How to Set up Fooocus with API Configuration on AWS - Developer Guide

Welcome to the Fooocus 2.0 Setup Guide, your key to unlocking the full potential of our AI-powered image creation tool. In this step-by-step guide, we'll walk you through the seamless installation process.

Blog

How to 1 Click Install Fooocus AI on AWS: The Ultimate Image Generator

Explore Fooocus, the forefront of AI-driven image generation, offering unparalleled efficiency and a user-friendly interface. Perfect for creatives in the UK, USA, Europe, Ireland, Singapore, and Thailand, embrace the future of digital artistry and step into a new era of image creation.

Meetrix.IO | Kelum Sampath

Learn more on Linkedin

How to Simply Set Up Fooocus 2.0 in Self Hosted on AWS

In the digital frontier, AI image generation stands as a testament to how far technology has advanced in understanding and replicating the nuances of human creativity. This rapidly advancing field allows us to convert complex ideas into vivid visuals, streamlining workflows across various industries.

Meetrix.IO | Published Nov 15, 2023

Launching the AMI

Step 1: Find and Select 'Fooocus 2.0' AMI

1. Log in to your AWS Management Console.
2. Navigate to the "Fooocus 2.0" in AWS Marketplace.

Step 2: Initial Setup and Configuration

1. Click the "Continue to Subscribe" button.
2. After subscribing, you will need to accept the terms and conditions. Click on "Accept Terms" to proceed.
3. Please wait for a few minutes while the processing takes place. Once it's completed, click on "Continue to Configuration".
4. Select the "CloudFormation Template for fooocus" as the fulfilment option and choose your preferred region on the "Configure this software" page. Afterward, click the "Continue to Launch" button.
5. From the "Choose Action" dropdown menu in "Launch this software" page, select "Launch CloudFormation" and click "Launch" button.

Create CloudFormation Stack

Step 1: Create Stack

1. Ensure the "Template is ready" radio button is selected under "Prepare template".
2. Click "Next".

Step 2: Specify Stack Options

1. Provide a unique "Stack name".
2. Provide the "Admin Email" for SSL generation.
3. For "DeploymentName", enter a name of your choice.
4. Provide the domain name for "FooocusDomainName". (Fooocus will automatically try to setup SSL based on provided domain name, if that domain is hosted on Route 53. Please make sure your domain name is hosted on Route 53. If it's unsuccessful then you have to setup SSL manually.)
5. Choose an instance type, "FooocusInstanceType" (Recommended: g4dn.2xlarge).
6. Select your preferred "keyName".
7. Set "SSHLocation" as 0.0.0.0/0.
8. Keep "SubnetCidrBlock" as 10.0.0.0/24.
9. Keep "VpcCidrBlock" as 10.0.0.0/16.
10. Click "Next".

Step 3: Configure Stack Options

1. Under "Stack failure options", select "Roll back all stack resources".
2. Click "Next".

Step 4: Review

1. Review and verify the details you've entered.

2. Tick the box that says, "I acknowledge that AWS CloudFormation might create IAM resources with custom names".

3. Click "Submit".

Afterward, you'll be directed to the CloudFormation stacks page. You can easily locate the corresponding stack by searching for the stack name you entered in Step 2. Please wait for 5-10 minutes until the stack has been successfully created. Afterward, you can click the "Refresh" button under the "Stacks" section.

Access Fooocus Dashboard

Method 1: Using Public IP

Click the link located under the "DashboardUrlIp" section in the "Outputs" tab. This will direct you to the Fooocus Dashboard.

Method 2: Using Domain

1. Copy the Public IP address indicated as "PublicIp" in the "Outputs" tab.

2. Go to AWS "Route 53" and navigate to "Hosted Zones".
3. From there, select the domain you provided to "FooocusDomainName".

4. Click "Edit record" in the "Record details" and then paste the copied "PublicIp" into the "value" textbox and click "Save".

5. Open a new tab and navigate to the "FooocusDomainName" to access the Fooocus dashboard.

Generate SSL Manually

Fooocus will automatically try to setup SSL based on the provided domain name, if that domain is hosted on Route 53. If it's unsuccessful then you have to setup SSL manually. Admin Email is required to generate SSL certificates.

Step 1: Point Domain Name to Server IP

Follow steps 1 to 4 in the "Method 2: Using Domain" section mentioned above, under "Access Fooocus Dashboard", to point the domain name to the server's IP.

Step 2: Log in to the Server

1. Copy the Public IP address indicated as "PublicIp" in the "Outputs" tab.

2. Open the terminal and go to the directory where your private key is located.
3. Paste the following command into your terminal and press Enter:

ssh -i <your key name> ubuntu@<Public IP address>

Type "yes" and press Enter. This will log you into the server.

Step 3: Generate SSL

Paste the following command into your terminal and press Enter:

sudo /root/certificate_generate_standalone.sh

Shutting Down

1. Click the link labeled "Fooocus" in the "Resources" tab to access the EC2 instance. You will be directed to the Fooocus instance in EC2.

