FlowMatch Euler Discrete Scheduler for ComfyUI

9 steps, big res, zero noise.

FlowMatchEulerDiscrete seems not exposed in ComfyUI, but it is what the official Z-Image demo in diffusers use.

So:

I am exposing it in the scheduler section for you to use within KSampler.

On top I provide a node, experimental, to configure the scheduler for use with CustomSampler and play with.

In short…if you want sharper and noise free images, use this!

Installation

use comfy ui manager (search erosDiffusion or ComfyUI-EulerFlowMatchingDiscreteScheduler)

or

git clone https://github.com/erosDiffusion/ComfyUI-EulerDiscreteScheduler.git in your custom nodes folder.

Example output (more below)

What you get

one new scheduler FlowMatchEulerDiscreteScheduler registered in the KSampler

a custom node that exposes all parameters of the FlowMatchEulerDiscreteScheduler which Outputs SIGMAS for use with SamplerCustom node.

Usage

Simple: select the FlowMatchEulerDiscreteScheduler in the default workflow from ComfyUI and run.

Advanced/experimental:

Add FlowMatch Euler Discrete Scheduler (Custom) node to your workflow

Connect its SIGMAS output to SamplerCustom node’s sigmas input

Adjust parameters to control the sampling behavior, you have ALL the parameters to play with.

Troubleshoot

if the scheduler does not appear when you have res4lyf package installed you can try:

— workaround 1: adding an samplerCustom node and connect the sigmas to a basicScheduler node. this way the scheduler should be available in the list

— workaround 2: disable res4lyf if you don’t need that

— workaround 3 use the flowmatch scheduler (custom) and connect to the sigmas of the samplerCustom.

if your install fails you might have to use the correct version of peft package, some users reported this as issue, check startup logs and install the proper version

Tech bits:

https://huggingface.co/docs/diffusers/api/schedulers/flow_match_euler_discrete

https://huggingface.co/Tongyi-MAI/Z-Image-Turbo/blob/main/scheduler/scheduler_config.json

Find this useful and want to support ?

Buy me a beer!

More examples:

Changelog

1.0.8

attempt fixing incompatibility with res4lyf by adding the scheduler to the list.

1.0.7

nunchaku qwen patch fix, tiled diffusion patch fix

users reported issues with dimensions not being handled correctly, this should fix it.

1.0.6

updated example

updated pyproject deps (diffusers)

1.0.5

remove bad practice of forking diffusers install on error (requirements.txt and does not rollback your diffusers if available)

1.0.4

add start and end step by Etupa, with some fixes (can be used for image to image or restart sampling)

1.0.3

node publish action

1.0.2

changed the device management in the custom scheduler node to be on gpu (cuda)

removed flash attention node dependency from the custom scheduler node

removed flash attention node from init

added mit licensing