CNAPS Studio User Guides

The complete guide to building AI-powered image, video, and audio workflows.

CNAPS Studio is a no-code AI platform for image, video, and audio work. Start on Home: pick a card, and a finished AI task runs for you — background removal, upscaling, poster generation, transcription, and more. When you want to change how a task works, open that same card on the canvas and rewire it yourself. This guide covers everything from your first card to batch processing.

Table of Contents

1. What is CNAPS Studio?
2. Home — Pick a Card, Get a Result
3. Understanding the Basics
4. Platform Guide
5. Common Challenges & Solutions
6. API Integration
7. Integrations
8. Glossary
9. Additional Resources

What is CNAPS Studio?

Two ways to use it

Who It's For

Teams that process images, video, or audio at volume and need the same result every time — marketing and e-commerce teams preparing product and campaign assets, media teams editing and anonymizing footage, and operations teams running inspection or analysis pipelines. For organizations whose data can't leave their own network, such as healthcare, manufacturing, and the public sector, Enterprise plans offer on-premise deployment.

What Problems It Solves

Pricing & Plans

Every plan includes every model and the full template library. Plans differ in usage capacity, batch processing, and team features:

• Free — basic capacity, watermarked outputs
• Starter and Pro — more capacity, no watermark, Batch Run (limited on Starter)
• Business — team workspace, SSO/SAML, role-based access control, Flow Versioning, webhooks
• Enterprise — custom capacity and on-premise deployment

🎁 New users get a 2-week free Pro trial.

For current prices and the full comparison, see cnaps.ai/pricing.

Home — Pick a Card, Get a Result

Home is where you land. Every card is a complete AI task that has already been built and tested for you. You don't need an account to start. Run a card as a guest — three a day, watermarked and view-only. Sign up to download, to open the canvas, and to keep what you made; guest work comes with you.

How it works:

1. Find a card. 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".
2. Open it. Every card opens with a finished example already on screen, so you can see exactly what it produces before you run anything yourself.
3. Swap in your own input on the right — text, an image, an audio file, or a video.
4. Click Run again. Your result replaces the example.
5. Download what you like. Everything you make is also saved under My Work → My Creations.

Good to know:

• New cards land continuously. Search is the fastest way to find one — the gallery is built to keep growing.
• Running a card's sample as-is is free. Change any input and the run counts against your capacity.
• A card can expose a single control that drives several nodes at once — one Strength slider, for example, may set the matching parameter on every model inside the card, so you tune the result rather than each step. Control labels are shown in your interface language.
• Works on mobile — browse cards, upload, run, and download results from your phone.
• Some cards run several AI models at once. The compare magnifier moves across every panel together, so the same region is magnified in each output as you move the cursor. You can also switch to Split Compare to drag a divider across two results instead.
• Each card shows an estimated run time before you start.
• Need more control? Click Open in CNAPS Studio on any card to load that card's actual workflow onto the canvas (sign-in required). It is the fastest way to learn how flows are built — and the way to customize one.

Understanding the Basics

New here? Complete the Quickstart Guide first — your first result takes about 30 seconds, and your first flow comes right after.

What is a flow?

A flow is a series of connected steps that process your data automatically. Each step is called a node, and nodes are connected by lines that show how data moves.

Think of it like a factory assembly line:

1. Raw materials enter (Input)
2. Each station does one job (AI Models & Tools)
3. Finished product exits (Output)

Node types

Input Nodes (data entry)

• Image Loader — upload images (JPG, PNG, WEBP, AVIF)
• Text Input — enter text data
• Video Loader — upload video files
• Sound Loader — drop in an audio file, or switch to the Record tab to capture from your microphone with a live waveform. Recording works in Chrome and Firefox (WebM) and in Safari (MP4)

AI Model Nodes (smart processing)

→ Browse all models: AI Model Hub

Tool Nodes (data manipulation)

