Armox
    Armox Academy 📚
    AI Models ReferenceVideo ModelsWan 2.6 T2V

    Wan 2.6 T2V

    Wan 2.6 T2V creates videos from text descriptions with audio synchronization capabilities and reference audio support.

    Overview

    PropertyValue
    ProviderWan
    Cost1,000 credits
    ModalityVideo
    Duration5-15 seconds
    Prompt RequiredYes

    What It's Best For

    • Text-to-video — Generate from descriptions
    • Audio sync — Match video to music
    • Longer videos — Up to 15 seconds
    • Music videos — Create visuals for audio
    • Flexible formats — Many aspect ratios

    Inputs

    Prompt (Required)

    Describe the video scene.

    Connection Color: 🟡 Yellow

    Image (Optional)

    Reference image for style/content.

    Connection Color: 🟢 Green

    Reference Audio (Optional)

    Audio to sync video motion to.

    Connection Color: 🟠 Orange (Audio)

    Configuration

    Aspect Ratio

    Type: Select
    Default: 16:9

    16:9, 9:16, 4:3, 3:4, 1:1, 21:9.

    Duration

    Type: Slider
    Range: 5 - 15
    Default: 9

    Resolution

    Type: Select
    Default: 720p

    480p, 720p, or 1080p.

    Frames Per Second

    Type: Select
    Default: 24

    16 or 24 fps.

    Seed

    Type: Number

    Output

    Type: Video
    Connection Color: 🟢 Green

    Use Cases

    Music Video

    Connect reference audio:

    Abstract visuals pulsing to the beat, 
    colorful particles, dynamic motion, 
    synchronized to music rhythm.
    

    Scene Generation

    Sunset over ocean, waves gently rolling, 
    seagulls flying, warm golden light, 
    peaceful atmosphere.
    

    Character Animation

    Anime character walking through city, 
    dynamic camera following, urban environment, 
    vibrant colors.
    

    Abstract Art

    Connect audio track:

    Flowing abstract shapes, colors morphing, 
    geometric patterns, synchronized to music.
    

    Tips for Best Results

    1. Use reference audio — For music-synced content
    2. Describe motion — Be specific about movement
    3. Use 15 seconds — Maximum storytelling potential
    4. Experiment with formats — Different aspect ratios

    Comparison with I2V

    FeatureWan 2.6 T2VWan 2.6 I2V
    Image InputOptionalRequired
    Primary UseText-to-videoImage animation
    Audio Sync✅✅
    Cost1,000 credits1,000 credits