image-generation

Create Stunning Images from Text Prompts with Instagram2

26 Apr 2025
Create Stunning Images from Text Prompts with Instagram2

In the world of digital content creation, visually appealing images can significantly enhance storytelling and engagement. Instagram2 provides a powerful Cognitive Action that allows developers to generate images directly from text prompts. This feature not only simplifies the creative process but also opens up a multitude of possibilities for automating content creation, enhancing user interactions, and personalizing experiences. Whether you're designing marketing materials, creating social media posts, or enhancing user-generated content, the ability to generate images on demand can save time and resources while delivering high-quality visuals.

Prerequisites

To get started with Instagram2, you will need a Cognitive Actions API key and a basic understanding of making API calls. This will enable you to authenticate your requests and leverage the full potential of the image generation capabilities.

Generate Image From Text Prompt

This action allows you to create an image based on a specified text prompt, using a variety of customizable parameters to tailor the output to your needs. The flexibility of this action supports multiple use cases, from artistic expression to practical applications in content generation.

Purpose

The "Generate Image From Text Prompt" action solves the challenge of creating unique and relevant images based on textual descriptions. By inputting a detailed prompt, users can produce images that align closely with their creative vision or project requirements.

Input Requirements

To utilize this action, you must provide a set of parameters:

  • Prompt: A descriptive text that outlines the desired image.
  • Width & Height: Dimensions for the output image, with defaults set to 1024 pixels.
  • Mask: An optional URI for inpaint mode, indicating areas of the image to modify.
  • Seed: For reproducibility, you can specify a random seed.
  • Refine Style: Choose how much refinement to apply to the generated image.
  • Lora Scale: Adjust the LoRA additive scale for trained models.
  • Scheduler Type: Select the sampling algorithm for image refinement.
  • Num Outputs: Specify how many images to generate.
  • Guidance Scale: Control the strength of the guidance applied to the image generation.
  • Negative Prompt: Define undesired elements to exclude from the image.

Expected Output

The expected output is a URI to the generated image, which can be directly used in applications or shared across platforms. For example, a typical output looks like this:

https://assets.cognitiveactions.com/invocations/unique_image_id.png

Use Cases for this Specific Action

  • Marketing Campaigns: Quickly generate images that capture the essence of a product or service based on promotional text.
  • Social Media Content: Create eye-catching visuals tailored to specific themes or messages without needing graphic design skills.
  • Personalization: Use user input to generate personalized images, enhancing user engagement and satisfaction.
  • Creative Projects: Artists and designers can visualize complex concepts or narratives by generating images from detailed descriptions.
import requests
import json

# Replace with your actual Cognitive Actions API key and endpoint
# Ensure your environment securely handles the API key
COGNITIVE_ACTIONS_API_KEY = "YOUR_COGNITIVE_ACTIONS_API_KEY"
# This endpoint URL is hypothetical and should be documented for users
COGNITIVE_ACTIONS_EXECUTE_URL = "https://api.cognitiveactions.com/actions/execute"

action_id = "3c5fb62a-63a7-420b-ab16-75e8a1b8e7bc" # Action ID for: Generate Image From Text Prompt

# Construct the exact input payload based on the action's requirements
# This example uses the predefined example_input for this action:
payload = {
  "width": 1024,
  "height": 1024,
  "prompt": "photograph taken with iPhone 12 of a dignified Iranian young woman from TOK who appears 'broken but dignified'. Her appearance should reflect resilience and strength, hinting at past struggles yet maintaining an air of elegance and beauty in style of TOK\n",
  "refine": "no_refiner",
  "loraScale": 0.6,
  "scheduler": "K_EULER",
  "numOutputs": 1,
  "guidanceScale": 7.5,
  "highNoiseFrac": 0.8,
  "applyWatermark": true,
  "negativePrompt": "hijab , scarf , black and white , iPhone ,European look , model , posing European look  , Indian , hijab , scarf , deformed, worst quality, text, watermark, logo, banner, extra digits, deformed fingers, deformed hands, cropped, jpeg artefacts, signature, username, error, sketch, duplicate, ugly, monochrome, horror, geometry, mutation, disgusting",
  "promptStrength": 0.45,
  "numInferenceSteps": 50
}

headers = {
    "Authorization": f"Bearer {COGNITIVE_ACTIONS_API_KEY}",
    "Content-Type": "application/json",
    # Add any other required headers for the Cognitive Actions API
}

# Prepare the request body for the hypothetical execution endpoint
request_body = {
    "action_id": action_id,
    "inputs": payload
}

print(f"--- Calling Cognitive Action: {action.name or action_id} ---")
print(f"Endpoint: {COGNITIVE_ACTIONS_EXECUTE_URL}")
print(f"Action ID: {action_id}")
print("Payload being sent:")
print(json.dumps(request_body, indent=2))
print("------------------------------------------------")

try:
    response = requests.post(
        COGNITIVE_ACTIONS_EXECUTE_URL,
        headers=headers,
        json=request_body
    )
    response.raise_for_status() # Raise an exception for bad status codes (4xx or 5xx)

    result = response.json()
    print("Action executed successfully. Result:")
    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 (non-JSON): {e.response.text}")
    print("------------------------------------------------")

Conclusion

The ability to generate images from text prompts using Instagram2 represents a significant advancement in content creation. This action not only streamlines the process of image generation but also empowers developers to create customized and engaging visual content for a variety of applications. By leveraging this technology, you can enhance user experiences, automate creative workflows, and ultimately deliver more compelling digital narratives. Start exploring the potential of image generation today and transform your projects with stunning visuals!

← Back to All Articles