2. Select the Fooocus instance by marking the checkbox and click "Stop instance" from the "Instance state" dropdown. You can restart the instance at your convenience by selecting "Start instance".

Remove Fooocus

Delete the stack that has been created in the AWS Management Console under 'CloudFormation Stacks' by clicking the 'Delete' button.

API Documentation

1. Generate Text-to-Image

Generate images based on the provided prompt.

Endpoint: /api/v1/generation/text-to-image
Method: POST

Request Body (Enter the text in 'prompt'):

{
  "prompt": "car",
  "negative_prompt": "",
  "style_selections": [
    "Fooocus V2",
    "Fooocus Enhance",
    "Fooocus Sharp"
  ],
  "performance_selection": "Speed",
  "aspect_ratios_selection": "1152*896",
  "image_number": 1,
  "image_seed": -1,
  "sharpness": 2,
  "guidance_scale": 4,
  "base_model_name": "juggernautXL_version6Rundiffusion.safetensors",
  "refiner_model_name": "None",
  "refiner_switch": 0.5,
  "loras": [
    {
      "model_name": "sd_xl_offset_example-lora_1.0.safetensors",
      "weight": 0.1
    }
  ],
  "advanced_params": {
    "adaptive_cfg": 7,
    "adm_scaler_end": 0.3,
    "adm_scaler_negative": 0.8,
    "adm_scaler_positive": 1.5,
    "canny_high_threshold": 128,
    "canny_low_threshold": 64,
    "controlnet_softness": 0.25,
    "debugging_cn_preprocessor": false,
    "debugging_inpaint_preprocessor": false,
    "disable_preview": false,
    "freeu_b1": 1.01,
    "freeu_b2": 1.02,
    "freeu_enabled": false,
    "freeu_s1": 0.99,
    "freeu_s2": 0.95,
    "inpaint_disable_initial_latent": false,
    "inpaint_engine": "v1",
    "inpaint_erode_or_dilate": 0,
    "inpaint_respective_field": 1,
    "inpaint_strength": 1,
    "invert_mask_checkbox": false,
    "mixing_image_prompt_and_inpaint": false,
    "mixing_image_prompt_and_vary_upscale": false,
    "overwrite_height": -1,
    "overwrite_step": -1,
    "overwrite_switch": -1,
    "overwrite_upscale_strength": -1,
    "overwrite_vary_strength": -1,
    "overwrite_width": -1,
    "refiner_swap_method": "joint",
    "sampler_name": "dpmpp_2m_sde_gpu",
    "scheduler_name": "karras",
    "skipping_cn_preprocessor": false
  },
  "require_base64": false,
  "async_process": false,
  "webhook_url": "string"
}

Response Body:

[
  {
    "base64": null,
    "url": "http://fooocus-test-prod.meetrix.io/api/files/2024-02-16/d0c43ae9-a4fa-4111-ac86-3976fcdaf3ea.png",
    "seed": "7157889350071648458",
    "finish_reason": "SUCCESS"
  }
]

2. List Models

Retrieves a list of available models.

Endpoint: /api/v1/engines/all-models
Method: GET

Response Body:

{
  "model_filenames": [
    "juggernautXL_version6Rundiffusion.safetensors",
    "sd_xl_base_1.0_0.9vae.safetensors",
    "sd_xl_refiner_1.0_0.9vae.safetensors"
  ],
  "lora_filenames": [
    "sd_xl_offset_example-lora_1.0.safetensors"
  ]
}

You can find out the full API documentation here https://github.com/konieshadow/Fooocus-API/blob/main/docs/api_doc_en.md

Upgrades

When there is an upgrade, we will update the product with a newer version. You can check the product version in AWS Marketplace. If a newer version is available, you can remove the previous version and launch the product again using the newer version. Remember to backup the necessary server data before removing.

Troubleshoot

1. If you face the following error, please follow https://meetrix.io/blogs/increase-aws-vcpu-quota/ blog to increase vCPU quota.

2. If you face the following error (do not have sufficient <instance_type> capacity...) while creating the stack, try changing the region or try creating the stack at a later time.

3. If you face the below error, when you try to access the API dashboard, please wait 5-10 minutes and then try.

Conclusion

The Fooocus 2.0 Setup Guide equips you with the knowledge to seamlessly install and unlock the full potential of this AI-powered image creation tool. Fooocus excels in AI-driven image generation with its unique inpainting algorithms, image prompt enhancements, versatile model support, and robust API capabilities. Offering a user-friendly yet powerful platform for both novice and advanced creators, Fooocus simplifies the creative process, allowing users to produce stunning, relevant images effortlessly. As you follow this guide, you'll discover why Fooocus is rapidly becoming the preferred choice for AI-generated imagery among beginners and seasoned professionals alike.

Technical Support

Reach out to Meetrix Support (aws@meetrix.io) for assistance with Fooocus issues.