image-generation

Real-Time Image Previews with Streaming Sdxl

26 Apr 2025
Real-Time Image Previews with Streaming Sdxl

In today's fast-paced digital landscape, having the ability to generate and stream image previews in real-time is a game-changer for developers. The "Streaming Sdxl" API provides an innovative solution for applications that require instant feedback on AI-generated images. By utilizing advanced inpainting and img2img modes, developers can create dynamic visual content while offering a seamless user experience. The benefits of using this service include enhanced speed, customization through configurable parameters, and the ability to provide immediate visual feedback to users.

Common use cases for Streaming Sdxl include online design tools, gaming applications, and visual content creation platforms where users need to see immediate results of their modifications. Whether it's adjusting an image based on user input or showcasing creative concepts effectively, the Streaming Sdxl API is designed to simplify these processes.

Prerequisites

To start using Streaming Sdxl, you’ll need an API key for Cognitive Actions and a basic understanding of how to make API calls.

Stream Image Previews

The Stream Image Previews action is designed to generate and stream image previews in real-time. This action helps developers address the need for instant feedback on AI-generated image content, making it ideal for applications where quick visual results are essential.

Input Requirements:
The input for this action includes a variety of parameters to customize the output:

  • Image: The input image used for img2img or inpaint mode.
  • Prompt: A text prompt guiding the image generation.
  • Width & Height: Define the dimensions of the output image (default is 1024x1024).
  • Refinement Style: Choose from various refinement options to enhance the image.
  • LoRA Scale and Weights: Control the additive scale and weights for trained models.
  • Scheduler Type: Specify the algorithm for image generation.
  • Preview Size: Set the size of the preview image.
  • Guidance Scale, Prompt Strength, and High Noise Fraction: These parameters fine-tune the image generation process.

Expected Output:
The action returns a series of image URLs that represent the generated previews. The output provides a quick glimpse into the AI's creative process, allowing developers to showcase multiple iterations or variations of an image almost instantaneously.

Use Cases for this specific action:

  • Design Tools: Enable designers to visualize changes instantly as they modify parameters.
  • Gaming: Provide game developers with real-time graphics rendering, allowing for rapid prototyping of visual assets.
  • Marketing: Allow marketers to generate and review visual content quickly for campaigns, enhancing the creative workflow.
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 = "fa0fbc47-208f-4d27-ba25-b47f5e4d3848" # Action ID for: Stream Image Previews

# 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": "An astronaut riding a rainbow unicorn",
  "refine": "no_refiner",
  "loraScale": 0.6,
  "scheduler": "K_EULER",
  "previewSteps": 5,
  "guidanceScale": 7.5,
  "highNoiseFrac": 0.8,
  "applyWatermark": true,
  "negativePrompt": "",
  "promptStrength": 0.8,
  "numberOfInferenceSteps": 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 Streaming Sdxl API offers a powerful solution for developers seeking to implement real-time image previews in their applications. With its customizable parameters and instant feedback capabilities, it streamlines the creative process and enhances user engagement. Whether you are building a design tool, a game, or a marketing platform, integrating Streaming Sdxl can elevate your project to new heights. Start exploring the potential of real-time image generation and leverage this technology to enrich your applications today!

← Back to All Articles