Armox
    Armox Academy 📚
    Core ConceptsNodes

    Understanding Nodes

    Nodes are the fundamental building blocks of your Armox workflows. Each node performs a specific function and can be connected to other nodes to create powerful content generation pipelines.

    What Are Nodes?

    Complete Workflow Example

    A complex workflow showing multiple nodes connected together: Upload nodes, Image generation, Text generation, and Video creation.

    In Armox, a node is a single unit of functionality in your Canvas workflow. Each node:

    • Has a specific purpose (text input, image generation, etc.)
    • Has inputs (left side) and outputs (right side)
    • Can be connected to other nodes
    • Has settings you can configure

    Think of nodes like building blocks—you connect them together to create complex creative workflows.


    Node Types Overview

    Armox has six main types of nodes:

    Node TypePurposeInputOutput
    TextWrite prompts or generate textTextText
    ImageGenerate images with AIText, ImageImage
    VideoGenerate videos with AIText, Image, VideoVideo
    AudioGenerate music or speechText, AudioAudio
    UploadAdd your own filesNoneImage, Video, or Audio
    ToolProcess and enhance contentVariesVaries

    Text Nodes

    Text nodes are where you write prompts or generate text content.

    Text Node with GPT-5

    A Text node using GPT-5 for AI-powered text generation.

    Two Modes

    1. Manual Mode — Type your own text directly
    2. AI Mode — Use an AI model to generate or refine text

    Use Cases

    • ✍️ Writing prompts for image generation
    • 📝 Generating marketing copy
    • 🔄 Refining or expanding ideas
    • 💬 Creating captions or descriptions

    Settings

    • Mode Toggle — Switch between manual and AI
    • Model — Choose AI model (GPT-5, Claude, Gemini, etc.)
    • System Prompt — Guide the AI's behavior

    Available Text Models

    ModelBest ForLearn More
    GPT-5Complex reasoning, coding, creative writingGPT-5 Reference
    Gemini 2.5 FlashFast responses, balanced performanceGemini 2.5 Flash Reference
    Claude 4.5 SonnetNuanced writing, analysis, safetyClaude 4.5 Sonnet Reference
    DeepSeek V3.1Code generation, cost-effectiveDeepSeek V3.1 Reference
    Grok 4Real-time info, conversationalGrok 4 Reference
    Llama 3 70BOpen-source, high performanceLlama 3 70B Reference
    Llama 3 8BLightweight, fastLlama 3 8B Reference

    📚 See all text models: Text Models Reference

    Output

    Text nodes output text (🟡 yellow connection) that can flow to:

    • Image nodes (as prompts)
    • Video nodes (as prompts)
    • Audio nodes (as text-to-speech input)
    • Other text nodes (for chaining)

    Image Nodes

    Image nodes generate images using AI models.

    Image Node with Nano Banana

    An Image node with the Nano Banana model selected for image generation.

    Capabilities

    • 🎨 Text-to-image generation
    • 🖼️ Image-to-image transformation
    • 📐 Multiple aspect ratios
    • 🎭 Various styles and aesthetics

    Settings

    SettingDescription
    ModelAI model (Flux, Nano Banana, SDXL, etc.)
    Aspect RatioOutput dimensions (1:1, 16:9, 9:16, etc.)
    Guidance ScaleHow closely to follow the prompt
    StylePreset styles (varies by model)

    Available Image Models

    ModelBest ForLearn More
    Nano Banana ProHighest quality, Google's flagshipNano Banana Pro Reference
    Nano BananaFast, high-quality generationNano Banana Reference
    Flux 2 ProProfessional quality, versatileFlux 2 Pro Reference
    Flux 2 FlexFlexible, balanced performanceFlux 2 Flex Reference
    Flux 1.1 Pro UltraUltra high resolutionFlux 1.1 Pro Ultra Reference
    Seedream 4.5Artistic styles, animeSeedream 4.5 Reference
    Wan 2.2 ImageRealistic, detailed imageryWan 2.2 Image Reference
    Grok 2 ImageCreative, fast generationGrok 2 Image Reference
    Qwen ImageVision-language, multimodalQwen Image Reference
    Stable Diffusion XLOpen-source, customizableSDXL Reference
    Flux Kontext MaxContext-aware editingFlux Kontext Max Reference

