$ show Kosinkadink/ComfyUI-Advanced-ControlNet
This repository is a ComfyUI custom node pack that extends the standard ControlNet functionality with advanced scheduling, weighting, and masking capabilities. It provides nodes for timestep and latent keyframes, custom weight curves, attention masks, effect masks, and sliding context windows for video generation (AnimateDiff integration). The system supports multiple control types: ControlNet, T2IAdapter, ControlLoRA, ControlLLLite, SparseCtrl, SVD-ControlNet, Reference, ControlNet++, and CtrLoRA. It also replicates features from Auto1111 like 'My prompt is more important' via soft weights and uncond_multiplier. The architecture is modular, with separate files for each control family (control.py, control_reference.py, control_ctrlora.py, etc.), a shared utilities module (utils.py) providing base classes like AdvancedControlBase and ControlWeights, and a node registration layer (nodes.py, nodes_main.py, etc.). The system integrates deeply with ComfyUI's internal APIs (comfy.controlnet, comfy.model_patcher, comfy.hooks) and uses monkey-patching to inject advanced behavior into standard control objects. A custom inter-node communication protocol (DinkLink) enables coordination with AnimateDiff-Evolved. Key entry points are the node classes registered in __init__.py and nodes.py, which are loaded by ComfyUI's extension system. The primary data flow involves loading a control model, optionally converting it to an advanced version, applying timestep/latent keyframes and weights, and then applying the control during sampling with optional reference injection or sliding context. The system is actively maintained with recent commits, CI publishing, and example workflows demonstrating advanced features like Qwen Image Inpainting and Anima LLLite v2.
The LLM identified 3 files worth highlighting for reuse:
Provides the foundational classes AdvancedControlBase, ControlWeights, TimestepKeyframeGroup, LatentKeyframeGroup, and StrengthInterpolation. These are self-contained, reusable components that encapsulate the core logic for timestep/latent scheduling, weight specification with base/uncond multipliers, and strength interpolation. They can be extracted and used in other ComfyUI extensions that need advanced control scheduling without modification.
Implements Reference ControlNet and ContextRef mechanisms using a bank-style storage pattern for reference features per UUID. Contains BankStylesBasicTransformerBlock and BankStylesTimestepEmbedSequential that store and retrieve reference features during diffusion. The wrapper-based injection via comfy.patcher_extension.add_wrapper_with_key demonstrates a clean, reusable pattern for modifying diffusion model forward passes. This module is relatively isolated (imports from utils and comfy) and could be adapted for other attention injection tasks.
Contains the sampling wrapper that handles reference injection and sliding context windows for video generation. It patches the sampling process to insert reference conditioning and manage sub-idxs for AnimateDiff. The wrapper pattern is self-contained and demonstrates how to intercept ComfyUI's sampling loop without modifying core code, making it reusable for other extensions that need to alter sampling behavior.