Create Engaging Text-Image Compositions with cjwbw/internlm-xcomposer Actions

22 Apr 2025
Create Engaging Text-Image Compositions with cjwbw/internlm-xcomposer Actions

In the world of content creation, the ability to generate captivating text-image compositions can significantly enhance user engagement and storytelling. The cjwbw/internlm-xcomposer API provides developers with powerful Cognitive Actions that leverage advanced models to create rich text-image interactions. One of the key offerings is the ability to generate interleaved text-image compositions, enabling applications to produce visually appealing content with minimal effort.

Prerequisites

Before you dive into using the Cognitive Actions provided by the cjwbw/internlm-xcomposer API, ensure you have the following:

  • An API key for accessing the Cognitive Actions platform.
  • Basic knowledge of making HTTP requests and handling JSON data.

Authentication typically involves passing your API key in the request headers. This allows you to securely access the Cognitive Actions without exposing your key.

Cognitive Actions Overview

Generate Interleaved Text-Image Composition

The Generate Interleaved Text-Image Composition action utilizes the InternLM-XComposer to create sophisticated text-image compositions. This action excels in generating long-form text, determining optimal image placements, providing captions, and selecting the most suitable images to complement the text. Its robust performance on multilingual benchmarks enhances the overall understanding and composition of text and images.

Input: The input for this action requires the following fields:

  • text (required): A string containing the primary text that relates to the image. This field provides context or poses questions regarding the associated image.
  • imageUri (optional): A string with the URI of the input image, which should be a valid and accessible web resource. This field serves as visual context for the text input.

Example Input:

{
  "text": "What makes this image special?",
  "imageUri": "https://replicate.delivery/pbxt/JcqDxAZJWep7WsZdWM0gc6Ead2ie0YDEXyemc9HXogSdpsOM/out-0%20%281%29.png"
}

Output: The output of this action is a descriptive text that encapsulates the essence of the image based on the provided input. For instance, it might return something like:

"The image is special because it features an astronaut sitting on a chair in a surreal, psychedelic landscape. The astronaut is dressed in an orange spacesuit, which adds to the futuristic and otherworldly feel of the scene..."

Example Output:

The image is special because it features an astronaut sitting on a chair in a surreal, psychedelic landscape. The astronaut is dressed in an orange spacesuit, which adds to the futuristic and otherworldly feel of the scene. The combination of the astronaut, the chair, and the psychedelic background creates an intriguing and visually captivating composition.

Conceptual Usage Example (Python): Below is a conceptual Python code snippet demonstrating how to call the Cognitive Actions execution endpoint for the Generate Interleaved Text-Image Composition action. This code constructs the necessary input payload and handles the API request.

import requests
import json

# Replace with your Cognitive Actions API key and endpoint
COGNITIVE_ACTIONS_API_KEY = "YOUR_COGNITIVE_ACTIONS_API_KEY"
COGNITIVE_ACTIONS_EXECUTE_URL = "https://api.cognitiveactions.com/actions/execute" # Hypothetical endpoint

action_id = "8b7a2bf1-4e05-4687-a89c-962199554f19" # Action ID for Generate Interleaved Text-Image Composition

# Construct the input payload based on the action's requirements
payload = {
    "text": "What makes this image special?",
    "imageUri": "https://replicate.delivery/pbxt/JcqDxAZJWep7WsZdWM0gc6Ead2ie0YDEXyemc9HXogSdpsOM/out-0%20%281%29.png"
}

headers = {
    "Authorization": f"Bearer {COGNITIVE_ACTIONS_API_KEY}",
    "Content-Type": "application/json"
}

try:
    response = requests.post(
        COGNITIVE_ACTIONS_EXECUTE_URL,
        headers=headers,
        json={"action_id": action_id, "inputs": payload} # Hypothetical structure
    )
    response.raise_for_status() # Raise an exception for bad status codes (4xx or 5xx)

    result = response.json()
    print("Action executed successfully:")
    print(json.dumps(result, indent=2))

except requests.exceptions.RequestException as e:
    print(f"Error executing action {action_id}: {e}")
    if e.response is not None:
        print(f"Response status: {e.response.status_code}")
        try:
            print(f"Response body: {e.response.json()}")
        except json.JSONDecodeError:
            print(f"Response body: {e.response.text}")

In this code snippet, replace YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key. The input payload is structured to align with the requirements for the Generate Interleaved Text-Image Composition action.

Conclusion

The cjwbw/internlm-xcomposer API provides developers with the tools to create engaging text-image compositions effortlessly. By integrating the Generate Interleaved Text-Image Composition action into your applications, you can enhance your content's visual appeal and narrative depth. Explore more use cases and imagine the possibilities of enriching user experiences through advanced cognitive actions!

← Back to All Articles