Setup Guide · RAY-L v0.5

Get RAY-L
running in Blender.

RAY-L connects Blender with Stable Diffusion via ComfyUI – everything runs locally on your machine. No cloud, no subscription, no vendor lock-in – all components are open source. This guide walks you through the complete setup from scratch.

00

Requirements

01 Blender

Your homebase. You build and light your scene here — composition, camera, materials, geometry. Everything that defines where things are and how light hits them. RAY-L lives inside Blender as a panel in the Render Properties (the camera icon in the Properties Editor).

02 Stability Matrix

An installer and launcher for local AI tools. Getting Stable Diffusion and ComfyUI running on macOS without it means dealing with Python environments, dependency conflicts, and a lot of Terminal troubleshooting — not a fun afternoon. Stability Matrix handles all of that: it installs ComfyUI with a single click, manages model folders, and keeps everything up to date. During daily work you don't interact with it directly — you just launch ComfyUI from it and let it run in the background.

03 ComfyUI

The local engine that runs Stable Diffusion on your machine. It receives the render from Blender, processes it through the AI pipeline, and sends the result back. RAY-L communicates with ComfyUI via a local API at 127.0.0.1:8188 — no cloud, no data leaving your machine.

04 Juggernaut XL Ragnarok

The image generation model — the actual AI brain. It has been trained on a large dataset of photographic images and specializes in photorealistic output. When RAY-L sends your Blender render to ComfyUI, this model does the heavy lifting: replacing flat render materials with believable textures, atmosphere, and light.

05 ControlNet — Canny SDXL

This is what makes RAY-L fundamentally different from just prompting an AI. Without ControlNet, Stable Diffusion ignores your Blender geometry and generates whatever it wants. ControlNet extracts the exact edge structure from your render using a Canny algorithm — every wall, corner, and silhouette — and forces the AI to stay within that structure while generating new materials and atmosphere. Your composition stays exactly as you defined it in Blender. Only the surface quality changes.

06 RAY-L — the Add-on

The connector. RAY-L sits in Blender's Render Properties and handles everything between the two worlds: it reads the Render Result buffer, runs the Canny edge extraction locally via OpenCV, builds the ComfyUI workflow, sends both the render and the edge map, and displays the result back in the Blender Image Editor. You never leave Blender.

Blender

Version 5.0

blender.org/download

System

macOS · Apple Silicon

M1 / M2 / M3 / M4 — min. 16 GB RAM

Disk space

~12 GB free

ComfyUI + models

ComfyUI via

Stability Matrix

github.com/LykosAI

Checkpoint model

Juggernaut XL Ragnarok

~6.6 GB · safetensors

ControlNet model

controlnet-canny-sdxl

~2.3 GB · safetensors

Performance note

On a MacBook Air with 16 GB, expect 15–30 minutes per render at 1024×1024 with SDXL. For quick feedback during setup, work at 512×512 or 768×768. A Mac Studio with 64 GB reduces render times significantly.

01

Install Blender 5.0

1

Download Blender 5.0

Go to blender.org/download and download version 5.0 for macOS Apple Silicon. This is the only version RAY-L v0.5 has been tested with.

2

Move to Applications

Drag Blender.app into your /Applications folder. RAY-L expects Blender at this path for Python integration to work correctly.

3

Install OpenCV in Blender's Python

RAY-L uses OpenCV to extract Canny edges locally — without a separate ComfyUI preprocessor node. Open Terminal and run:

# Install OpenCV into Blender's bundled Python /Applications/Blender.app/Contents/Resources/5.0/python/bin/python3.11 \ -m pip install opencv-python-headless

If the install succeeds you'll see a confirmation line ending in Successfully installed opencv-python-headless.

4

Verify the installation

In the same Terminal window, run a quick check:

/Applications/Blender.app/Contents/Resources/5.0/python/bin/python3.11 \ -c "import cv2; print(cv2.__version__)"

Should print something like 4.13.0. If it does, you're good.

02

Install ComfyUI via Stability Matrix

Stability Matrix is the easiest way to install and manage ComfyUI on macOS. It handles dependencies, model folders and updates — no manual Python environment setup required.

1

Download Stability Matrix

Go to github.com/LykosAI/StabilityMatrix and download the latest macOS release. Open the DMG and move the app to your Applications folder.

2

Install ComfyUI as a package

Launch Stability Matrix. On first run it will ask where to store data — choose a location with enough disk space (at least 15 GB free). Then click Add Package → ComfyUI → Install.

Stability Matrix — Add Package screen Stability Matrix — ComfyUI package installation
3

Start ComfyUI and verify it's running

Click Launch in Stability Matrix. After a moment, ComfyUI's web interface opens in your browser at 127.0.0.1:8188. Leave this running whenever you use RAY-L — it must be active in the background.

4

Note the model folder path

By default, Stability Matrix stores everything at ~/DATEN/StabilityMatrix/Packages/ComfyUI/ — or wherever you chose during setup. You'll need the models/ subfolder in the next step.

03

Download Models

Two models are required. Place them in the correct subfolders inside your ComfyUI models directory.

