Extensions/ComfyUI-MixMod
ComfyUI Extension

ComfyUI-MixMod

A custom node extension for ComfyUI that allows mixing multiple models during the sampling process for enhanced image generation.

By kantsche·Created about a year ago·Updated 11 months ago· 31
kantsche/ComfyUI-MixMod
Nodes13
On cloudLocal install
Categorymixmod/special, mixmod/components
Stars31
Updated11 months ago

Nodes (13)

MixMod Band FFT Guider

Slice the frequency spectrum into N bands for your mix

mixmod/special
MixMod Depth Guider

Background model vs. foreground model

mixmod/special
MixMod Dynamic Mask Alternative Guider

The no-depth-model foreground/background splitter

mixmod/special
MixMod Dynamic Mask Guider

Masks that evolve during sampling

mixmod/special
MixMod FFT Guider

What the FFT modes actually do

mixmod/special
MixMod Guider Component

How one checkpoint becomes a voice in the mix

mixmod/components
MixMod Guider Component Pipeline

Turn a MixMod pipeline into an actual component in the blend

mixmod/components
MixMod Guider

The MixMod team-mode guider

mixmod/components
MixMod High Res Guider

Read this before you expect a hires fix

mixmod/special
MixMod Options Mask

The mask option

mixmod/options
MixMod Options Scale

The scale option

mixmod/options
MixMod Options Scheduler

Who's on duty for which sampling steps

mixmod/options
MixMod Pipeline

Stop re-wiring the same model and prompt everywhere

mixmod/components
Readme

ComfyUI-MixMod

ComfyUI-MixMod provides a powerful way to combine multiple models during sampling.

VRAM requirement: Around 8gb vram is minimum. You might need to replace some models with gguf, I got 1sdxl, 1sdxlgguf and pixart sigma with gguf te running on 8gb vram.

Features

  • Mix multiple models during sampling
  • SD1.5+SDXL (use https://huggingface.co/ostris/sdxl-sd1-vae-lora to align the latents)
  • SDXL+Pixart sigma for increased prompt adherence, needs GGUF and ExtraModels for Comfyui
  • Scheduling everything
  • Multiple experimental modes.

Please share cool workflows you find under discussion, this stuff is really experimental and still needs discoveries.

Installation

  1. Clone this repository into your ComfyUI's custom_nodes directory:
cd ComfyUI/custom_nodes
git clone https://github.com/Kantsche/comfyui-mixmod.git
  1. Restart ComfyUI if it's already running.

Tips

  • Different models excel at different aspects - try mixing a detail-focused model with a composition-focused one
  • For FFT modes, base models work well for low frequencies, style models for high frequencies
  • Experiment with weights and CFG values to find the best balance
  • Schedule models to activate at different sampling steps for creative control

Compatibility

  • Tested with SD 1.5, SDXL and Pixart Sigma
  • Works with different model architectures (base, inpainting, etc.)
  • Only tested on Windows

Example workflow with pixart sigma: ShadowPCDisplay_n735IOn8Gu

It improves the prompt adherence of sdxl in general prompts:

ShadowPCDisplay_0d5BXStu6l

Example with Ponyv6 and NoobAI:

Only Pony, Pony+Noob, Only Noob image image

Credits

Created by Kantsche