• Annotation (1) — Canny Edge Annotator
• Blur & Effects (5) — Image Blur (Fast / Standard / Simple), Lens Blur, Selective Blur
• Color Adjustments (2) — Grayscale, Inverse
• Comparison (3) — Image Compare, Video Compare, Text Compare
• Image Blending (2) — Image Add, Image Multiply (now with auto-fit)
• Image Masking (5) — Masker by Class / by Coord / by Region, Manual Masker, Object Picker
• Image Resizing (3) — Resize, Conditional Resize, Resize to Match
• Layered Tools (1) — Layer Compose
• Selection & Extraction (15) — Color Pick by Class / by RGB Value, Crop by Class / by Coord / by Text, Image Selector, List Extract / List Inject, Image Gate by Text, Manual Color Picker, Manual Crop, Video Frame Extract, Video Reassemble, Video Split, Video Trim
• Text Tools (4) — Draw Text, Region Extract, Text Concatenate, Text Decorator
• Video Editing (18) — Audio Finish, Hook Teaser (Cold Open), Ken Burns (Still to Video), Narration Mux (Cold Open), Remove Dead Zone, Slice Transcript to Clips, Snap Segments to Speech, Video Caption, Video Clean Span, Video Concat, Video Constraint Map, Video EDL, Video EDL Planner, Video Narrate (Qwen3), Video Reframe (9:16), Video SFX, Video Speed, Video Subtitle (Spoken)

Output Nodes (View Results)

Where you see the final results.

• Image Viewer — display processed images (resizable)
• Text Viewer — display text results and data
• Video Viewer — display generated/processed videos
• Sound Output — play the resulting audio, with its waveform displayed

AI-Generated Content Labels

When your flow uses AI models to generate or manipulate content, CNAPS Studio automatically labels the output — both in the viewer and in downloaded files.

Chain detection: If your flow has FLUX (image gen) → BiRefNet (segmentation) → Output, the segmentation output still shows the "AI-generated · FLUX Schnell" badge because the upstream chain contains generation. The badge tracks the earliest AI generation step in the flow.

Why it's there:

• EU AI Act Article 50 requires AI-generated content to be identifiable
• The badge tells anyone viewing the output that it came from an AI model — useful for compliance, journalism ethics, and end-user trust
• CNAPS also embeds machine-readable provenance metadata in downloaded files

When it appears:

• ✅ Flow includes any generative model (image generation, image editing, video generation, TTS, multimodal LLM, image captioning)
• ✅ Flow includes OCR (labeled as "AI-extracted" not "generated" — to preserve accuracy)
• ❌ Pure utility flows (upscaling, denoising, resize, blur, object detection) — no badge

Connecting Nodes: The Color System

Nodes have colored connection points (called "ports") showing what data type they handle:

• 🔵 Blue dots = Image data
• 🔴 Red dots = Text data
• Light Blue dots = Video data
• 🟢 Green dots = Audio data
• Multiple colors = Nodes that handle more than one type

Understanding Usage Capacity

CNAPS Studio measures your usage by GPU processing time - essentially, how much computing power your flows consume.

• Each plan includes a set amount of usage capacity
• Complex AI models use more capacity than simple tools
• Failed runs don't count — if a run errors out, its GPU time isn't recorded against your capacity
• Capacity resets every 5 hours (rolling window)
• Monitor real-time usage: your avatar → Usage
• If you exceed capacity: processing pauses until the next reset, or upgrade for more

BlindSpot — One-Click Anonymization

A standalone web app for privacy-safe images — no workflow, no setup:

1. Upload an image (PNG, JPEG, WebP, AVIF, BMP, or HEIC — up to 10 MB)
2. Choose what to hide: Face, Tattoo, License Plate, Person, Logo, Text, or Custom (type anything)
3. Get your anonymized image back on the same page

Platform Guide

Interface Overview

Two panels run the whole product: the left sidebar takes you between Home, the canvas, and your work; the avatar menu in the top right holds your workspace, billing, and account settings.

→ New user? Complete the Quickstart Guide to familiarize yourself with the interface.

Left Sidebar (Navigation)

• Home — the card gallery, with search at the top. See the Home section above.
• CNAPS Studio — the full canvas. Opens a new blank flow where you can drag, connect, and configure nodes yourself.
• Community — flows published by other users. Fork any of them into your own workspace, then run or modify them.

• My Work
• My Creations — every result you've made from a card on Home
• My Flows — your flow library, with thumbnails, status, permissions, model counts, and last-modified dates. Search flows by name in real time, and Shift-click to multi-select for bulk delete or share. Per-flow actions: Add to Batch Run, Share, Publish to Community, Fork, Delete

• Batch Runs — monitor batch executions, preview inputs/outputs, download results as ZIP

• Shared with me — flows others have shared with you

• API Key — create keys for programmatic access: Batch Run via the REST API, and the n8n integration
• → See details: API Integration section below

At the bottom of the sidebar

• Appearance — switch the whole interface between Light, Dark, and System (System follows your operating system setting)
• Guides — opens this documentation site

Collapse the sidebar with the toggle next to the logo when you want more room for the canvas.