    📚 See all image models: Image Models Reference

    Inputs

    • Prompt (required) — Text describing the desired image
    • Reference Image (optional) — Image for style or content reference

    Output

    Image nodes output an image (🔵 blue connection) that can flow to:

    • Video nodes (for image-to-video)
    • Tool nodes (for processing)
    • Other image nodes (for chaining)

    Video Nodes

    Video nodes create AI-generated videos.

    Video Node with Kling

    A Video node using Kling V2.5 Turbo Pro for high-quality video generation.

    Capabilities

    • 📝 Text-to-video generation
    • 🖼️ Image-to-video animation
    • 🎬 Various durations and resolutions
    • 🔊 Some models include audio

    Settings

    SettingDescription
    ModelAI model (Kling, Veo, Seedance, Sora, etc.)
    DurationVideo length (5s, 10s, etc.)
    ResolutionOutput quality
    FPSFrames per second

    Available Video Models

    ModelBest ForLearn More
    Kling 2.6 ProCinematic quality, long durationKling 2.6 Pro Reference
    Kling V2.5 Turbo ProFast, high-quality videoKling V2.5 Turbo Pro Reference
    Veo 3.1Google's flagship, highest qualityVeo 3.1 Reference
    Veo 3.1 FastFast Google video generationVeo 3.1 Fast Reference
    Seedance 1 ProAnime, stylized contentSeedance 1 Pro Reference
    Wan 2.6 T2VText-to-video, versatileWan 2.6 T2V Reference
    Wan 2.6 I2VImage-to-video animationWan 2.6 I2V Reference
    Sora 2 ProOpenAI's flagship video modelSora 2 Pro Reference
    Hailuo 2.3Fast image animationHailuo 2.3 Reference
    Gen4 AlephRunway's professional videoGen4 Aleph Reference

    📚 See all video models: Video Models Reference

    Inputs

    • Prompt (required) — Text describing the video
    • Reference Image (optional) — Starting frame or style reference
    • Audio (optional) — Some models accept audio input

    Output

    Video nodes output a video (🟢 green connection) that can flow to:

    • Tool nodes (for processing)
    • Other video nodes (for chaining)

    Audio Nodes

    Audio nodes generate music, speech, and sound effects.

    Audio Node with MusicGen

    An Audio node using MusicGen for music generation.

    Capabilities

    • 🎵 Music generation
    • 🗣️ Text-to-speech
    • 🎙️ Voice cloning
    • 🔊 Sound effects

    Settings

    SettingDescription
    ModelAI model (MusicGen, Speech-02, Lyria, etc.)
    DurationAudio length
    VoiceVoice selection (for speech models)
    StyleMusic genre or mood

    Available Audio Models

    ModelBest ForLearn More
    MusicGenMusic generation, versatileMusicGen Reference
    Music 1.5Advanced music generationMusic 1.5 Reference
    Music-01Professional music creationMusic-01 Reference
    Lyria 2Google's music model, high qualityLyria 2 Reference
    Speech-02 HDHigh-quality text-to-speechSpeech-02 HD Reference
    Speech-02 TurboFast text-to-speechSpeech-02 Turbo Reference
    Voice CloningClone any voiceVoice Cloning Reference
    XTTS-v2Multilingual speechXTTS-v2 Reference

    📚 See all audio models: Audio Models Reference

    Inputs

    • Prompt (required) — Text description or script
    • Reference Audio (optional) — For voice cloning or style matching

    Output

    Audio nodes output audio (🟠 orange connection) that can flow to:

    • Video nodes (for adding sound)
    • Tool nodes (for processing)

    Upload Nodes

    Upload nodes let you bring your own files into workflows.

