Napkin AI wants you to stop using so many words in your PowerPoints and Google Slides.
Napkin is a text-to-visual AI tool that lets you upload text to a blank document or “napkin” and it will generate a visual representation of your information. Napkin is one of numerous AI startups that emerged as generative AI technology advanced with chatbots like ChatGPT and image generators like Midjourney. It’s not a data visualization tool – you can’t upload an Excel database and get bar and pie charts. But you can use Napkin to create graphics for presentations, blog posts, reports, and school assignments, among other things.
Napkin officially launched in August, but my colleague and I grabbed a demo from its founder, Pramod Sharma. Sharma has worked at Google for much of his career, particularly on the Docs team, and that influence is evident in the way Napkin looks and works. Sharma described Napkin as a “visual Google Docs editor,” with the goal of letting users experience the “art of making things fun and enjoyable.” Napkin is currently available in English, and today announced that it will soon support German, French, Japanese, and Chinese.
There are many different graphic design and visual creation programs available, but giants like Adobe and Canva make up a large portion of the market. Both are also investing in AI-powered tools, including image generators like Firefly and Magic Media, with varying degrees of success. I’ve used and reviewed many AI creative services, and after using Napkin, I think there’s a place for it among these competitors.
The best thing about Napkin is that it’s easy to use and can quickly create graphics. It’s great for quickly improving a presentation or adding extra flair to a report. Students, small businesses, and other creatives who don’t want to spend time (or money) using advanced services will benefit from Napkin’s stripped-down efficiency.
Here are three of the best ways I’ve found to use Napkin. And if you create an account now while it’s still in beta, you’ll get more personalization options for free.
Spice up presentations
In my test of Napkin, I had it create graphics to enhance presentation slides, break down a complicated topic for an article, and come up with different visual ideas. Napkin was good for all of the above tasks, but it was by far the best program for adding the finishing touches to a presentation.
A general rule of thumb when creating presentation slides is to have as few words on the slides as possible. This is where Napkin can help. You can upload a block of text to Napkin, which will then be shortened and turned into a visually appealing graphic that you can copy and paste onto your slide.
It only takes 10 to 30 seconds to generate. Napkin collects and anonymizes users’ data and interactions with its AI for training purposes, but Sharma confirmed via email that your personal information will remain confidential and your uploaded text will not be used to generate content for other users. As with any AI service, I caution against uploading sensitive information to the site.
I pulled an old presentation from a film class in college to test. My original slide was wordy and had seven long bullet points. Napkin created really unique graphics, including a pro/con list that I really liked and a more artistic representation that summarized my main point of the slide, which was that Netflix’s original movies suck. I recreated the slide with the new graphics to compare and it’s now much easier to digest than rolling your eyes at a big block of text.
The new version (below) is much easier to read than the original (above).
I used a few other slides from presentations, including drier ones explaining various communication theories and summaries of various novels. Each time, Napkin provided graphics that made my slides not only more entertaining but also easier to understand. I made a few changes to make my points clearer, but for the limited amount of text I took out of the context of the entire presentation, Napkin did well. One thing I would have liked is the ability to customize my graphics to exactly match the colors of my deck theme, but for now, this was fine.
Breaking down complicated topics
If you’re not that familiar with graphic design strategies, you can use Napkin as a brainstorming tool. During my testing, I found it to be very creative and versatile, allowing you to try out many different options based on the same text. To put its creativity to the test, I had Napkin create four different graphics to explain the concept of the Fediverse, a set of interconnected, decentralized social media platforms built on a set of rules called ActivityPub protocols. I have a whole article explaining what that is, but I wanted to see what Napkin could come up with to break down a complicated topic. These are some of the best options.
These are three of the graphics created by Napkin. None of them are quite correct.
The first three suggested graphics looked good, but from a subject matter expert’s perspective they are misleading. The first pinwheel graphic correctly identifies several Fediverse platforms that I list in my text, but incorrectly attributes the ActivityPub protocols to them; they are the foundation of all platforms. The second graphic pulled out a number of relevant keywords, but is not helpful without an explanation of why they are relevant. The last cycle graphic was interesting because it pulled out more implicit information from my text, but it did not answer my core question of what the Fediverse is.
This napkin graphic correctly displays concepts related to the Fediverse.
After scrolling a bit, I found a good match. With this graphic, Napkin has correctly selected the relevant platforms, properly contextualized the ActivityPub protocols, and highlighted two important facets of the fediverse – decentralization and open source. This is a great visualization because it gives the reader a good framework to understand what’s important at a glance and can spark interest to read on. While it took a bit of work to get the best graphic – and I would have edited it before publishing – I was pretty happy with Napkin’s ability to read and synthesize the text I gave it. After all, no AI tool is perfect.
Brainstorming for image ideas
If you’re not quite sure what kind of graphic you want, Napkin is great for brainstorming ideas. I pulled some text – the longest I tested was about 157 words – from a guide I’d written on writing the best AI image prompt and entered it into Napkin. I wanted to highlight the three essential elements that every AI prompt should include, but I didn’t care how exactly that was done. Napkin came back with lots of different ideas, and it was nice to be able to look through all the options since I wasn’t locked into a specific design or look. This is the idea that immediately caught my eye.
Napkin’s graphic not only highlights the elements I discussed in my text, but it also reinforces my point about how important these things are by presenting them as pillars. Without such a pillar, the building falls down and the prompt fails. Any of the graphics Napkin created would have been fine, but this one conveys its importance implicitly. This is a great example of something I’ve found time and time again when testing AI image services—people need to be involved in the design strategy and process, or your results won’t resonate with your audience. Napkin, like any other AI service, is just a tool to get you there. For all of these examples, our developers at CNET could have come up with these graphics and probably improved them. But for people without a large creative team or a lot of time to create, or for those who just want to come up with some initial ideas, Napkin is a great place to start.
TL;DR: Napkin is promising
It’s safe to say that AI art startups like Napkin are in a tough spot and need to prove they have something different and useful to offer. In this case, I’m optimistic that Napkin is on the right track. It’s user-friendly and creative enough to cater to amateurs like me, but it’s also a helpful, practical tool for professional creatives just starting out in the design process.
My two biggest wishes are more customization options, especially custom colors and fonts, and integrations with other word processing software. I would also love it if Napkin gave users the option to opt out of training AI models altogether, which I think would be desirable for both businesses and privacy-conscious people.
One of the things I’ve found time and time again with AI creative tools, including Napkin, is how present the human using the service needs to be, and that these tools can’t be used successfully without human design and decision-making. It doesn’t matter if you create hundreds of different Napkin graphics if you don’t know your audience and your material well enough to decide which is the best choice to convey that information. In that regard, Napkin shows promise, and I’m excited to see how it continues to develop new features and functionality.