Account & Workspace Menu (top right)

Click your avatar in the top-right corner.

Workspaces

• Workspace switcher — switch between workspaces, or create a new one with + Business Workspace
• Personal - For Free, Starter, and Pro users
• Business - For Business users. You can create a business/team workspace here once you subscribe to the Business pricing plan.
• Workspace Settings — open the workspace switcher (your workspace name at the top of the menu), then Workspace Settings. Four tabs: General, Billing, Usage, and Integrations
• General

1. Workspace Icon: Upload a custom icon to personalize your workspace
2. Workspace Name: Give your workspace a unique name
3. Handle: A unique, taggable @username (e.g., @creator) for CNAPS Community
4. Workspace Type: Displays whether this is a Personal or Business workspace
5. Your Role: Displays your role within the workspace (relevant for Business plan team members)
• Billing

1. View your current subscription plan and manage billing, upgrades, downgrades, or cancellations.
2. Also linked directly in the avatar menu as a shortcut.
• Usage

1. Track your usage capacity consumption for the current 5-hour period. The usage bar shows what percentage you've used, with your capacity automatically resetting every 5 hours.
2. Also linked directly in the avatar menu as a shortcut.
• Integrations — API Keys for External Models. Paste your own Anthropic, OpenAI, or Google API keys to enable external model nodes. These bill through your provider accounts and don't consume your CNAPS capacity.
• Get API keys from providers:
• Claude: https://console.anthropic.com/
• OpenAI: https://platform.openai.com/api-keys
• Google: https://aistudio.google.com/app/apikey
• Paste keys on the Integrations tab
• External models become available in the Component panel

Account

• Account Settings - profile, security (password/email), activity log, and account management. Interface available in 9 languages: English, Korean, Japanese, Chinese, Spanish, Arabic, French, Vietnamese, Portuguese. Your language choice is stored on your account, not in the browser, so it follows you across every CNAPS.ai site you sign in to rather than resetting per site or per device.
• Security → Connected apps — the assistants and automation tools you have authorized through MCP with OAuth, such as Claude, Zapier, or Glama. Each row shows the workspace the app can reach, its access (expand Show all for the full scope list), and when it was last used. Disconnect revokes that app's access immediately. Anything a connected app does on your account counts as your own action and uses your capacity, so review what you approve.
• Legal - terms and privacy
• Docs - Guides · Quickstart · Models · FAQ
• Sign Out

🧩 Creating and Managing Flows

Starting a New Flow

3️⃣ Method 3: Start from a card 🆕

Open any card on Home, then click Open in CNAPS Studio. The card's real workflow lands on your canvas, fully wired and ready to run — the fastest way to see how an experienced flow is put together, and the easiest place to start customizing.

Configuring Nodes

Each node has settings that control its behavior. Configuration options appear directly on the node card when you select it.

Click any node to see its settings directly on the node card. Common options:

• Class — which object type to detect or process (e.g., "person", "car")
• Confidence Score — minimum certainty threshold (0–100%); higher = fewer but more accurate results
• Scale Factor — meaning depends on the node: an enlargement multiplier on upscaling models (e.g., 2x, 4x), or how much to downscale before blurring on Blur & Effects tools — see the tool's page
• Kernel Size — size of processing filter; larger = stronger effect
• Diffusion Steps — changes the result itself, not just its sharpness; higher values take longer. Start with the default
• Random Seed — the same seed, settings, and input reproduce the same result (useful for testing)

Running Your Flow

Single Run (testing & development)

1. Upload input data to Input nodes
2. Verify connections
3. Click Run Flow (top right)
4. Watch progress — the currently-processing node glows
5. View results in Output nodes; click to see full detail; download if needed

Visual cues during a run: animated button states (Default → Running → Done/Failed), glowing active node, smooth step-by-step progress bars, and background execution — flows keep running even if you switch tabs.

Batch Run (Production Processing)

Process up to 100 files through the same workflow at once.

