PiAPI
HomeWorkspace
HomeWorkspace
Join Discord
  1. Get Started
  • Get Started
    • Overview
    • Quickstart
    • Make Instruction: How to Use PiAPI to Build a Workflow on Make?
  • Endpoints
    • Song(Udio)
      • Song API Task Creation Examples
      • [Udio] Song Extend
      • Get Task
      • Create Task
      • [Udio] Generate Lyrics
    • Kling
      • Lipsync With PiAPI Kling API Examples
      • Motion Brush With PiAPI Kling API Example
      • Kling Elements Video Generation API
      • Kling Effects Video Generation
      • Cancel Task
        • Cancel Tasks
        • Cancel Task
      • Get Task
      • Create Task
      • Kling Virtual Try-On
    • Hailuo
      • Hailuo Director Mode Example
      • Generate Video
      • Get Task
    • Flux
      • Flux with LoRA and Controlnet
      • Available LoRA and Controlnet
      • Flux API with Redux Variation, Fill, Inpaint and Outpaint
      • Create Task
        • Text to Image
        • Image to Image
      • Get task
    • AI Hug
      • Get Task
      • Create Task
    • LLM
      • Use Cases for GPT-4o Image API
      • How To Avoid Timeouts in Completion API
      • GPT-4o Image Generation API
      • LLM API | Basic Completions
      • Get Task
    • Midjourney
      • PiAPI Penalties on Midjourney Usage
      • Detailed Explaination on Midjourney Task Result
      • Midjourney V7 API Instructions
      • Create Task
        • Imagine
        • Upscale
        • Variation
        • Reroll
        • Describe
        • Seed
        • Blend
        • Inpaint
        • Outpaint
        • Pan
      • Cancel Task
        • Cancel Task
        • Cancel Tasks
      • Get Task
    • Faceswap
      • Multi Faceswap
      • Image Faceswap
      • Video Faceswap
      • Get Task
    • TTS
      • Zeroshot Text-to-Speech F5-TTS
      • Get Task
    • Trellis
      • Create Task
      • Get Task
    • Luma Dream Machine
      • Cancel Task
        • Cancel Tasks
        • Cancel Task
      • Create Task
      • Get Task
    • WanX
      • Generate WanX Task with LoRA Using PiAPI
      • Available LoRA Types for Wanx
      • Use Cases for Wanx LoRA
      • Use Cases for Wanx Control Camera
      • Create Task
      • Get Task
    • Skyreels
      • Create Task
      • Get Task
    • Framepack
      • Create Task
      • Get Task
    • Hunyuan Video
      • How to Make a Hunyuan API Call
      • Get Task
      • Generate Video
    • Mmaudio
      • Get Task
      • Generate Audio
    • DiffRhythm
      • Generate Audio
      • Get Task
    • Tools
      • File Upload API
      • Video Upscale
      • Video Upscale-Get Task
      • Remove Background API
      • Remove Background-Get Task
      • Segment With Prompt API
      • Segment With Prompt API-Get Task
      • Image Upscale(Super Resolution) API
      • Image Upscale-Get Task
    • PiAPI Account Management
      • PiAPI Account Info
      • Task List Info
      • User Task History
  • Resources
    • Change Log
    • Output Storage
    • Unified API Schema
    • Webhook
    • Bulk Generation Service
    • Billings
    • PiAPI MCP Server
    • Workspace Manual
      • Host-your-account (HYA) | Back-up Account
      • Host-your-account (HYA) | Debug Checklist
      • Host-your-account (HYA) | Connected Account Status
    • Announcements
      • PiAPI 2025 January 1st Pricing Update
  • Legacy Documentation
    • Midjourney
      • Midjourney Webhook
      • Imagine
      • Reroll
      • Upscale
      • Variation
      • Inpaint
      • Outpaint
      • Pan
      • Describe
      • Blend
      • Seed
      • Fetch
      • Multi Fetch
      • Cancel
    • Face Swap
      • Video Faceswap
      • Multi-face-swap
      • Fetch
    • Dream Machine
      • Video Generation
      • Video Extend
      • Get Video Generation
    • Kling
      • Video Generation
      • Video Extend
      • Get Video Generation
  1. Get Started

Make Instruction: How to Use PiAPI to Build a Workflow on Make?

