MicroCosmos & Beyond: LLM-Driven Proportion Engine (Krea2 + Ollama)
Welcome to MicroCosmos & Beyond, a highly calibrated, automated ComfyUI workflow designed to master extreme scaling, flawless proportions, and cinematic macro/fantasy environments.
Standard image models often break anatomy or warp scale when dealing with miniature subjects (like a 10cm pixie) or complex hybrid creatures. This workflow solves that issue permanently by using Ollama (LLM) as a real-time prompt translator that enforces physical scale mechanics, combined with the raw speed and aesthetic power of Krea2.
🚀 Key Features & Included Presets:
This workflow is a multi-functional prompt engine. Check the dropdown menu inside the PromptManager (Node 14) to switch between these custom-built engines:
The MicroCosmos Engine: Perfect for flawless 5-10cm miniature worlds, pixies, and small characters interacting with giant everyday human objects. Completely optimized using positive-only framing to prevent duplicate background faces or texturing errors.
The Hybrid Anatomy Engine (Default Load): Built for epic, heavy dark-fantasy spectacles, massive hybrid beasts, and detailed biomechanical cyborg transformations in the legendary style of Frank Frazetta and Greg Rutkowski.
⚠️ IMPORTANT: Quality & Upscaling Hint
All preview images shown here are 100% RAW generations straight out of the first KSampler pass to showcase the sheer power of the model's texturing capability.
Pro Tip: To inject micro-details, razor-sharp textures, and perfectly polished skin pores/eyes into your final art, add a FaceDetailer node (YOLOv5l) and a 2x Upscale pass at the end of the image output chain. The raw base generation provides the perfect mathematical foundation for stunning upscales!
📦 Prerequisites & Setup:
To make this workflow run out of the box, ensure you have the following assets ready:
1. Required Custom Nodes (Install via ComfyUI Manager):
comfyui-simple-ollama(For the Ollama LLM node integration)prompt-manager(To hold the System Prompt presets)comfyui-workflow-encrypt(For the LoraManager and custom ImageSavers)pysssss-comfyui(For the automated ShowText title-saver display)
2. Models & Settings:
Base UNET:
Krea2\krea2Turbo18For_v2.safetensors(Runs at an ultra-fast 4 steps!)Text Encoder:
qwen3vl_4b_fp8_scaled.safetensorsVAE:
krea2RealVae_v10.safetensorsLatent Resolution: Configured to a cinematic, ultra-wide 1728 x 720 aspect ratio.
LLM Model (Ollama):
gemma-4-abliterated(or any modern 8B model like Llama 3 / Mistral)Active LoRAs utilized in this stack:
krea2_turbo_4step_rank_64_lora(Strength: 1.00)zy_BackgroundDetail_K2(Strength: 0.50)Nijireol Krea2 v1 Ep5(Strength: 1.00)BeMyHero_-_LeaX_epoch_9(Strength: 1.00)
⚙️ How to Operate the Auto-Titling Engine:
The secondary Ollama node at the end of the chain automatically analyzes the positive prompt output and generates a clean, custom 1-2 word filename (e.g., "Crimson Cyborg") for your SaveImage directory, keeping your outputs highly organized without manual typing.
Load the .json file, choose your preset in Node 14, type a few short words, and let the LLM build your next masterpiece! Leave a review and share your generations in the gallery below.
Feel free to leave a review and share your tiny universe creations in the gallery below!
Description
"Initial Release - Stable build for Krea2 and Ollama prompt engineering."
Comments (3)
any chance you could upload without encryption node. for whatever reason I dont get the interface to come up. I downloaded the encryption software for linux, but I dont get the portion that allows to interact with.
Hi!
Thank you so much for reaching out and bringing this to my attention! I really appreciate your support and interest in my workflow.
The issue you are experiencing is actually not related to your Linux system or any missing encryption software. The error message is a bit misleading: "comfyui-workflow-encrypt" is simply the internal package name of a specific custom node extension within ComfyUI. Because your ComfyUI setup is missing these specific nodes, the interface fails to load the workflow properly.
Here is how you can easily fix this:
Via ComfyUI Manager (Recommended / Automatic):
Open your ComfyUI in your browser as usual.
Click on the Manager button in the menu on the right side.
Select the option Install Missing Custom Nodes.
ComfyUI will automatically search for the exact extensions used in my workflow. Simply install them and restart your ComfyUI afterward.
Manual Installation (If the Manager doesn't find them):
The workflow requires nodes for Ollama and Lora Management. If the automatic installation fails, you can manually clone the missing repositories into your ComfyUI/custom_nodes/ directory. The main missing packages are:
ComfyUI-SimpleOllama (used for the LLM text generation nodes)
comfyui-prompt-manager
Once these nodes are installed and ComfyUI is restarted, the interface will load the entire workflow smoothly on Linux! I truly hope these steps solve the issue for you—let me know if it works!
Answer is KI translated.
Update:
The mystery is solved! The error is caused by a custom node pack called ComfyUI-vslinx-nodes. The developer of this pack internally named their nodes "comfyui-workflow-encrypt", which is why ComfyUI is asking for it. It has nothing to do with Linux security software.
To fix it instantly, you just need to install this specific node pack. You can find it in the ComfyUI Manager by searching for ComfyUI-vslinx-nodes, or you can install it manually from her https://github.com/vslinx/ComfyUI-vslinx-nodes inside your ComfyUI/custom_nodes/ directory:
After installing it and restarting ComfyUI, the workflow will open perfectly!
I hope it works now. Good Luck and have Fun.