WorldofAI • 10:06 • 2 segments
Stitch is a free, AI‑powered UI design tool from Google that generates web and mobile interfaces from natural‑language prompts or uploaded wireframes, using Gemini models.
The experimental mode gives up to 100 free UI generations per month with Gemini 2.5 Pro, while the standard mode uses Gemini 2.5 Flash for faster iterations, theme edits, and Figma export.
The redesigned canvas displays the entire user flow, tracks component states, and a multi‑select feature lets you edit several screens at once for rapid, consistent updates.
Gemini 2.5 Pro runs on TPUs, producing each UI roughly three times faster than the standard mode.
Users may opt‑in or opt‑out of having their prompts used to train future Gemini models, and the tool remains free for anyone with a Google account via a simple dashboard link.
"But something important you will notice is that if you keep it on experimental mode, this is how you can access the Gemini 2"
00:00
"And it's easy to see why, cuz each generation is outputed quite quickly and it does a better job than even the standard mode, making outputs more creative and more importantly, easier to edit"
00:00
"And you can even add other additional pages to this canvas and it will just add in another canvas to the right hand side developing the next important feature a part of this UI that you had focused on"
05:59
✓ Obsidian export ready
./data/notes/aajr_uhJV3A_Google_Stitch_20_FULLY_FREE_Powerful_Coding_Agent_.md
A while back, we had taken a look at Stitch by Google, which is a free AI powere...
that this is one component that it had generated for us. Now say if we want to h...
A while back, we had taken a look at Stitch by Google, which is a free AI powered code design tool that transforms your ideas into beautiful user interfaces. It's powered by the latest Gemini models, where Stitch lets you generate UIs by simply typing in natural language prompts. You can upload images, wireframes, or files for the AI to reference, giving you more control and context over the output. Whether you're designing for the web or mobile, Stitch makes designs iteration fast, simple, and accessible. It's a tool built to streamline early stage design workflows, which lets you as a developer or just a regular user find a way to design quickly where you can go from concepts to functional UI mockups without needing to start from scratch. And obviously, the best part is that this tool is completely free to access right now. For example, take a look at it live in action where Stitch first initially developed the background for a romance and date app. And it was just requested to change the app theme to a light yellow. And it's also ensuring that all the images and icons match this new color. And you can see right away that it's able to rapidly work on iterating on all the different pages a part of that app as in terms of the UI and it makes the necessary changes across all of that. But ever since we had taken a look at Stitch, there have been new updates that the team has been releasing that makes it even better. To start off, there's a bigger experimental mode. This is where you get now up to 100 generations per month, which is awesome cuz you get access to the Gemini 2.5 Pro as something that you can use within the experimental mode and get 100 generations completely for free to develop any sort of UI. There's also faster workflows with suggested responses that show up right in your chat thread. There's more languages that you can use within Stitch, better designs with improved quality and consistency of generated UIs. And there's also a fresh look with a polished UI across the whole product. This is the new redesigned Stitch. And in terms of its UI, it looks pretty decent and easy to work with where you can start with a new design by describing your prompt over here for a mobile or web interface that you want to develop. You can even attach different mockups, wireframes or images. And then you can generate the design by clicking on this. But something important you will notice is that if you keep it on experimental mode, this is how you can access the Gemini 2.5 Pro, which is exceptional for UI designs. You also have the ability to change it to the standard mode where you can design faster with the Gemini 2.5 Flash. And this will let you actually quickly edit themes and export to Figma. The next new big feature is the canvas update, which is where they're rolling out with brand new foundational features that lets you see your entire user flow at once. This makes it super easy to track component states, ensure the design consistency is there across your project. And this is actually just the beginning cuz they're also focusing on setting the stage for more features like duplication of different canvases, having infinite generations of multiple pages by a single prompt, and many other smaller things. Now, another new feature is where Stitch got a major boost with TPUs as well as with the Gemini 2.5 Pro, which is where you can now have it so that it is nearly three times more faster than the standard mode. And it's easy to see why, cuz each generation is outputed quite quickly and it does a better job than even the standard mode, making outputs more creative and more importantly, easier to edit. And lastly, one of the big new updates that was introduced is the multi select feature. This is a powerful new feature that lets you edit multiple screens with a single prompt, which is just insane. Now you can actually hold shift and click and select all the different screens that you want to edit. And this is where once you have selected it, you can simply write one prompt and it will apply that across all the chosen screens at once. It's going to make it perfect for creating consistent designs and variations and even update the entire user flow in just seconds. This is going to give you more speed, consistency, and creative freedom when you're developing different UIs. Before we get started, I just want to mention that you should definitely go ahead and subscribe to the World of AI newsletter. I'm