Image-to-Image

​

Overview

The image-to-image pipeline of the Livepeer AI network enables advanced image manipulations including style transfer, image enhancement, and more. This pipeline leverages cutting-edge diffusion models from the HuggingFace image-to-image pipeline.

​

Models

​

Warm Models

The current warm model requested for the image-to-image pipeline is:

• timbrooks/instruct-pix2pix: A powerful diffusion model that edits images to a high-quality standard based on human-written instructions.

​

On-Demand Models

The following models have been tested and verified for the image-to-image pipeline:

​

Basic Usage Instructions

To generate an image with the image-to-image pipeline, send a POST request to the Gateway’s image-to-image API endpoint:

curl -X POST https://<GATEWAY_IP>/image-to-image \
    -F model_id="ByteDance/SDXL-Lightning" \
    -F image=@<PATH_TO_IMAGE>/cool-cat.png \
    -F prompt="a hat"

In this command:

• <GATEWAY_IP> should be replaced with your AI Gateway’s IP address.
• model_id is the diffusion model for image generation.
• The image field holds the absolute path to the image file to be transformed.
• prompt is the text description for the image.

For additional optional parameters, refer to the Livepeer AI API Reference.

After execution, the Orchestrator processes the request and returns the response to the Gateway:

{
  "images": [
    {
      "nsfw": false,
      "seed": 3197613440,
      "url": "https://<GATEWAY_IP>/stream/dd5ad78d/7adde483.png"
    }
  ]
}

The url in the response is the URL of the generated image. Download the image with:

curl -O "https://<STORAGE_ENDPOINT>/stream/dd5ad78d/7adde483.png"

​

Orchestrator Configuration

To configure your Orchestrator to serve the image-to-image pipeline, refer to the Orchestrator Configuration guide. The following system requirements are recommended for optimal performance:

• NVIDIA GPU with at least 20GB of VRAM.

​

API Reference