Intorduction#

Hey there! Recently, to help more content creators easily use PiAPI for their projects, Flux by PiAPI has officially launched on the Make platform!
For content creators or anyone without coding background who find API concepts challenging, this documentation will use visual guides to help you overcome these challenges.
🙋Here’s what we’ll cover step by step listed as follows:
1.
Finding PiAPI's Flux Modules on Make Platform
2.
Calling APIs on the PiAPI Platform
3.
Understanding PiAPI's Endpoint Structure
4.
Using the Flux App (PiAPI on Make) and Integrating It into your Workflow
5.
Adjusting Module Parameters and Their Meanings: Flux Module Selection and Parameter Configuration Guide
6.
Building a Simple Workflow Using PiAPI on Make
💡 If you have a technical background, you can quickly grasp Make's functionality and start building workflows to experiment with creative ideas. 🙌
We would be glad to see you:
Share your workflow output on social media with us
Join our Discord to discuss!
All in all, we would be pleasant to see you share your workflow output in any social media with us and join our discord to make a discussion!

How to find PiAPI's Flux Modules on Make Platform?#

Log in to the Make platform, locate Scenarios in the left Dashboard, click Create Apps, and you will enter the main workflow builder interface.
Then search for "PiAPI/Flux" and you'll see the Flux API modules available for use.
image.png
Now that you've learned how to find PiAPI's Flux Module on Make, let's explore PiAPI's endpoint structure and walk through the process of calling Flux APIs. This knowledge will help you:
Better understand the architecture behind each module
Confidently configure parameters when building workflows
Maximize the potential of PiAPI's capabilities in Make
We'll demonstrate the API calling process step-by-step, giving you practical insights to apply directly in your workflow development.

Understanding PiAPI's Endpoint Structure#

Before organizing your workflow automation, let's walk through the key concepts needed for successful API calls with PiAPI. You should familiarize yourself with:

Core Concepts#

API Structure and its components
Purpose of each structural element
Endpoint Types and their functions
Parameter Definitions and requirements
Best Practices for executing flawless API calls
This foundation will ensure you can effectively work with PiAPI's endpoints when building your workflows.
image.png
An endpoint in PiAPI consists of three core components:

1. URL#

The service path that directs your request.
Key Requirement: You must use the correct address to successfully reach PiAPI.
HTTP Methods:
POST - Used when you need to create a task.
GET - Used when retrieving task response.
image.png
These methods (POST and GET) define your action type when making API calls. And there are some differences between the urls of different http methods.
If you want to make an api call to make an API call, then you should choose POST. In this way could you send your request to Flux API. If you want to fetch your response, you should choose GET and could just send URL and Header Params then you could get your response (especially when you need to check or use an output in your workflow) in a specific task you have initiated.

2. Header Params#

Usually conludes your X-API-Key.

3. Body Params#

Model
Task-type
Input
prompt
width
height
......
Tips: Usually the input params are mainly based on the model and task-type. You could check the section Flux Module Selection and Parameter Configuration Guide to check the params that could be concluded when you choose different task-type based on your need.
Now, let's explore API calls on PiAPI to deepen your understanding of Make Modules.

How to Make an API Call in PiAPI#

In PiAPI, you have two methods to call Flux APIs (applicable to other APIs as well):
1.
Using Playground: Fill in the required parameters for direct execution.
image.png
2.
Via Run API: Submit your API call, then retrieve the task results from the respective model's Task History section.
image.png
When using the Run API to call PiAPI platform APIs, you'll have a broader range of options. As mentioned earlier regarding API call structures, you can:
1.
Refer to the parameter specifications below for task_type selection
2.
Configure input parameters according to your requirements
Through understanding the constructure of every API reuqest, you could mainly create an API call on your own. Isn't that diffucult, right? 💪
Now you've understood how to create an API call on PiAPI, next let's learn how to make an API call in Make.

How to make an API call in Make?#

According to http methods which depends on whether you want to create a task (POST) or get your task response (GET).

