Unleashing Creativity: Generate Images with Inpainting Using datiggadev/flux_datigga-selfie Actions

22 Apr 2025
Unleashing Creativity: Generate Images with Inpainting Using datiggadev/flux_datigga-selfie Actions

In the realm of image generation, the datiggadev/flux_datigga-selfie API offers powerful Cognitive Actions designed to create stunning visuals through advanced techniques like inpainting. This set of pre-built actions allows developers to customize images based on detailed prompts, adjust parameters, and produce high-quality outputs across various formats.

By integrating these Cognitive Actions into your applications, you can elevate your projects with dynamic image generation capabilities, making it easier than ever to create unique and engaging content.

Prerequisites

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

  • An API key for the Cognitive Actions platform, which will be used for authentication.
  • Familiarity with JSON for structuring requests and handling responses.

Authentication typically requires you to pass your API key in the headers of your requests, allowing you to securely access the image generation functionalities.

Cognitive Actions Overview

Generate Image with Inpainting

Purpose

This action allows you to generate images using inpainting techniques, which enables the customization of images based on specified prompts and parameters. You can adjust factors like model selection, aspect ratios, and image formats to create highly tailored visuals.

Input

The input for this action requires a prompt and may include several optional parameters to enhance customization. Below is the structured schema:

{
  "prompt": "string", // Required
  "mask": "string", // Optional, URI for inpainting
  "seed": "integer", // Optional, for reproducibility
  "image": "string", // Optional, input image for inpainting
  "model": "string", // Optional, model selection (default: "dev")
  "width": "integer", // Optional, width in pixels
  "height": "integer", // Optional, height in pixels
  "extraLora": "string", // Optional, load additional LoRA weights
  "loraScale": "number", // Optional, scale for LoRA application
  "megapixels": "string", // Optional, approximate megapixels
  "aspectRatio": "string", // Optional, aspect ratio (default: "1:1")
  "imageFormat": "string", // Optional, output format (default: "webp")
  "imageQuality": "integer", // Optional, quality setting (default: 80)
  "guidanceScale": "number", // Optional, guidance scale (default: 3)
  "optimizeSpeed": "boolean", // Optional, toggle speed optimization
  "extraLoraScale": "number", // Optional, scale for extra LoRA
  "inferenceSteps": "integer", // Optional, number of denoising steps (default: 28)
  "promptStrength": "number", // Optional, strength when using img2img
  "numberOfOutputs": "integer", // Optional, number of outputs (default: 1)
  "disableSafetyChecker": "boolean" // Optional, toggle safety checker
}

Example Input

Here is an example of the JSON payload needed to invoke the action:

{
  "model": "dev",
  "prompt": "photo of tgga as classic circus clown, highly detailed",
  "loraScale": 1,
  "megapixels": "1",
  "aspectRatio": "1:1",
  "imageFormat": "webp",
  "imageQuality": 80,
  "guidanceScale": 3,
  "optimizeSpeed": false,
  "extraLoraScale": 1,
  "inferenceSteps": 28,
  "promptStrength": 0.8,
  "numberOfOutputs": 1
}

Output

Upon successful execution, the action typically returns a URL to the generated image. Here's an example of the output you might receive:

[
  "https://assets.cognitiveactions.com/invocations/32a6c490-3e11-4aba-9fd4-75607f270c54/3ac988c0-57e4-4a7d-bf0b-104cbd9f2a7a.webp"
]

Conceptual Usage Example (Python)

Below is a conceptual Python code snippet demonstrating how to call the Cognitive Actions execution endpoint for this 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 = "c0a1511d-45aa-4ab6-8f62-0d67f7e57dbe" # Action ID for Generate Image with Inpainting

# Construct the input payload based on the action's requirements
payload = {
    "model": "dev",
    "prompt": "photo of tgga as classic circus clown, highly detailed",
    "loraScale": 1,
    "megapixels": "1",
    "aspectRatio": "1:1",
    "imageFormat": "webp",
    "imageQuality": 80,
    "guidanceScale": 3,
    "optimizeSpeed": False,
    "extraLoraScale": 1,
    "inferenceSteps": 28,
    "promptStrength": 0.8,
    "numberOfOutputs": 1
}

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, replace YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key. The payload variable contains the input structure defined earlier. The response will provide a link to the generated image, allowing you to easily integrate this functionality into your application.

Conclusion

The Generate Image with Inpainting action from the datiggadev/flux_datigga-selfie API opens up a world of creative possibilities for developers. By leveraging this Cognitive Action, you can create unique images tailored to your specific needs, enhancing your applications with dynamic visual content.

Next steps could include experimenting with different prompts, adjusting parameters for optimal results, or integrating other Cognitive Actions to further enrich your image generation capabilities. Happy coding!

← Back to All Articles