We have several new projects underway for our Home Lab and the services it provides. We’re adding a Home Lab Blog to share current projects and information! We are doing this to help our readers follow our progress and learn about our projects.
We are also enabling our readers to comment on our Blog. This enables us to answer questions and allows our readers to shape the direction of our Home Lab.
Projects We Are Working On
We have several new projects that we are working on, including:
An enterprise-level upgrade to our Core Network that enables high-availability and expanded capacity in our core network and Internet connectivity
Here are a few images from our in-progress projects.
Enterprise-Grade Core Rack UpgradeHigh-Availability Enterprise-grade Firewall and AggregationNext Generation AI Camera SystemEquipment for Fiber Network Upgrades
We hope that you’ll check our Home Lab Blog often and follow/comment on our progress!
We want to generate images locally. Several different applications can do this. To get started, we choose Stable Diffusion WebUI. This tool provides both text-image and image-image generation capabilities.
The WebUI part offers a user interface. Users can select image generation models, set up these models, and generate images from text.
# Location where AI tools are installedcd~/AI/stable-diffusion-webui# Log startup of Stable Diffusionecho"*** Launching Stable Difussion at `date` ***" >> ~/AI/ai.log# Run Stable Difussion using login/password; enable API./webui.sh--api--listen--gradio-auth <uid>:<password> >> ~/AI/ai.log
Basg Script to Launch Stable Diffusion
We also used the Mac Automator to launch it when logging in.
The final step is to allow access to the WebUI via a proxy host, our Nginx Proxy Manager.
Choosing and Downloading Models
Once Stable Diffusion is installed, you’ll want to download models to generate images. A good source for models is Hugging Face. Here’s a guide to choosing models. We have these models installed here –
The quality and look of the images you can generate using Stable Diffusion are endless. You can control how your images look and their content through the choices that you make in –
Heun Sampler – A high-quality image convergence algorithm
CFG Scale is set to 7 – sets how closely the image prompt is followed during image generation.
Image Size is 800×600 – the size of the images in pixels.
Steps is set to 50, which is the number of steps used to refine the image based on your prompt.
You can experiment with these settings using the Stable Diffusion WebUI. This will help you find a combination that produces good results on your setup.
I wanted to do a simple project using our home lab’s LLMs and image generation tools. This project will show the capabilities of our platform. We will write an AI-generated story.
Creating The Story
I used the deep-seek-r1:32b LLM to create the AI story. Here’s the prompt –
Please write me a story about a lovely home by a lake in New England. The scene is a fall with colorful fall foliage.
The prompt is all the information I gave the LLM running here on my Mac Mini system. The AI model generated the rest. The model was run using a combination of Open WebUI and Ollama.
Creating The Accompanying Image
I used the gemma3:27b model to generate a photo prompt using the story, I then used the image generation choice in Open WebUI to generate an image from the image prompt. Here’s my setup for image generation in Open WebUI.
The entire process was run locally on our Mac Mini system. It took less than 5 minutes to finish. How did my AI story turn out? You be the judge.
A Lovely Home by a Lake in New England
In the heart of New England’s serene countryside stands an enchanting cottage, its wooden walls weathered yet warm, wrapped in ivy that clings gracefully like an embrace from the earth. The house is nestled beside a tranquil lake, whose surface mirrors the vibrant tapestry of autumn hues reflected by the surrounding foliage.
The exterior of the cottage is painted in soft earth tones—muted greens and rusty reds—that harmonize perfectly with the season’s palette. A wraparound porch invites weary travelers to rest, its wooden slats worn smooth by time and weather. The roof, steeply pitched, seems to bow under the weight of golden leaves that have drifted down from the trees.
The lake is a mirror of the fall, its waters rippling gently with hues of amber, burgundy, and gold. Along its shores, birches stand tall, their trunks white as snow against the deepening forest backdrop. The air carries the crispness of approaching winter, yet the sun still warms the land, casting long shadows that dance across the landscape.
Inside the cottage, a crackling fire in the hearth fills the room with a comforting glow. Plush chairs and sofas are arranged around the fireplace, their upholstery soft to the touch, inviting stories to be shared. Large windows frame the view of the lake and forest, allowing sunlight to filter through, highlighting dust motes that twirl in the golden beams.
The scent of wood smoke mingles with the earthy aroma of damp leaves outside. A cat curls up by the fire, its fur as warm as the blankets draped over the furniture. The house is alive with the sounds of life: the occasional splash from the lake, birdsong echoing through the trees, and the distant crunch of leaves underfoot as someone takes a stroll through the woods.
Autumn activities are a delightful part of daily life here. Apples picked from nearby orchards are transformed into pies that fill the house with a sweet aroma. Walks through the forest reveal hidden treasures—acorns, pine cones, and the occasional squirrel darting across the path. The simplicity of these moments is cherished, each day a gift to be savored.
As evening approaches, the sky softens into hues of peach and lavender, casting a warm glow over the landscape. The lake reflects this twilight beauty, its surface still as if holding its breath. Inside the cottage, the fire casts dancing shadows on the walls, and the sounds of the day give way to the gentle rustle of leaves in the breeze.
This is a place where time moves slowly, where each season brings its own magic. In the fall, the cottage by the lake becomes a haven of warmth and beauty, a testament to nature’s artistry, inviting all who enter to find peace and wonder in the simple joys of life.
Open WebUI simplifies the process of embedding AI capabilities into web environments. It allows developers to create dynamic interfaces. Users can enter data, view AI-generated outputs, and visualize real-time results. Its open-source nature provides flexibility for customization, adapting to various AI project requirements, or integrating with popular machine learning libraries. (This summary was written, in part, using the deepseek-r1:32b model).
Open WebUI Installation
We installed Open WebUI as a Docker container using the approach outlined in the video below.
Encryption and reverse proxy implementation is handled using Traefik. A docker-compose template file for our installation follows. It can be installed as a Portainer stack.