Critical Usage Notes for Method 1: Weighting is extremely sensitive: The "Sweet Spot" is below 0.1. Start at 0.0 and increase by 0.01 increments until you reach the desired effect. Do not use 1.0. Chaining Order: Due to DoRA characteristics, this node must be placed BEFORE any standard LoRA Loader nodes in your workflow. Performance: You may notice slower load times during the first generation or when switching checkpoints/weights. This is normal behavior for the LyCORIS loader and does not affect the final image quality. Method 2: The "Standard" Method (V-Pred Checkpoints Only) Recommended for: Convenience, or if you cannot use custom nodes. You can load this model using the standard LoRA loader (or LoRA Stack), but ONLY if you are using a V-Prediction Base Model. Weighting: Functions like a standard LoRA. Recommended range: 0 - 0.8. ⚠️ WARNING: Do NOT use this method with Epsilon-Prediction models (standard SDXL, Juggernaut, etc.). It will result in severe overexposure, artifacts, and noise.