> ## Documentation Index
> Fetch the complete documentation index at: https://docs.comfystream.org/llms.txt
> Use this file to discover all available pages before exploring further.

# ComfyStream Nodes

> Explore the native nodes provided by ComfyStream for real-time workflows.

export const GitHubFooter = ({url, float = "right"}) => <div style={{
  float: float,
  textDecoration: "none"
}}>
    <Icon icon="github" iconType="brands" color="white" />
    <a href={url} target="_blank" rel="noopener noreferrer" style={{
  marginLeft: "5px"
}}>
      GitHub
    </a>
  </div>;

<Note>
  These native nodes are pre-installed with ComfyStream when you install the
  package. You do not need to install them manually. See the [ComfyStream
  Installation Guide](/technical/get-started/install) for details.
</Note>

The ComfyStream package provides native nodes essential for real-time AI workflows in ComfyUI, handling tasks like converting audio and images into tensors, processing data, and converting tensors back into usable formats. Additionally, the **ComfyStream Toolkit** includes a **StreamPack**, which extends functionality with advanced custom nodes for video, audio, and data workflows. Learn more in the [StreamPack Overview](/technical/custom-nodes/stream-pack/overview) page.

## Input Nodes

ComfyStream provides input nodes to convert media inputs into tensors, enabling AI processing in real-time workflows.

<AccordionGroup>
  <Accordion title="LoadAudioTensor">
    Converts audio inputs into tensors, enabling real-time audio processing in ComfyStream workflows.

    <GitHubFooter url="https://github.com/livepeer/comfystream/blob/main/nodes/audio_utils/load_audio_tensor.py" />
  </Accordion>

  <Accordion title="LoadTensor">
    Converts image inputs into tensor format for computation in real-time AI workflows.

    <GitHubFooter url="https://github.com/livepeer/comfystream/blob/main/nodes/tensor_utils/load_tensor.py" />
  </Accordion>

  <Accordion title="PrimaryInputLoadImage">
    A passthrough node that specifies a reference image for real-time AI workflows, such as LivePortrait.

    <GitHubFooter url="https://github.com/livepeer/comfystream/blob/main/nodes/video_stream_utils/primary_input_load_image.py" />
  </Accordion>
</AccordionGroup>

## Output Nodes

ComfyStream provides output nodes to convert tensors back into media formats for real-time streaming.

<AccordionGroup>
  <Accordion title="SaveAudioTensor">
    Converts audio tensors into audio frames.

    <GitHubFooter url="https://github.com/livepeer/comfystream/blob/main/nodes/audio_utils/save_audio_tensor.py" />
  </Accordion>

  <Accordion title="SaveTensor">
    Converts image tensors into image frames.

    <GitHubFooter url="https://github.com/livepeer/comfystream/blob/main/nodes/tensor_utils/save_tensor.py" />
  </Accordion>
</AccordionGroup>

## Task-Specific Nodes

Most task-specific nodes are part of the StreamPack, but the ComfyStream package includes a few for example purposes.

<AccordionGroup>
  <Accordion title="PitchShifter">
    Shifts the pitch of an input audio stream, demonstrating audio
    transformations in real-time workflows.

    <Tip>
      Check out the [Example Workflow](https://github.com/livepeer/comfystream/blob/main/workflows/comfystream/audio-tensor-utils-example-api.json) to see the `PitchShifter` in action.
    </Tip>

    <GitHubFooter url="https://github.com/livepeer/comfystream/blob/main/nodes/audio_utils/pitch_shift.py" />
  </Accordion>
</AccordionGroup>