import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-3.5-large", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("Superklok/SunnyChuxemLoRA")
prompt = "SunnyChuxem"
image = pipe(prompt).images[0]
SunnyChuxemLoRA is 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:
SunnyChuxemRecommended 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 SunnyChuxemLoRA or any other LoRA yourself? Get the raw 50-image dataset, local portable offline ComfyUI LoRA Training Workflow, and complete user guide on our GitHub Repository.
- 🌞 Want to turn primitive concepts or rough sketches into high-fidelity, original character assets completely offline? Purchase our production-grade Premium ComfyUIcharacter ComfyUI + SillyTavern Pipeline directly via our Contra Store.
➡️
- 🪄 Need a Bespoke Brand Adaptation? If you want the ultimate all-in-one ComfyUI plus SillyTavern character automation pipeline tailored perfectly to bring your company's next original character asset to life, generate high-quality written lore, and use all assets 100% commercially, order a Bespoke ComfyUIcharacter ComfyUI + SillyTavern Pipeline on Upwork today!
🏢 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:
- Downloads last month
- 16
Model tree for Superklok/SunnyChuxemLoRA
Base model
stabilityai/stable-diffusion-3.5-large