Set up a POST Module#

image.png
1.
Connect your PiAPI account
Make sure you're logged in first.
2.
Prepare your request
Create a JSON module (this is where you type your settings). Usually a JSON Module contains the structure of an endpoint's body including model, task-type and input. In this step, you need to construct your data structure based on the endpoint on your own.
image.png
image.png

Set up a GET request#

1.
Connect your PiAPI account
Ensure you're properly logged in.
2.
Select the API call node
Choose "Make an API Call" from available options
3.
Configure the request
URL: Enter /v1/task/ followed by your specific task_id
(Example: /v1/task/12345)
Method: Select GET
4.
Run the request
Execute to retrieve your task results
image.png

Flux Node Selection and Parameter Configuration Guide#

What is LoRA & Accessing LoRA Options#

Simply put, LoRA is a style filter for AI art. To choose a LoRA, check the available styles in PiAPI's Flux Documentation.
Check this page to get your ideal style of LoRA.
image.png

What is ControlNet & Accessing ControlNet Options#

ControlNet is a neural network structure designed to precisely control AI image generation by incorporating additional input conditions (e.g., edge maps, depth maps, human poses). It acts as a "steering wheel" for models like Stable Diffusion, ensuring generated images strictly adhere to structural constraints while following text prompts.
Check PiAPI's Flux Documentation to get ControlNet type.
Congratulations! Now that you understand both LoRA and ControlNet and know where to get the type list, you’re ready to explore beyond the PiAPI platform.
On Make, you can:
Select different task_type options to experiment with various LoRA and ControlNet combinations.
Customize these features based on your specific needs
Understanding this structure will empower you to generate higher-quality images!
Next, I’ll walk you through each module’s parameters. You’ll learn to:
Configure parameters effectively
Make optimized Flux API calls

Module Types and Param Configuration Setting#

Based on these instructions, you can understand the purpose of each module's parameters and adjust them as needed until they meet your requirements.

Extend an Image#

Expands the boundaries of an image. The user uploads an image, and the system generates new background or scenery based on the original content. Suitable for extending the image’s view into a broader scene.
image.png
Parameter NameDescriptionConstraints&Details
imageImage URLURL format.
promptContent to show in the extended partstring
outpaint_leftExpand canvas pixels to the leftTotal delta pixel size < 1024×1024
outpaint_rightExpand canvas pixels to the rightTotal delta pixel size < 1024×1024
outpaint_topExpand canvas pixels to the topTotal delta pixel size < 1024×1024
outpaint_bottomExpand canvas pixels to the bottomTotal delta pixel size < 1024×1024
denoiseControls noise/artifact removal strength in AI-generated imagesRange: 0.1 to 1
guidance_scaleAdjusts adherence between generated content and text promptRange: 1.5 to 5.0

Generate an Image from an Image#

Generates a new image based on an input image. The user uploads an existing image, and the system modifies or transforms it to generate a new version.
image.png
Parameter NameDescriptionConstraints&Details
imageImage URLURL format.
promptContent to display in the extended partstring
Example: "A lovely puppy"
negative_promptElements to avoid during generationstring
denoiseProportion of input images (controls noise removal)float (0.1-1.0)
guidance_scaleControls adherence between generated content and text promptfloat (1.5-5.0)

Generate an Image from an Image with LoRA#

Generates a modified image based on the LoRA model.
image.png
ParameterDescriptionConstraints&Details
ImageImage URLURL format.
PromptDesired image descriptionstring
Example: "A lovely puppy"
Lora_typeArt style selectionChoose from PiAPI's available LoRA options
Lora_strengthLoRA style intensity• Range: 0.1 (faint) to 1.0 (strong)
Guidance_scalePrompt adherence level• Range: 1.5 (creative) to 5.0 (strict)
Negative_promptElements to excludeOptional
Example: "blurry, distorted hands"
Width/HeightImage dimensionsIn pixels (e.g., 1024×768)
Max: 2048×2048

Generate an Image from Text#

Creates an image based on a text description.
image.png
Parameter NameDescriptionConstraints&Details
Batch_sizeBatch image generation count• Type: Integer
• Range: 1 to 4
• Default: 1
imageSource image URL• Type: String (URL format)
promptDescription of desired image contentstring
Example: "A lovely puppy"
negative_promptElements to avoid in generationOptional
guidance_scaleControls prompt adherence strengthRange: 1.5 to 5.0

