Generate Stunning Images with Inpainting Using Jonathan Flux3 Cognitive Actions

22 Apr 2025
Generate Stunning Images with Inpainting Using Jonathan Flux3 Cognitive Actions

In the realm of image generation, the Jonathan Flux3 Cognitive Actions provide powerful capabilities that allow developers to create and manipulate images using advanced techniques such as inpainting and image-to-image conversion. By utilizing pre-built actions designed for various needs, you can streamline the image generation process and focus on integrating these capabilities into your applications. In this post, we will explore how to leverage the Generate Image with Inpainting action, which enables you to generate images with customizable parameters and quality settings.

Prerequisites

To get started with the Cognitive Actions from the Jonathan Flux3 spec, you will need an API key to authenticate your requests. Typically, this involves passing the API key in the headers of your HTTP requests. Ensure that you have access to the Cognitive Actions platform and have set up your environment to make API calls.

Cognitive Actions Overview

Generate Image with Inpainting

The Generate Image with Inpainting action allows you to create images using inpainting techniques and image-to-image transformations. This action is particularly useful for developers looking to generate unique images based on specific prompts or modify existing images by applying masks. You can adjust various parameters such as model selection, image specifications, and output quality.

Input

The action requires a set of parameters structured in a JSON object. The only required parameter is prompt, while other parameters are optional and fine-tune the image generation process.

{
  "prompt": "A photo of JONSHUBJAM3 as a hobbit.",
  "loraScale": 1,
  "modelType": "dev",
  "numOutputs": 1,
  "guidanceScale": 3.5,
  "outputQuality": 90,
  "extraLoraScale": 1,
  "promptStrength": 0.8,
  "imageAspectRatio": "1:1",
  "imageOutputFormat": "webp",
  "numInferenceSteps": 28
}
  • Required Fields:
    • prompt: The text input that describes what the image should depict.
  • Optional Fields:
    • mask: URI for the image mask used in inpainting mode.
    • seed: Integer value for a reproducible random seed.
    • image: URI for the input image for image-to-image conversion.
    • width: Width of the generated image (only if custom aspect ratio is applied).
    • height: Height of the generated image (only if custom aspect ratio is applied).
    • goFast: Boolean to use a speed-optimized model.
    • numOutputs: Number of output images to generate.
    • guidanceScale: Adjusts the guidance during the diffusion process.
    • outputQuality: Quality level for the output images.
    • imageAspectRatio: Aspect ratio of the generated image.
    • imageOutputFormat: Format for the output image (webp, jpg, png).
    • numInferenceSteps: Number of denoising steps for image generation.

Output

The action returns a URL pointing to the generated image. Here’s an example of the expected output:

[
  "https://assets.cognitiveactions.com/invocations/91cc40c3-8cad-497b-aff9-a242d97253c9/d226abd5-1fd5-4f97-9e1a-f543c8c2dbbe.webp"
]

Conceptual Usage Example (Python)

Here’s how you can invoke the Generate Image with Inpainting action using a conceptual Python snippet. This example focuses on structuring the input JSON payload correctly.

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 = "b979d557-de39-442c-ba39-1fc9cc873f55"  # Action ID for Generate Image with Inpainting

# Construct the input payload based on the action's requirements
payload = {
    "prompt": "A photo of JONSHUBJAM3 as a hobbit.",
    "loraScale": 1,
    "modelType": "dev",
    "numOutputs": 1,
    "guidanceScale": 3.5,
    "outputQuality": 90,
    "extraLoraScale": 1,
    "promptStrength": 0.8,
    "imageAspectRatio": "1:1",
    "imageOutputFormat": "webp",
    "numInferenceSteps": 28
}

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 the YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key. The action ID and input payload are structured according to the requirements specified for the action.

Conclusion

The Generate Image with Inpainting action from the Jonathan Flux3 Cognitive Actions offers developers a robust tool for creating and refining images through customizable prompts and parameters. By integrating this action into your applications, you can unlock creative possibilities and enhance user experiences. Consider exploring other capabilities within the Cognitive Actions suite to further enrich your projects!

← Back to All Articles