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

# Which Training Path?

> Compare video-based and image-based Phoenix replica training and open the guide that matches your workflow.

You can create a replica by uploading a **training video** or a **training image** asset. Use the [Create Replica](/api-reference/phoenix-replica-model/create-replica) API with either `train_video_url` or `train_image_url` (mutually exclusive). You may also use the [Developer Portal](https://platform.tavus.io/dev/replicas/create), which walks through the same choices.

<Tip>
  In the [Developer Portal](https://platform.tavus.io/dev/replicas/create), you can record your training video directly within the platform using a guided workflow, or upload an image with real-time validation to ensure it meets all requirements before training.
</Tip>

## Compare video and image training

Each path has a different setup time and quality trade-offs.

<CardGroup cols={2}>
  <Card title="Record or upload video" icon="video" href="/sections/replica/train-with-a-video">
    Record or upload a training video for a replica with your personalized facial expressions.

    **`train_video_url`** in the API.

    * Captures your facial expressions
    * Highest fidelity output
    * Best for customer-facing use
  </Card>

  <Card title="Upload image" icon="image" href="/sections/replica/train-with-an-image">
    Upload a photo and select a voice. Quicker to set up with a more generalized output.

    **`train_image_url`** and **`voice_name`** in the API.

    * Fastest to set up
    * No webcam required
    * Generalized facial expressions
  </Card>
</CardGroup>