to make a text on a specific topic or to give us ideas to write in our blog. In addition, it is available in 18 languages, making this generative AI tool one of the first to be available worldwide.

Text-to-image functionality 

Text to Image is another new tool. The AI allows you to transform what you type into an image.

Apart from these tools, the company has added other new features such as:

"Styles" allows users to search for suggested color palettes and fonts.

"Layers" to view all elements in one place, including text, shapes, images, and video.

"Alt Text" can provide additional context to images and elements to describe them for people with visual impairments or accessibility needs.

"Fonts" have added 953 new fonts, including Arial, Courier, Helvetica, and Times New Roman.

"Gradients" add depth and character to your design with customizable gradients.

The post Canva enters the world of AI appeared first on Cross-Border Magazine.