The ultimate open-source commercial benchmarking character model for TrenchPetals Sunny Chuxem. Trained natively on Stable Diffusion 3.5 Large to flawlessly convert primitive MS Paint concept art into high-fidelity production assets!
📜 License & Mandatory Attribution
This repository is distributed under the SUPERKLOK LABS UNIFIED PUBLIC ASSET LICENSE v1.0:
100% Free for Commercial Use: You are fully permitted to use this LoRA, test images, and configurations to generate commercial artwork.
Mandatory Credit: You must credit Superklok Labs by linking to or tagging one of our official handles Twitter(X) or Instagram whenever you publish content created or upscaled with this asset.
💵 100% Commercial Freedom
Unlike standard community assets tied to restrictive non-commercial licenses, this entire architecture is completely free for commercial deployment.
Indie Game Developers: Rapidly iterate and generate concept art locally.
Content Creators: Streamline and automate character asset generation streams.
IP Creators: Monetize your visual outputs with zero platform overhead.
🚀 Generation & Training Parameters
Activation Trigger Word: SunnyChuxem
Recommended Weight: 0.8 - 1.0 (Use 1.0 for absolute character fidelity; dial down to 0.8 if stacking with heavy environment styles)
Native Resolution Layout: 1344x768 (Landscape centered-crop dataset)
Dataset Metrics: 50 hand-selected images at 30 iterations per file (3,000 steps total)
Final Loss Score: 0.0242 (Gold-standard character lock)
🛠️ Open-Source Training & Premium Workflows
Sunny Chuxem was generated using the ComfyUIcharacter engine. This specialized pipeline converts primitive sketches and text prompts into clean, detailed production images.
🌐 Want to train it yourself? Get the raw dataset, local ComfyUI scripts, and setup guides on our GitHub Repository.
💰 Want the definitive setup? Purchase our production-grade Premium ComfyUI Workflows directly via our Gumroad Store.
💼 Hire Superklok Labs for Enterprise Solutions
If you need custom-engineered generation pipelines, bespoke brand LoRAs, or enterprise-optimized local ComfyUI environments, let's build it together:
Description
Initial public release of the TrenchPetals Sunny Chuxem character neural weights.
Comments (1)
You set your LoRA as a model checkpoint. In order to correct this, click on your model page on the three vertical points in the top right corner and then on Edit Model. There in the second line you can change the Type to LoRA and don't forget to click on Save at the bottom of the page. If you correct this, just answer to this comment and I will delete it.