Three input modes per node:

How to run a batch:

1. Open the dropdown next to Run Flow and choose Batch Run — one panel opens per input node (#1, #3, …)
2. Choose Batch / Shared / Flow Value per input
3. Drag & drop files or folders (up to 100 items)
4. Files in the same row are paired and run together — use Export CSV / Import CSV to reorder pairings for complex batches
5. Click Run Batch, then monitor at My Work → Batch Runs
6. The completion email now links straight to your results — one click from inbox to download
7. Download everything as a ZIP, or preview and download individual files

(Developers can also trigger batches via API — see API Integration below.)

Working with external models

Use AI services from Anthropic, OpenAI, and Google without consuming your CNAPS capacity — they bill through your own provider accounts.

Current external lineup:

• Audio: Gemini TTS
• Image/Video: GPT Image, Nano Banana, VEO, Video Analysis (Gemini), Omni
• Language: ChatGPT, Claude, Gemini

Setup:

1. Get API keys — Anthropic · OpenAI · Google
2. Paste them in your avatar → Workspace Settings → Integrations
3. In the Component panel, external models show white text when ready (gray = needs API key)

Common Challenges & Solutions

This section addresses the most frequent issues users encounter, especially those new to AI workflows.

Challenge #1: "I don't know where to start"

Start from something that already works, then change it one piece at a time.

1. Run a card on Home, then click Open in CNAPS Studio to see the flow behind it.
2. Change one thing — an input, a single setting, or one model — and run again. Compare the result.
3. Build your own starting from Input → one model → Output. Once that runs, add steps.

Common questions

• Which model should I use? Start with 🔥 Hot Models in the Component panel, then check the AI Model Hub for what each one is good at.
• What does this setting do? Leave it at the default until the flow works, then change one setting at a time. See the Glossary.
• What connects to what? Match port colors. Data flows left → right.
• Not getting what you expected? Add an Output node after each step to see where the result changes.

Still stuck? Browse CNAPS Community for working flows you can fork, or watch the video tutorials.

Challenge #2: "The AI model didn't work as I expected"

This is common because AI models have different training and vocabularies.

Solution 1: Try Different Models

CNAPS Studio provides multiple models for similar tasks:

Solution 2: Check the input size

Very large inputs slow detection down without making it more accurate, and very small ones lose the detail the model needs. If detection misses objects, try resizing the input so its longer side is around 1024 px, keeping the aspect ratio. Leave OCR inputs at their original size. See Challenge #3 for when to resize and when not to.

Challenge #3: "My flow is taking too long"

Nodes run one after another, so a flow's run time is roughly the sum of every step. Most slow flows come down to one of three things.

Large inputs. Processing time grows with resolution. If a step doesn't need full resolution — detection, classification, captioning — add a Resize node before it. Keep full resolution for OCR and for any step where fine detail is the output.

Stacked upscalers. Each upscaler enlarges the image every later step has to handle. Upscale once, at the end of the flow. For 4×, use one 4× model rather than two 2× passes. On large inputs (2K and up), choose SMFANet+ — PiSA-SR becomes very slow at that size.

Heavy models. Image and video generation, image editing, object removal, and video upscalers (SeedVR2, FlashVSR, SparkVSR) are the slowest nodes; a single video job can take several minutes. Run each heavy model on its own with one input before chaining it with others.

Batch runs take longer by design. A batch processes its items one after another, so a 100-item batch takes roughly 100 times as long as a single run. Run the flow once on a single input to estimate the total. You don't need to keep the tab open — the completion email links straight to your results.

Challenge #4: "I ran out of usage capacity"

Capacity is GPU time, measured over a rolling 5-hour window. When you reach the limit, new runs wait until capacity frees up — you are never charged extra.

• See where you stand: your avatar → Workspace Settings → Usage shows how much of the current window you've used.
• Make runs lighter: the fixes in Challenge #3 also cut capacity use. Heavy models and large inputs consume the most.
• Test small first: run a flow on one input before starting a batch.
• Need more room: higher plans include more capacity per window — your avatar → Billing.

External models (ChatGPT, Claude, Gemini, GPT Image, VEO, and others) don't use CNAPS capacity. They bill to your own provider account.