1

Checkpoint — Juggernaut XL Ragnarok

This is the image generation model — the brain behind the photorealistic output. Download juggernautXL_ragnarokBy.safetensors (~6.6 GB) from Civitai and place it in:

~/[StabilityMatrix-folder]/Packages/ComfyUI/models/checkpoints/
Civitai download page for Juggernaut XL Ragnarok
2

ControlNet — Canny SDXL

This model locks Stable Diffusion to your Blender geometry. Download controlnet-canny-sdxl.safetensors (~2.3 GB) from Hugging Face and place it in:

~/[StabilityMatrix-folder]/Packages/ComfyUI/models/controlnet/
3

Restart ComfyUI

After placing both files, restart ComfyUI from Stability Matrix so the models are recognized. You can verify they appear in ComfyUI's model dropdown when you open the web interface at 127.0.0.1:8188.

04

Install the RAY-L Add-on

1

Download RAY-L

Download the RAY-L_v05.zip from this link. Don't unzip it — Blender installs directly from the ZIP file.

2

Install in Blender

Open Blender → Edit → Preferences → Add-ons → Install. Navigate to the downloaded ZIP and confirm. The add-on RAY-L: ComfyUI Bridge will appear in the list.

Blender Preferences — Add-ons — Install from ZIP
3

Enable the add-on

Check the checkbox next to RAY-L: ComfyUI Bridge to activate it. The RAY-L panel will now appear in Blender's Render Properties — the camera icon in the Properties Editor on the right side.

4

Verify the connection

Make sure ComfyUI is running. In the RAY-L panel, the status line should show ComfyUI connected at 127.0.0.1:8188. If it shows a connection error, check that ComfyUI is active in Stability Matrix.

05

Your First Render

The daily workflow is four steps. Always follow this exact order.

F12 Render in Blender
① Save as Reference
Canny Preview (optional)
② Send to ComfyUI
Result in Image Editor
1

Render your scene — F12

Press F12 to render with Cycles or EEVEE. Wait until the render is complete before moving to the next step. For a first test, keep resolution at 512×512 to keep waiting time short.

2

Save as Reference — Button ①

In the RAY-L panel, click ① Als Referenz speichern. This saves the current Render Result buffer as input for ComfyUI. Do this immediately after F12 — the buffer is overwritten once ComfyUI returns a result.

3

Configure Canny edge detection

In the RAY-L panel under Settings → ControlNet Canny, set the edge detection thresholds. The defaults work well for most scenes:

Canny Low: 50 — lower = more edges detected Canny High: 150 — higher = fewer edges detected

For clean architectural geometry, keep the defaults. If your render has fine surface detail (wood grain, fabric), raise Low to 80–100 to suppress noise. If important edges are missing, lower High to 100–120.

4

Optional: check the Canny preview

Click Canny Vorschau to see the edge map that will be sent as ControlNet input. Edges should be clean and clearly defined. Heavy noise means the render has too much texture detail at low resolution — try a slightly higher resolution.

RAY-L panel — Canny edge preview in the Blender Image Editor
5

Send to ComfyUI — Button ②

Click ② Referenz → ComfyUI. RAY-L sends the render and Canny edge map to ComfyUI, which runs Stable Diffusion with ControlNet. The result appears automatically in the Blender Image Editor when done.

Important — Step order

Always press F12 first, then immediately save as Reference (①). If you click Send (②) before saving, you'll be sending an old reference image — or none at all. The Render Result buffer is overwritten after each ComfyUI pass.

06

Key Settings Explained

These are the parameters you'll adjust most often. Start with the defaults, then tune from there.

Parameter Default What it does
ControlNet Strength 0.85 – 0.95 How strongly Blender geometry controls the result. 1.0 = exact geometry, 0.5 = loose suggestion. Start at 0.90.
Canny Low 50 Lower threshold for edge detection. Lower = more edges captured. Keep at 50 for most scenes.
Canny High 150 Upper threshold. Higher = only main structural edges. Raise if the edge map looks noisy.
Steps 20 – 25 More steps = better quality, longer render time. Use 10 steps for fast tests during setup.
CFG Scale 6.0 – 7.0 How strictly the prompt is followed. Above 10 often looks artificial. 7.0 is a reliable starting point.
Seed Random Random seed = different result each time. Fix a seed to reproduce a good result — read it from the status bar after a successful render.
Output size From Blender Automatically taken from Render Properties. Keep at 512×512 or 768×768 on MacBook Air for practical render times.

Prompt structure that works well for photorealistic architecture:

RAW photo, [scene description], [material/style], [light], Canon EOS R5, 85mm, photorealistic, 8k uhd, DSLR
Negative prompt: cartoon, illustration, drawing, painting, cgi, 3d render, smooth, plastic, artificial, overprocessed, anime, sketch

Sampler

The tested and recommended sampler is Euler Ancestral with 25 steps and CFG 7.0. This combination is what the Juggernaut XL Ragnarok model was optimized for.

Download RAY-L Beta → Tutorials on 3dwrkshp.com ↗