Others

欢迎大家来到内测群进行内测,我们将征求一些建议!Download is not required here. We are just testing the view of the testers.

We have prepared 100,000 materials for AI development research on the game interface this time.The large model for the game UI interface is currently undergoing internal testing, and UI interfaces can be generated based on rough sketches. You can use rough wireframes to realize your interface design style. After the internal testing is completed, it will be first tested in the QQ group.

QQ测试组:855795962

discord GUI testing group:https://discord.gg/xRn2NG8v7R

A collection of ComfyUI custom nodes to help streamline workflows and reduce total node count.

Github Repo: https://github.com/LucianoCirino/efficiency-nodes-comfyui

Currently Available Nodes:

Ksampler (Efficient)

• A modded KSampler with the ability to preview/output images and run scripts.

Efficient Loader

• A combination of common initialization nodes.

XY Plotter Nodes

• A collection of nodes that allows users to specify parameters for the KSampler (Efficient) to plot on a grid.

Image Overlay

• Node that allows for flexible image overlaying.

SimpleEval Nodes

• A collection of nodes that allows users to write simple Python expressions for a variety of data types using the "simpleeval" library.

I recently found myself collecting datasets from animated Gifs and videos, then having to deleted similar images.

that's exactly what this tool does.

requires :

• openCV : pip install opencv-python

• scikit-image : pip install scikit-image

This workflow template is intended as a multi-purpose template for use on a wide variety of projects. It can be used with any checkpoint model.

Prerequisites

• ComfyUI installation

• WAS Node Suite custom nodes, v2.0 or higher

• at least 10GB VRAM is recommended

Installation

• save the workflow on the same drive as your ComfyUI installation

• save the Custom Nodes from the download in your \ComfyUI\custom_nodes folder

• install WAS Node Suite from https://civitai.com/models/20793/was-node-suite-comfyui

On first use

• select models and VAE

• select a default LoRA in each Load LoRA node

• select upscale models

• select ControlNet models

• add a default image in each of the Load Image nodes (purple nodes)

• add a default image batch in the Load Image Batch node

• do a test run

• save a copy to use as your template

Template Features

• Txt2Img, Img2Img or Img2Img batch

• dual models

• dual prompts

• up to 5 LoRAs (these can be toggled On/Off)

• up to 2 ControlNets or a ControlNet batch

• ControlNet diff models

• image borders

• various noise options

• Hires Fix and latent upscaling

• image upscaling

• post-processing styles and enhancements

Tips

• each optional component can be bypassed using logic switches (red nodes)

• set the Load Image Batch to single-image when it is not being used

• the default setting on all switches is Off (1)

• Preview Image nodes can be set to preview or save image using the output_type

• use ComfyUI Manager to download ControlNet and upscale models

• if you are new to ComfyUI it is recommended to start with the simple and intermediate templates in Comfyroll Template Workflows

Change History

v2

• fixed bug in Post Processing routing

• added data types on re-route nodes