    Capabilities

    • 📤 Upload images, videos, or audio
    • 🖱️ Drag-and-drop support
    • 📁 Use your own assets as AI inputs

    Supported Formats

    TypeFormats
    ImageJPG, PNG, WebP, GIF
    VideoMP4, MOV, WebM
    AudioMP3, WAV, M4A

    Output

    The output type depends on what you upload:

    • Upload an image → 🔵 Blue (image) output
    • Upload a video → 🟢 Green (video) output
    • Upload audio → 🟠 Orange (audio) output

    Use Cases

    • 🖼️ Reference images for style transfer
    • 🎬 Videos to transform
    • 🎤 Audio samples for voice cloning
    • 📷 Product photos to enhance

    Tool Nodes

    Tool nodes process and enhance existing content.

    Tools Submenu

    The Tools submenu showing Image Tools and Video Tools categories.

    Available Image Tools

    ToolPurposeLearn More
    Crystal UpscalerEnhance image resolution up to 4xCrystal Upscaler Reference
    Remove BackgroundRemove backgrounds from imagesRemove Background Reference
    Face SwapSwap faces between imagesFace Swap Reference
    Image FiltersApply artistic effects and filtersImage Filters Reference
    Professional HeadshotTransform photos into headshotsProfessional Headshot Reference
    Text RemovalRemove text from imagesText Removal Reference
    Add WatermarkAdd watermarks to imagesAdd Watermark Reference

    Available Video Tools

    ToolPurposeLearn More
    Video Upscale [Runway]Enhance video resolutionVideo Upscale Runway Reference
    Video Upscale [Topazlabs]Professional video upscalingVideo Upscale Topaz Reference
    Lip Sync ProSync lips to audioLip Sync Pro Reference
    Auto CaptionGenerate video captionsAuto Caption Reference
    Replace Character [Wan-2.2]Replace characters in videoReplace Character Reference
    Motion Transfer [Wan-2.2]Transfer motion between videosMotion Transfer Reference
    Merge VideosCombine multiple videosMerge Videos Reference

    📚 See all tools: Tools Reference

    When to Use Tools

    • 🔍 Upscaling — Make images/videos larger and sharper
    • ✂️ Background Removal — Isolate subjects
    • 🎭 Face Swap — Replace faces in images
    • 🎨 Filters — Apply artistic effects
    • 📝 Captions — Add subtitles to videos
    • 👄 Lip Sync — Match lips to audio

    Connection Handles

    Nodes have colored handles that indicate data types:

    ColorData TypeExample
    🟡 YellowTextPrompts, captions, scripts
    🔵 BlueImagePhotos, graphics, art
    🟢 GreenVideoClips, animations
    🟠 OrangeAudioMusic, speech, sounds

    Connection Rules

    1. Output to Input — Always connect from right (output) to left (input)
    2. Type Matching — Colors should generally match (🔵 blue to 🔵 blue)
    3. Text is Flexible — Text (🟡 yellow) can connect to most input types as prompts
    4. Some Nodes Accept Multiple Types — Check the input handles

    Adding Nodes to Canvas

    Method 1: Drag and Drop

    1. Open the node sidebar on the left
    2. Find the node type you want
    3. Drag it onto the canvas

    Method 2: Click to Add

    1. Open the node sidebar
    2. Click on a node type
    3. It appears in the center of your view

    Method 3: Context Menu

    1. Right-click on the canvas
    2. Select a node type from the menu

    Node States

    Nodes show different states:

    StateAppearanceMeaning
    IdleNormalReady to run
    RunningSpinning indicatorCurrently generating
    CompleteShows resultGeneration finished
    ErrorRed indicatorSomething went wrong

    Best Practices

    Start Simple

    Begin with basic two-node workflows:

    • Text → Image
    • Upload → Tool
    • Text → Video

    Plan Your Flow

    Before adding nodes, think about:

    1. What's your input? (text, image, etc.)
    2. What's your desired output?
    3. What processing steps are needed?

    Keep It Organized

    • Arrange nodes left-to-right
    • Leave space between nodes
    • Name your canvases descriptively

    Next Steps

    Now that you understand nodes, learn about:

    AI Models Reference

    Explore detailed documentation for each AI model: