“Hippo is a plugin to create stunning vector illustrations and web assets right in Figma, thanks to AI. It’s made to be easy to use, with 22 handpicked styles tailored for the web – no prompt engineering required. It can also vectorize or edit any image with AI.”

This new AI assistant for Figma that helps you write effective UX copy just won the Product of the Day on Product Hunt last week. It’s focused specifically on UX writing best practices and provides copy suggestions inspired by world-class products in your industry, tailored to your target users, and product voice and tone.

Amelia Wattenberger wrote an insightful essay discussing a few reasons chatbots are not the future of interfaces and how adding controls, information, and affordances can make them more usable.

Tutorial Tim shows how to use the AI plugin Wireframe Designer.

Silvia Bormüller interviews Chris Lüders about his upcoming ​“The Power of AI in Design Systems” workshop, where they discuss how AI can help with the design systems documentation, how tokens help in daily work, and the steps and prompts for generating design tokens for Tokens Studio with ChatGPT.

Punit Chawla showcases a few new AI plugins — Figaro, FontExploreAI, Aidentic, Cube GPT, QoQo​.AI, AI Designer, AI Color Palette Generator, and Diagram. While many of them still feel like proof of concept rather than a daily tool, it’s really interesting to see the direction design tools are taking.

A proof of concept that generates wireframe designs using the GPT 3.5 model. See this thread by Wu Chenmu on how it works.

Effortlessly remove backgrounds or isolate objects using AI.

The new plugin by Meng To uses AI to upscale up to 8X the original resolution. Perfect for a variety of images including avatars, background images, Midjourney renders, and marketing images. (Interesting that the author heavily relied on ChatGPT 4 to build it.)

I love seeing how teams improve their workflows with internal Figma plugins. Here, Bryan Berger from Discord built a handy plugin to randomize avatar fills from their design system library. The source code is available on GitHub. (I guess something is in the air, as Miguel Solorio is building something similar for his specific use case.)

I mentioned the FigGPT plugin in the last issue, and now Edward Chechique wrote a detailed walkthrough of using this plugin. It requires an OpenAI API key but then provides direct access to ChatGPT prompts and tools for UX writing directly from the Figma document.

“FigGPT is a tiny plugin that connects ChatGPT to Figma and helps you to compose and edit copy.”

Discord designer Daniel Destefanis built an internal plugin for generating entire conversations using ChatGTP and rendering them using their design system. This is an excellent example of automating a mundane part of day-to-day work with AI.

Cool open-source proof-of-concept, related to the above post by Edward. For now, I’m skeptical of AI-generated components (explaining ideas and details may take longer than building from scratch), but bullish on offloading mundane tasks, error detection, and quality checks to the AI.

Edward Chechique shares some ideas for AI features that he hopes to see at Config 2023.

Adobe announced Firefly, a family of creative generative AI models coming to Adobe products. The integration with Creative Suite and responsible generative AI is what makes it potentially very interesting. I also like that it’s positioned (similarly to GitHub’s Copilot) as a productivity tool and not a substitute for creators. For more context, see this thread by Sudharshan and another one by Linus with mind-blowing examples.

Jordan Singer shares what Diagram learned from participating in OpenAI Converge with early access to GPT‑4 and how they’re using it in Magician and Genius plugins.

A demo of a really smart FigJam widget that lets you collect data onto the canvas, fine-tune a model, and keep that tuned model directly on the canvas to generate new images: ​“With a few simple API endpoints (/​train, /​status, /​imagine), I made a multiplayer-enabled (!) canvas that had live-trained ML models living in it. Many people can come together and try out the model, you can alt-drag trained models to try out explorations without losing your history, you can mark it up with pencil drawings and stickies and do anything else you’ve gotten used to in FigJam and Figma.”

Nick Stamas is making a good point that Figma is uniquely positioned to create an AI assistant for designers, but instead of replacing them, it will be more like GitHub Copilot. ​“There’s one place where an enormous pile of UI data exists in a way that could be used to train a large neural network: Figma.”

If introducing Genius wasn’t enough, here is another upcoming AI tool for creating editable UI designs from a simple text description. As Vitaly Friedman rightfully put, ​“It’s about time to get used to websites looking exactly the same everywhere.”