Generate Image with Text based on Lora#

Creates an image based on a text description using LoRA for fine-tuned generation.
image.png
ParameterDescriptionDetails& Constraints
PromptDescribe your desired imagestring
Example: "A lovely puppy"
Lora_typeSelect an art styleAvailable PiAPI LoRA options
Lora_strengthLoRA style effect intensity• Default: 1.0 (maximum effect)
• Range: 0.1 (faint) - 1.0 (strong)
Guidance_scaleAI prompt adherence levelRange: 1.5 (random) - 5.0 (strict)
Negative_promptElements to excludeOptional
Example: "blurry, distorted hands"
Width/HeightOutput image dimensionsIn pixels (e.g., 1024×768)

Generate an Image with ControlNet and LoRA#

Generates an image using ControlNet and LoRA.
image.png
ParameterDescriptionConstraints&Details
ImageSource image URL(URL format)
PromptDesired image descriptionstring
Example: "A lovely puppy"
control_typeControlNet type• depth (default)
• soft_edge
• canny
• openpose
control_strengthControlNet effect intensityRange: 0.0 - 5.0
Lora_typeArt style selectionSelect from PiAPI's LoRA options
Lora_strengthLoRA style intensityRange: 0.1 (faint) - 1.0 (strong)
denoiseInput image proportionRange: 0.1 - 1.0
Guidance_scalePrompt adherence levelRange: 0.0 (random) - 5.0 (strict)

Generate a Variation of an Image#

Creates a new variation of an image based on the original input.
image.png
ParameterDescriptionConstraints&Details
Batch_sizeBatch image generation countDefault: 1
• Range: 1-4
imageSource image URL(valid URL)
promptContent for extended image partstring
Example: "A lovely puppy"
widthImage length in pixelsRecommended: ≤2048
heightImage width in pixelsRecommended: ≤2048
denoiseNoise removal strengthRange: 0.1-1.0
guidance_scalePrompt adherence strengthRange: 0.0-5.0

Remove the Background from an Image#

Removes the background from an image, leaving a transparent or solid-color background.
image.png
ParameterTypeDescriptionExample
imagestringSource image URLhttps://example.com/image.jpg

Restore an Image#

Restores a damaged image. The user uploads an image with some parts missing or damaged, and the system fills in these gaps based on the user's description.
image.png
ParameterDescriptionConstraints&Details
Batch_sizeBatch image generation countDefault: 1
• Range: 1-4
imageSource image URLvalid URL format
promptContent for extended image partstring
Example: "A lovely puppy"
denoiseNoise/artifact removal strengthRange: 0.1-1.0
guidance_scalePrompt adherence strengthDefault: 2.5
• Range: 0.0-5.0
service_modePayment method selection• ppu (pay-per-use)
• byoa (bring-your-own-account)

How to Build a Simple Workflow Using PiAPI on Make#

In this section, I will show you how to make a simple workflow with google sheets and Flux API.
image.png
First, input your parameters (such as prompt and lora_strength) into a Google Sheet based on your selected module type. Next, choose the Google Sheet trigger node . In this case, I've selected "Watch New Rows," which means the workflow will only execute when new row data is added. You may alternatively select other Google Sheet trigger nodes to suit different needs. The "Limit" setting determines how many rows are fetched per execution - I've configured it to retrieve only one row at a time.
image.png
image.png
Add a Flux node and input all required parameters.
image.png
The final step involves configuring a node to capture your output results—you can either check the small bubble notification in the upper-right corner after each workflow execution, or implement a more structured approach. For this example, I’ve selected "Update a Row" to automatically store the target image’s URL at the end of the input row upon workflow completion. This ensures seamless traceability by appending results directly to your Google Sheet.
image.png
Click Run Once
image.png
And you could check the url feedback.
image.png
image.png
And finally, you could fetch your output here. The workflow has been constructed successfully.

Join Our Discord#

Join our Discord community to showcase your work or get troubleshooting help.
Our contact details are available on the homepage.
image.png
We are looking forward to friendly and constructive discussions.
Plus, we would be so glad to see your creative workflows🙌!
Previous
Quickstart
Next
Endpoints