Fuser Apps - Vibecode apps, sites & games on everyone's favorite canvas

You can now build apps directly in Fuser—no code required. Fuser is an end-to-end creative engine. Make images, video, sound, 3D and more on canvas. Your references, generations, media and data can become something your app reads, responds to, and evolves from. Prompt, generate, edit, and ship in one click. Go live in minutes. Try it now: app generations are free for the next month on fuser.studio 💙

Add a comment

Replies

Best

Congratulations to Fuser for shipping this new feature. Been using this platform and love the Fuser Apps!

 excited to see what you've been building :)

 Thanks for always supporting us Zeng :)

 Thanks for being our day 0 supporter! Please make some cool websites and apps and share them with us. :)

Being able to mix images, video, sound and 3D on one canvas and turn it straight into a live app is a different pitch than the usual vibe coding tools. Curious about style consistency - if I generate a character in one node and reuse it across a video node and a game asset node, does it stay recognizably the same character, or do you end up reprompting each modality separately to match it up?

 Nodes support multi-modal inputs. If you have a character, you can easily "pipe" it to a generator node (image, video, 3d) to continue across the modality chain. Style consistency used to be tricky, but newer models have pretty much solved the problem. What's really cool is that you can get these generated assets and use them directly in your apps. That 3d model you generated? It can go directly into the hero :)

 This is a very good question! In addition to what Hirad, our CTO, has suggested, users can maintain character consistency for video generations by first generating a character sheet. The whole idea is to have everything available on the same canvas so that these details are possible to achieve without having to switch between different platforms

modular databases and multiplayer instantly on publish sounds great for a demo, but that's usually where these canvas-to-app tools start showing cracks - once two people are editing the same app's data at once, or a database migration is needed. has anyone actually shipped something with real user data through this, not just a prototype

 all valid points. DBs were probably the hardest part of this implementation. When it comes to editing, only 1 person at a time can really edit the DB entries. Although we have CRDT for the canvas, the database editing is different beast altogether, so we resorted to constrained mutations. Migrations are automatically handled by the model on as-needed basis. And yes! we've been piloting Apps for a couple of weeks now and already have users building functional apps with real users ;)

good to hear the constrained mutations approach actually holds up, that's the part i was skeptical about. curious how the model decides when a migration is needed vs just adding a new field - does it ever get that wrong on a live app with real data

The canvas-as-source-material idea is the interesting leap here. What I'd want to know is what happens to the model nodes once you hit publish. At design time a slow or flaky model call is fine because you're sitting there iterating, but in a live app that same node sits on an end user's hot path. Does a published app cache node outputs or fall back when a model times out or returns junk, or does the user just see the raw failure? That's usually where it-worked-on-my-canvas breaks.

 Apps have version support so you can easily go back and forth between your iterations. Wrt to model output, we have automatic recovery and error handling to minimize users interfacing with raw model outputs.

Spent a few minutes dragging nodes around and connecting different models together, and it felt way more intuitive than other node tools I've poked at. Really liked how the canvas stayed smooth even when I started stacking iterations on top of each other.

 that means a lot to hear you say that, Poyraz! What sets us apart from other node tools is that this team has first-hand experience making professional projects and teaching creative software over the years, and we know how important the details of performance, legibility, and accessibility are for the creative process.

This is the piece that clicks for me. Apps built directly on the canvas mean the creative work doesn't end when the generation does and the canvas itself becomes the source. Now that workflow can be a living, shareable thing. That's not a small feature, it's a new stage in the process that didn't exist before: you're not just producing an asset, you're producing something someone else can open, edit, use, pass on etc.


These apps are tailored to what's actually built on the canvas, they occupy this new layer between the creator and the outcome, between process and result. That layer is what's been missing from most creative AI tooling. Everyone's solved "generate more, generate faster," but almost no one has solved "turn what I made into something that lives and travels on its own."

This feels foundational rather than incremental, not just for AI in design, but for where design as a discipline is heading across every industry that touches a screen.

Super excited to see where this goes, so proud of that team!

 You said it! This launch is foundational. You've made some incredible apps already. Thank you for all your hard work on this launch. Excited to be building this together

How does Fuser handle version control when iterating across multiple models and modalities, and is there a way to roll back to a previous node configuration without losing the downstream outputs?

 Great question! Generation nodes have their own generation history, and you can pin older versions, freeze nodes so they do not regenerate when running entire workflows. This is also true for apps. Every generation of the app node is saved in its own history. You can also fork or branch from apps to evolve an idea from where you left off without rewriting the current version.

Finally tried fusing ideas across text and image models without juggling tabs, and the node view makes it so much easier to see what feeds into what. The orchestration layer actually feels useful, not just a buzzword.

 Thank you Erhan. Orchestration is key for creative work with AI. Context switching and asset management is really a silent creativity killer for us all. Our goal with Fuser is to foster a state of being locked in when working on an idea.

Congrats on the launch!

 Thanks for your support!

 Thank you!

I've been using it for a few days now and I'm still discovering the potential of having apps directly on the canvas... It's supa-powerful! The UX of Fuser Apps is also smoooooth! 🤌

 So glad to hear that Lubos! Always iterating and improving, so please let us know if something would make your life easier while using it. I was using it to make a couple landing page iterations for a friend, and the canvas managed to support 7 app nodes but the recommended amount from our engineers is 20 max haha.