Flux Image Generator

Different tasks call for different models, and FlowHunt is committed to giving you the best of AI without the need to sign up for countless subscriptions. Instead, you get dozens of text and image generator models in a single dashboard. The Image Generator type of components houses image models grouped by provider, allowing you to generate images from text prompts.

What is Flux?

Flux is an innovative AI research company known for its advancements in generative modeling, particularly in the field of image synthesis and manipulation.

One of Flux’s notable contributions is the development of FluxCapacitor, a versatile generative model architecture that supports various applications such as image inpainting, style transfer, and super-resolution. This model framework has been praised for its ability to generate high-quality images from minimal input and its flexibility in adapting to different artistic styles and tasks.

It’s hard to pinpoint what Flux models are good for, since the company keeps introducing new innovative models of varying strengths and capabilities. You can enjoy a whopping 9 Flux models in FlowHunt.

Flux Image Generator Settings

The Guidence parameter controls how closely the generated image adheres to the input prompt. Higher values result in images that more strictly follow the prompt, while lower values give the model greater creative freedom. The default value in FlowHunt is 3, balancing adherence and creativity.

Number of outputs means how many pictures to generate from a single prompt. This way, you can pick the best option without having to send the prompt repeatedly. The default in FlowHunt is 1 output, and the value typically ranges from 1 to 4. Don’t generate too many unnecessary outputs, as this can get costly quite fast.

Image ratio defines the width-to-height proportion of the generated image, influencing its overall composition. Common aspect ratios include 1:1 for square images and 16:9 for widescreen formats. Flux models support a variety of popular aspect ratios, allowing for flexibility in image dimensions.

Tool Description: This optional message lets the AI Agent know how to use this tool. If you’re connecting as an Agent tool, here you can input instructions to let the Agent know how to use this tool.

Tool Name: The name by which the agent will refer to this tool. This name is optional and helps you better understand verbose reporting.

Verbose: Check if you want to see a detailed report of what the agent is doing and thinking during the generation process.

Model

This is the model picker. Here, you’ll find all the supported models from Flux:

• Flux Pro: A proprietary model accessible via API, designed for high-fidelity image generation with advanced features.
• Flux 1.1 Pro: An enhanced version of Flux Pro, released on October 2, 2024, offering improved image quality and performance.
• Flux 1.1 Pro ultra: Introduced on November 6, 2024, this model can generate images up to 4 megapixels without compromising speed, making it suitable for high-resolution outputs.
• Flux Schnell: An open-source model released under the Apache License, optimized for speed and efficiency in image generation tasks.
• Flux Depth Pro: A model that utilizes depth information to guide image generation, allowing for the creation of images with specific poses, backgrounds, and objects.
• Flux Depth Dev: A developer-focused version of Flux Depth, available for experimentation and integration into various applications.
• Flux Canny Pro: Employs Canny edge detection to guide image generation, enabling the model to follow specific lines and shapes for precise outputs.
• Flux Canny Dev: A developer-oriented version of Flux Canny, intended for testing and development purposes.
• Flux Dev: A source-available model under a non-commercial license, providing developers with access to Flux’s capabilities for research and development.

Component Handles

Input Handles

Input Prompt: Since AI won’t just start generating without any instructions, there’s a green handle for inputting prompts. This handle can take any text format. This means human prompts via Chat Input and prompts from any other component that outputs text.
Image: Flux models can use your images as guidance. For example, to copy the style or to redraw your photos into digital art. This input option only works with Canny, Depth and Dev models.

Output Handles

Tool : As a tool for AI agents. This way, the Agent decides when it needs the tool, can call on it, and give it prompts.
Image : Outputting the picture. For more straightforward usage, this image acts as text and can simply be sent to output or other components for further processing.

How To Add The Flux Image Generator To Your Flow

This component is a generator, meaning AI does its magic in this box. It creates pictures based on input and can output the pictures to chat or other components.

Let’s create the simplest possible Flow to see the component in action. You can think of it as a basic connection to Flux. This Flow will allow you to send prompts in chat and have the Flow respond with generated images.

This simple Flow includes:

• Chat input: Represents the message a user sends in chat.
• DallE Image Generator creates images based on user prompts.
• Chat output: Represent the chatbot’s final response.

This use case opens up the doors to various other scenarios. These three components can be a part of a large workflow, where Flux is just one of the components being called and managed by an autonomous AI agent to create and place just the right images automatically.

Let’s test it out. We’ll send this simple prompt in chat:

A calico kitten riding a bicycle

We’ll use default settings of 1:1 ratio with the Flux Schnell model. Here’s the generated image: