<h3 id="microcosmos-and-beyond:-llm-driven-proportion-engine-(krea2-+-ollama)">MicroCosmos &amp; Beyond: LLM-Driven Proportion Engine (Krea2 + Ollama)</h3>Welcome to MicroCosmos &amp; 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.<hr /><h3 id="key-features-and-included-presets:">🚀 Key Features &amp; Included Presets:</h3>This workflow is a multi-functional prompt engine. Check the dropdown menu inside the PromptManager (Node 14) to switch between these custom-built engines:<ol><li>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.</li><li>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.</li></ol><hr /><h3 id="important:-quality-and-upscaling-hint">⚠️ IMPORTANT: Quality &amp; Upscaling Hint</h3>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.<ul><li>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!</li></ul><hr /><h3 id="prerequisites-and-setup:">📦 Prerequisites &amp; Setup:</h3>To make this workflow run out of the box, ensure you have the following assets ready:<h3 id="1.-required-custom-nodes-(install-via-comfyui-manager):">1. Required Custom Nodes (Install via ComfyUI Manager):</h3><ul><li><code>comfyui-simple-ollama</code> (For the Ollama LLM node integration)</li><li><code>prompt-manager</code> (To hold the System Prompt presets)</li><li><code>comfyui-workflow-encrypt</code> (For the LoraManager and custom ImageSavers)</li><li><code>pysssss-comfyui</code> (For the automated ShowText title-saver display)</li></ul><h3 id="2.-models-and-settings:">2. Models &amp; Settings:</h3><ul><li>Base UNET: <code>Krea2\krea2Turbo18For_v2.safetensors</code> (Runs at an ultra-fast 4 steps!)</li><li>Text Encoder: <code>qwen3vl_4b_fp8_scaled.safetensors</code></li><li>VAE: <code>krea2RealVae_v10.safetensors</code></li><li>Latent Resolution: Configured to a cinematic, ultra-wide 1728 x 720 aspect ratio.</li><li>LLM Model (Ollama): <code>gemma-4-abliterated</code> (or any modern 8B model like Llama 3 / Mistral)</li><li>Active LoRAs utilized in this stack:<ul><li><code>krea2_turbo_4step_rank_64_lora</code> (Strength: 1.00)</li><li><code>zy_BackgroundDetail_K2</code> (Strength: 0.50)</li><li><code>Nijireol Krea2 v1 Ep5</code> (Strength: 1.00)</li><li><code>BeMyHero_-_LeaX_epoch_9</code> (Strength: 1.00)</li></ul></li></ul><hr /><h3 id="how-to-operate-the-auto-titling-engine:">⚙️ How to Operate the Auto-Titling Engine:</h3>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 <code>SaveImage</code> directory, keeping your outputs highly organized without manual typing.<hr />Load the <code>.json</code> 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.<hr />Feel free to leave a review and share your tiny universe creations in the gallery below!

MicroCosmos & Beyond: LLM-Driven Proportion Engine (Krea2 + Ollama)

"Initial Release - Stable build for Krea2 and Ollama prompt engineering."

Files with SHA256: c720d03961eb1a01fd2c0f95bbf1fa2d3d429a1654ce67ffc6c98a566380af65