Challenge #5: "The output looks wrong or unexpected"

Systematic Troubleshooting:

Step 1: Check Each Node Individually

Add temporary Output nodes after each step:

Input → [Output 1] → Model A → [Output 2] → Model B → [Output 3] → Final Output

Process:

1. Run the flow
2. Check Output 1: Is the input correct?
3. Check Output 2: Did Model A work correctly?
4. Check Output 3: Did Model B work correctly?
5. Identify WHERE things go wrong

Step 2: Check Input Quality

Your input affects output quality:

✅ Good inputs:

• Clear, well-lit images
• Reasonable file size and resolution
• Correct format (JPG, PNG, WEBP, AVIF)
• Not heavily compressed or corrupted

❌ Bad inputs:

• Extremely dark or bright images
• Tiny thumbnail-sized images
• Heavily compressed or degraded
• Wrong file format

Quick test: Try the flow with a sample image from a template to see if it works correctly.

Step 3: Try Different Models

If one model produces poor results:

1. Swap it for an alternative model (same category)
2. Try models with higher star ratings
3. Compare results between 2-3 options
4. Different models have different strengths

Step 4: Simplify and Rebuild

If output is completely unexpected:

1. Create a new blank flow
2. Add just Input → Problematic Model → Output
3. Test if model works in isolation
4. Gradually add back other nodes
5. Identify which combination causes issues

Challenge #6: "My run was rejected"

CNAPS Studio screens content automatically at two points: your prompt and uploaded files before the flow runs, and generated outputs before they are stored. A request can be refused at either point.

You are not charged for a refused request — at either stage, and also when a request is refused because screening was temporarily unavailable. This is different from a run that simply errors out, which also doesn't consume capacity, but for a different reason: there, the work failed; here, we stopped it.

What to do:

1. Read the message on the node — it tells you at which stage the request was refused.
2. If the prompt or an uploaded file was refused, the flow never started. Revise and try again.
3. If the output was refused, the inputs passed but what came back did not. Changing the input image or the prompt's framing usually matters more than changing model settings.
4. Check the rules — Section 4 of the Terms of Service, plus Section 8.8 for anything you publish to Community, and the AI Policy.
5. If you believe it was a mistake, email support@cnaps.ai. Screening is automated, and you can ask for a human to review the decision.

Note: asking us not to use your Workflow structure to improve the Services (Privacy Policy §2(f)) does not turn off safety screening. Screening continues either way.

API Integration

Getting Your API Key

Managing Your API Keys

After creating a key, you can see it listed in the API Key menu with three options:

• Deactivate - Use when you temporarily want to stop using a key without deleting it
• Regenerate - Use when you think your key might be compromised or want to update it. Issue a new key value for the same entry and update every integration that uses it.
• Delete - Use when you no longer need this key

Web console only. API keys can only be created, viewed, regenerated, and deleted here in the web console. Key management is deliberately not exposed as an MCP tool or API endpoint, so an automated agent cannot issue itself a new key or delete one you depend on.

Batch Run via API

Go to Batch Run and click the "Call via API" dropdown to access technical integration details:

• ENDPOINT: The API URL for programmatic batch run execution
• Format: POST https://cnaps.ai/api/v1/batch-runs/run
• Click "Copy" to copy the endpoint
• HEADER: Your authentication key
• Format: x-api-key: YOUR_API_KEY
• Get your API key from API Key in the left sidebar
• Click "Copy" to copy the header
• FORM DATA: Required parameters for the API call
• flow_id: Your workflow's unique identifier
• files: one or more files, sent as -F "files=@your_file.png" — repeat the flag for each file
• Click "Copy ID" to copy your flow ID
• CURL EXAMPLE: Ready-to-use command line examples
• Toggle between Linux/macOS, Windows CMD, and PowerShell
• Complete curl command with your flow ID and file paths
• Click "Copy" to copy the command
• Replace YOUR_API_KEY and file paths with your actual values

After Running:

• Monitor execution status in the Batch Runs page
• View processing duration and completion time
• Preview input and output files
• Download all results as a ZIP file
• Batches are metered on measured GPU time, the same as runs you start from the canvas — not on a flat per-run rate

Integrations

You can drive CNAPS Studio from outside the web app. Pick the route that matches how you work:

You stay in control of the connection. Approve the OAuth consent screen only after checking the redirect host and any unverified-app warning, and disconnect an assistant any time from your avatar → Account Settings → Security → Connected apps — access stops immediately.

Claude, n8n, and Zapier all connect to the same CNAPS.ai MCP server and see the same tools. API keys are created and managed only in the web app, under API Key in the left sidebar.

Glossary

Additional Resources

Getting Started:

• Video tutorials
• CNAPS Community

Last Updated: Sep 27th, 2026