Kosinkadink/ComfyUI-Advanced-ControlNet

ControlNet scheduling and masking nodes with sliding context support

What it solves

This project provides advanced scheduling and control for ControlNet in ComfyUI, allowing users to precisely manage how ControlNet strength varies across sampling timesteps and individual latents in a batch. It bridges the gap between basic ControlNet application and the granular control found in other tools like Auto1111, specifically regarding prompt and ControlNet importance.

How it works

The system introduces "Timestep Keyframes" and "Latent Keyframes" to create schedules. Timestep Keyframes define settings (strength, weights, masks) that activate at specific percentages of the sampling process. Latent Keyframes allow for specific strength assignments to individual images (latents) within a batch. The project also implements "Soft Weights" to replicate features like "My prompt is more important" and "ControlNet is more important" by adjusting base and unconditional multipliers.

Who it’s for

Digital artists and AI video creators using ComfyUI who need precise temporal or spatial control over their image generation process, particularly those using AnimateDiff or SVD-ControlNets.

Highlights

  • Comprehensive Model Support: Works with ControlNet, T2IAdapters, ControlLoRAs, ControlLLLite, SparseCtrls, SVD-ControlNets, and Reference models.
  • Granular Scheduling: Support for timestep and latent strength scheduling via keyframes.
  • Attention Masking: Ability to apply masks to decide which parts of an image the ControlNet affects.
  • Advanced Weighting: Replicates Auto1111's prompt vs. ControlNet importance features via Soft Weights.
  • Sliding Context Support: Fully compatible with sliding context sampling used in AnimateDiff-Evolved.

Related

  • Project
    asagi4/comfyui-prompt-control

    A ComfyUI extension that lets you control complex AI image generation workflows (like LoRA loading, prompt scheduling, and regional prompting) using simple text prompts instead of manually wiring dozens of nodes.

  • Project
    cardenluo/ComfyUI-Apt_Preset

    A ComfyUI plugin that simplifies complex workflows by organizing them into a streamlined Loader-Controller-Sampler framework with preset support.

  • Project
    AlekPet/ComfyUI_Custom_Nodes_AlekPet

    A collection of custom nodes for ComfyUI that adds prompt translation, AI-driven content generation, and image manipulation tools.

  • Project
    shiimizu/ComfyUI_smZNodes

    Custom ComfyUI nodes (CLIP Text Encode++ and Settings) that replicate AUTOMATIC1111's prompt parsing and embedding, enabling identical image generation between stable‑diffusion‑webui and ComfyUI.

  • Project
    Jonseed/ComfyUI-Detail-Daemon

    A set of ComfyUI nodes that enhance image details and reduce background blur by adjusting noise schedules (sigmas) during sampling, specifically optimized for Flux and SDXL models.