Enhance Your Images with sinazar/campfire-tiger3 Cognitive Actions

24 Apr 2025
Enhance Your Images with sinazar/campfire-tiger3 Cognitive Actions

In today's digital landscape, the ability to generate and refine images with precision is a game-changer for developers. The sinazar/campfire-tiger3 Cognitive Actions provide powerful capabilities for image generation through customizable parameters and advanced techniques. Whether you're looking to create stunning visuals for applications, websites, or marketing materials, these pre-built actions streamline the process, allowing you to focus on creativity rather than technical constraints.

Prerequisites

Before diving into the Cognitive Actions, ensure you have the following:

  • An API key for accessing the Cognitive Actions platform.
  • Familiarity with sending HTTP requests and handling JSON payloads.
  • Basic understanding of image generation concepts.

Conceptually, authentication can be achieved by passing your API key in the request headers.

Cognitive Actions Overview

Generate Enhanced Images

The Generate Enhanced Images action produces images using inpainting and img2img techniques, allowing for intricate refinements and detailed outputs. With options for advanced customization, developers can control aspects such as refinement style, noise levels, and sampling algorithms to achieve the desired image quality.

Input

The input for this action requires the following fields:

  • mask (string, optional): URI of the mask image for inpaint mode. Black areas remain unchanged, while white areas are processed for inpainting.
  • seed (integer, optional): Random seed for reproducibility; leave blank to randomize.
  • image (string, required): URI of the input image for img2img or inpaint mode operations.
  • width (integer, optional, default: 1024): Width of the output image in pixels.
  • height (integer, optional, default: 1024): Height of the output image in pixels.
  • prompt (string, required): Textual input prompt to guide image generation.
  • refine (string, optional, default: "no_refiner"): Style of refinement to apply.
  • loraScale (number, optional, default: 0.6): Scale factor for LoRA adjustments.
  • scheduler (string, optional, default: "K_EULER"): Algorithm used for sampling intermediate steps.
  • guidanceScale (number, optional, default: 7.5): Intensity of classifier-free guidance.
  • applyWatermark (boolean, optional, default: true): Determines if a watermark should be applied.
  • inferenceSteps (integer, optional, default: 50): Total number of denoising iterations.
  • negativePrompt (string, optional): Text input to suppress certain aspects.
  • promptStrength (number, optional, default: 0.8): Influence strength of the prompt.
  • numberOfOutputs (integer, optional, default: 1): Specify the number of output images.
  • highNoiseFraction (number, optional, default: 0.8): Intensity of noise for refinements.
  • disableSafetyChecker (boolean, optional, default: false): Toggle for disabling the safety checker.

Here’s an example input JSON payload for this action:

{
  "width": 1024,
  "height": 1024,
  "prompt": "A photo of TOK standing next to a bonfire, animal crossing, hands in pockets",
  "refine": "expert_ensemble_refiner",
  "loraScale": 0.6,
  "scheduler": "K_EULER",
  "guidanceScale": 7.5,
  "applyWatermark": false,
  "inferenceSteps": 75,
  "negativePrompt": "realistic",
  "promptStrength": 0.7,
  "numberOfOutputs": 4,
  "highNoiseFraction": 0.8
}

Output

The output of this action typically consists of an array of image URLs generated based on the input parameters. Here’s an example of the expected output:

[
  "https://assets.cognitiveactions.com/invocations/63411d60-9203-4a95-827d-43bd9a031a34/ce4c3678-614f-4092-ac87-06189af9e7e0.png",
  "https://assets.cognitiveactions.com/invocations/63411d60-9203-4a95-827d-43bd9a031a34/2f66e108-ab86-4160-82e2-ce8eebeeb664.png",
  "https://assets.cognitiveactions.com/invocations/63411d60-9203-4a95-827d-43bd9a031a34/f6cad749-02c5-4d2f-8edb-44ba471a92f5.png",
  "https://assets.cognitiveactions.com/invocations/63411d60-9203-4a95-827d-43bd9a031a34/5b65f673-36a0-4c5c-bdef-35424803133d.png"
]

Conceptual Usage Example (Python)

Here’s a conceptual Python code snippet demonstrating how to invoke the Generate Enhanced Images action:

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 = "4fda34cd-6002-4534-bc56-066ae32a72c7"  # Action ID for Generate Enhanced Images

# Construct the input payload based on the action's requirements
payload = {
    "width": 1024,
    "height": 1024,
    "prompt": "A photo of TOK standing next to a bonfire, animal crossing, hands in pockets",
    "refine": "expert_ensemble_refiner",
    "loraScale": 0.6,
    "scheduler": "K_EULER",
    "guidanceScale": 7.5,
    "applyWatermark": False,
    "inferenceSteps": 75,
    "negativePrompt": "realistic",
    "promptStrength": 0.7,
    "numberOfOutputs": 4,
    "highNoiseFraction": 0.8
}

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 snippet:

  • Replace YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key.
  • The action_id variable holds the ID for the Generate Enhanced Images action.
  • The payload variable structures the input JSON according to the action's schema.

Conclusion

The sinazar/campfire-tiger3 Cognitive Actions, particularly the Generate Enhanced Images action, offer developers a powerful toolset for creating and refining images. By leveraging customizable parameters and advanced techniques, you can elevate your application's visual content with ease. Consider exploring additional use cases, such as integrating these actions into creative platforms, e-commerce sites, or marketing campaigns to fully harness their potential.

← Back to All Articles