santa hat
deerdeer nosedeer glow
Sign In

Comfyroll Templates - Installation and Setup Guide


This guide is intended to help you get started with the Comfyroll template workflows

We hope this will not be a painful process for you. If you do get stuck, you will be welcome to post a comment asking for help on CivitAI, or DM us via the AI Revolution discord.

There is a thriving ComfyUI community on AI Revolution that can help with questions and share workflows.

Installation Guide

Custom Nodes


Please run updates on the custom nodes before loading new template versions. This will ensure the template picks up new node versions and not the older versions.


  • Please keep your ComfyUI up to date

  • You may get errors if your ComfyUI is on an old version

Recommended Downloads

SD1.5 Recommended Downloads

SDXL Recommended Downloads

LoRA models should be copied into:


ControlNet models should be copied into:


Upscale models

We recommend downloading these upscale models to get started:

You can find many more upscale models on the Upscaler Wiki

Upscaler Wiki - Model Database

Please ensure you have at least one upscale model installed

Upscaled models should be copied into:


Setup Guide

On first use

Select Models

  • Select a model and VAE

  • Select upscale models

  • On Intermediate and Advanced Templates

    • select default LoRAs or set each LoRA to Off and None

    • select ControlNet models

Default Images

  • Default images are needed because ComfyUI expects a valid image in each of the image loading nodes

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

  • Add a default image batch in the Load Image Batch node (on Advanced and Pro templates only)

    • e.g. E:\Comfy Projects\default batch

    • it should contain one png image, e.g. image.png

Setup Parameters

  • Set the batch-size parameter in Aspect Ratio node (e.g. 1, 2, 4)

  • Set the filename_prefix in Save Image to your preferred sub-folder

  • Set control_after_generate in the Seed node to randomize, or set to fixed if you want to do some testing on a specific seed

Test and Save

  • Do a test run

  • Save a copy to use as your template


On SDXL workflows you will need to setup models that were made for SDXL. these include

  • SDXL checkpoint models


  • SDXL LoRAs

  • SDXL ControlNet models

  • select an SDXL aspect ratio in the SDXL Aspect Ratio node

    • SDXL was trained on specific image sizes and will generally produce better images if you use one of the pre-configured aspect ratios

  • 1.5 models are generally not compatible with XL models