constantly posting different newsletters on a weekly basis. So, this is where you can easily get up-to-date knowledge about what is happening in the AI space. So definitely go ahead and subscribe as this is completely for free. And like I said at the start, it's super easy to get started. Just make sure you have a Google account and you can easily access Stitch completely for free. All you got to do is use the link which I'll leave in the description below and just click on the try now button which will take you to the main dashboard. This will take you to the main dashboard of Stitch. This is where you can describe your prompts in natural language and have it generate mobile or web user interfaces. Now, before you start generating anything, I want you to click on your profile icon. And over here, you can click on stitch settings. This is where you can toggle this off cuz you don't want it to allow the AI model to train off of the prompts that you're sending into this. So, I recommend that you turn this off and click on save changes because otherwise it is going to let Google use your future stitch conversation to train its generative AI models. Obviously, do it based off your own preference. I personally don't want it used for training models, but now you can try in any sort of prompt and have it generate it like make a catalog page with seasonal home decor items listed in a minimalistic grid layout with images, etc., etc. I can send in this prompt and you'll see that the agents will be deployed using the Gemini 2.5 Pro to generate the UI components for this idea that I want. You can see all of it being processed live in action within the canvas. And you can see that it is starting to generate the canvas and all the different components. And it looks like the seasonal decor catalog has been fully generated. And it looks pretty decent. And you can see
that this is one component that it had generated for us. Now say if we want to have it viewed as a desktop app, you can click on this button and it will start loading this up to be viewable as a desktop app. But now what you'll see is there's also new components added to the canvas where you can edit the designs in the chat where you can click on this and it will reference this canvas this specific one within the chat so that you can edit components like you can't see an image being loaded over here. So you can say add an image over here. Now if you want you can also change the color theme as well which is only available in the standard mode. Now if you want to get a full screen of this you can click on this and then you can access the code on over here where you can then copy the code that it had generated so that you can locally extract it. Now in the standard mode you can export this to Figma but since we're in the experimental mode we can't actually do that at this current moment. Another thing is you can directly access it over here. You can download it. You can delete it. But something cool that you'll notice is that when you whenever you send in any sort of prompt like make an app discovering California activities and getaways focus on showcasing destinations, musical events as well as easy trip planning. You'll see that it designs a comprehensive plan for this. There's also a suggested reply, design only the home screen for now, but we want to say design all the screens for this app because we want the stitch AI agents to focus on developing all the components for our app over here. So now now that we have said this reply after has sent in the plan, it'll generate multiple screens simultaneously for us which is just amazing. There we go. It looks like it has finished generating all the different screens for our travel app. It lists out the main home explore page, the individual pages like the about page, the events that are being hosted within the city, as well as different trips that you have planned beforehand. So, you can see that it generates all these different designs of different screens asynchronously, which is pretty cool. And you can even add other additional pages to this canvas and it will just add in another canvas to the right hand side developing the next important feature a part of this UI that you had focused on. Now like we had mentioned beforehand you can click on the select feature where if you press on command or shift you can select multiple different canvases and you can make changes to all of these different tagged canvases within stitch. So now that I have selected it, I can say something like change the theme for each of these different screens. And I'm asking to change it to green. And you can see now it has made the necessary changes where it first initially was green or a darker shade, but now we have a lighter green shade implemented to all of these different screens. If you like this video and would love to support the channel, you can consider donating to my channel through the super thanks option below. Or you can consider joining our private Discord where you can access multiple subscriptions to different AI tools for free on a monthly basis, plus daily AI news and exclusive content, plus a lot more. But that's basically it, guys, for today's video on Stitch. This is an impressive UI generator that is completely free to access. So, I highly recommend that you make the most out of this cuz I believe they will be turning over to a paid tier in the future. So, it's best to get the most out of it while it's free, as well as using the Gemini 2.5 Pro as the main model to generate your UIs. But with that thought, guys, I hope you enjoyed today's video and got some sort of value. I'll leave all these links in the description below. Join the newsletter, join our Pride or our second channel, join our Discord, follow me on Twitter, and lastly, make sure you guys subscribe, turn on notification bell, like this video, and please take a look at our previous videos cuz there is a lot of content that you will truly benefit from. But with that thought, guys, have an amazing day. Spread positivity and I'll see you guys fairly shortly.
