From sign-in to your first AI result in about 30 seconds — then to your first custom workflow in ten minutes.
1. Sign in and land on Home
Go to cnaps.ai and sign in. The first thing you see is Home: a gallery of cards, each one a complete AI task that has already been built and tested for you.
You don't need a paid plan to start. The Free plan gives you continuous access with a basic usage capacity that refills every 5 hours, and every model is available on every plan.
A card is a finished AI task. Someone already picked the models, wired them together, and tuned the settings. All that's left is your input.
2. Run your first card
① Find one. Scroll the gallery, or type what you want in the search bar at the top — "make my video sharper", "remove the background", "poster of me". New cards land continuously, so search is usually faster than scrolling.
② Open it. Every card opens with a finished example already on screen. Look at it first: this is exactly the kind of result the card produces. The example is a saved result, not a fresh run — browsing costs you nothing.
③ Swap in your own input. The panel on the right holds whatever the card needs — a line of text, an image, an audio file, a video. Replace the example with yours.
④ Click Run again. Your result replaces the example. The card tells you roughly how long to expect before you start.
⑤ Download it. Each result has its own download button. Some cards run several AI models at once and show you the results side by side — compare them and keep the one you prefer.
Nothing to configure. If the result isn't quite what you wanted, the first thing to change is your input, not the settings. Be more specific: "a red fox in a snowy pine forest at sunrise, soft golden light" gets you much further than "a fox".
3. Find your results later
Everything you make from a card is saved under My Work → My Creations in the left sidebar. Nothing expires when you close the tab.
4. See how the card actually works
This is the step that turns a card user into a flow builder.
On any card, click Open in CNAPS Studio. The card's real workflow lands on the canvas — every model, every tool, every connection, exactly as it ran.
Take a minute to read it left to right:
- Input nodes on the left hold your text, image, audio, or video
- AI model and tool nodes in the middle do the work, one job each
- Output nodes on the right show the result
- Colored lines connect them. Data flows left → right, and colors must match: 🔵 blue for images, 🔴 red for text, 🟢 green for audio, light blue for video
You now have something most people never get: a working, non-trivial flow whose output you have already seen.
5. Make it yours
Change exactly one thing. Swap a model for a similar one, adjust a single setting, or add an Output node in the middle of the chain to see what an intermediate step produces. Then click Run Flow and compare.
Repeat that a few times and the canvas stops being mysterious. Changing one thing at a time is the whole technique — it's how you learn which knob does what, and it's how experienced users debug.
Useful while you experiment
- Flow History — the History panel on the right records every edit. Restore any earlier state with one click, so nothing you try is irreversible.
- Sticky Notes — right-click empty canvas to search/add a sticky note
When you're ready to build from nothing, click CNAPS Studio in the left sidebar for a blank canvas. Start with three or four nodes — Input → one AI model → Output — get it running, then add from there.
6. Where to go next
If you want to… | Go to |
Run the same flow over 100 files at once | Batch Run — see the User Guides |
See what other people have built, and fork it | Community in the left sidebar |
Use your own Claude, OpenAI, or Google keys | your avatar → Workspace Settings → Integrations |
Call CNAPS Studio from your own code | API Key in the left sidebar, then the API Integration guide |
Drive CNAPS Studio from Claude, n8n, or Zapier | |
Browse every available model |