mlx-bun library API
    Preparing search index...

    Module @mlx-bun/inference/input/vision

    AudioTokenIds
    MultimodalPrompt
    MultimodalTowers
    PreprocessedImage
    RGBImage
    VisionPrompt
    VisionTokenIds
    MODEL_PATCH_SIZE
    NUM_SOFT_TOKENS
    PATCH_SIZE
    POOLING_KERNEL_SIZE
    VIDEO_MAX_FRAMES
    VIDEO_SAMPLE_FPS
    buildMultimodalPrompt
    buildVisionPrompt
    decodeImage
    extractAudio
    extractImages
    extractVideoFrames
    extractVideos
    preprocessImage
    resizeBicubic
    resolveFrameExtract
    targetSize
    VisionEncoder → VisionEncoder

    Settings
    Member Visibility

    On This Page
    Interfaces
    Variables
    Functions
    References