How to Use This Site

Introduction

Welcome to Comfy-with-ComfyUI!

There are many excellent explanations of ComfyUI, including the official documentation. However, I felt that there was surprisingly little information on points where beginners first stumble, so I created this site to focus on explaining those parts!

I think it will be a good place for veteran users to know how ComfyUI is evolving.

Sections

By switching the Section Tab on the top left, articles corresponding to each theme will be displayed. The outline of the main sections is as follows.

🧭 Begin With ComfyUI

Introduces the installation and basic operation of ComfyUI.

The UI changes frequently these days. I want to fix it, but it will probably change again, so I will update it after it stabilizes to some extent.

🖼️ Data / Image Utilities

Summarizes how to prepare images and data used for generation. It covers image processing/conversion and how to handle many images at once.

🔼 AI Capabilities

Many beginners do not know what kinds of AI exist in the first place before how to use AI. It is structured so that you can look up "what AI can be used" from "what you want to do".

The very simple mechanism of image generation AI is also explained here.

🗺️ Basic Workflows

Explanation of basic workflows. It is not much different from ComfyUI's template, but it has a more minimal and easy-to-understand structure.

☹️ FAQ / Troubleshooting

Summarizes questions that are now taken for granted, such as "Why are there many 512px?" and "Seed value 1234 and 1235 are completely different things".

Also, errors and troubles likely to be encountered in ComfyUI are collected, and their causes and countermeasures are introduced.

Workflow Copy Button

This site provides JSON for almost all workflows introduced.

Although not well known, if you copy the JSON text of the workflow and press Ctrl + V on the ComfyUI canvas, you can paste the workflow as is.

Test workflow:

Stable_Diffusion_1.5.json

{
  "id": "8b9f7796-0873-4025-be3c-0f997f67f866",
  "revision": 0,
  "last_node_id": 9,
  "last_link_id": 9,
  "nodes": [
    {
      "id": 7,
      "type": "CLIPTextEncode",
      "pos": [
        413,
        389
      ],
      "size": [
        425.27801513671875,
        180.6060791015625
      ],
      "flags": {},
      "order": 3,
      "mode": 0,
      "inputs": [
        {
          "name": "clip",
          "type": "CLIP",
          "link": 5
        }
      ],
      "outputs": [
        {
          "name": "CONDITIONING",
          "type": "CONDITIONING",
          "slot_index": 0,
          "links": [
            6
          ]
        }
      ],
      "properties": {
        "cnr_id": "comfy-core",
        "ver": "0.3.33",
        "Node name for S&R": "CLIPTextEncode"
      },
      "widgets_values": [
        "text, watermark"
      ]
    },
    {
      "id": 6,
      "type": "CLIPTextEncode",
      "pos": [
        415,
        186
      ],
      "size": [
        422.84503173828125,
        164.31304931640625
      ],
      "flags": {},
      "order": 2,
      "mode": 0,
      "inputs": [
        {
          "name": "clip",
          "type": "CLIP",
          "link": 3
        }
      ],
      "outputs": [
        {
          "name": "CONDITIONING",
          "type": "CONDITIONING",
          "slot_index": 0,
          "links": [
            4
          ]
        }
      ],
      "properties": {
        "cnr_id": "comfy-core",
        "ver": "0.3.33",
        "Node name for S&R": "CLIPTextEncode"
      },
      "widgets_values": [
        "beautiful scenery nature glass bottle landscape, , purple galaxy bottle,"
      ]
    },
    {
      "id": 5,
      "type": "EmptyLatentImage",
      "pos": [
        473,
        609
      ],
      "size": [
        315,
        106
      ],
      "flags": {},
      "order": 0,
      "mode": 0,
      "inputs": [],
      "outputs": [
        {
          "name": "LATENT",
          "type": "LATENT",
          "slot_index": 0,
          "links": [
            2
          ]
        }
      ],
      "properties": {
        "cnr_id": "comfy-core",
        "ver": "0.3.33",
        "Node name for S&R": "EmptyLatentImage"
      },
      "widgets_values": [
        512,
        512,
        1
      ]
    },
    {
      "id": 8,
      "type": "VAEDecode",
      "pos": [
        1209,
        188
      ],
      "size": [
        210,
        46
      ],
      "flags": {},
      "order": 5,
      "mode": 0,
      "inputs": [
        {
          "name": "samples",
          "type": "LATENT",
          "link": 7
        },
        {
          "name": "vae",
          "type": "VAE",
          "link": 8
        }
      ],
      "outputs": [
        {
          "name": "IMAGE",
          "type": "IMAGE",
          "slot_index": 0,
          "links": [
            9
          ]
        }
      ],
      "properties": {
        "cnr_id": "comfy-core",
        "ver": "0.3.33",
        "Node name for S&R": "VAEDecode"
      },
      "widgets_values": []
    },
    {
      "id": 9,
      "type": "SaveImage",
      "pos": [
        1451,
        189
      ],
      "size": [
        210,
        270
      ],
      "flags": {},
      "order": 6,
      "mode": 0,
      "inputs": [
        {
          "name": "images",
          "type": "IMAGE",
          "link": 9
        }
      ],
      "outputs": [],
      "properties": {
        "cnr_id": "comfy-core",
        "ver": "0.3.33"
      },
      "widgets_values": [
        "ComfyUI"
      ]
    },
    {
      "id": 4,
      "type": "CheckpointLoaderSimple",
      "pos": [
        26,
        474
      ],
      "size": [
        315,
        98
      ],
      "flags": {},
      "order": 1,
      "mode": 0,
      "inputs": [],
      "outputs": [
        {
          "name": "MODEL",
          "type": "MODEL",
          "slot_index": 0,
          "links": [
            1
          ]
        },
        {
          "name": "CLIP",
          "type": "CLIP",
          "slot_index": 1,
          "links": [
            3,
            5
          ]
        },
        {
          "name": "VAE",
          "type": "VAE",
          "slot_index": 2,
          "links": [
            8
          ]
        }
      ],
      "properties": {
        "cnr_id": "comfy-core",
        "ver": "0.3.33",
        "Node name for S&R": "CheckpointLoaderSimple"
      },
      "widgets_values": [
        "📷-v1.x\\v1-5-pruned.safetensors"
      ]
    },
    {
      "id": 3,
      "type": "KSampler",
      "pos": [
        863,
        186
      ],
      "size": [
        315,
        262
      ],
      "flags": {},
      "order": 4,
      "mode": 0,
      "inputs": [
        {
          "name": "model",
          "type": "MODEL",
          "link": 1
        },
        {
          "name": "positive",
          "type": "CONDITIONING",
          "link": 4
        },
        {
          "name": "negative",
          "type": "CONDITIONING",
          "link": 6
        },
        {
          "name": "latent_image",
          "type": "LATENT",
          "link": 2
        }
      ],
      "outputs": [
        {
          "name": "LATENT",
          "type": "LATENT",
          "slot_index": 0,
          "links": [
            7
          ]
        }
      ],
      "properties": {
        "cnr_id": "comfy-core",
        "ver": "0.3.33",
        "Node name for S&R": "KSampler"
      },
      "widgets_values": [
        1234,
        "fixed",
        20,
        8,
        "euler",
        "normal",
        1
      ]
    }
  ],
  "links": [
    [
      1,
      4,
      0,
      3,
      0,
      "MODEL"
    ],
    [
      2,
      5,
      0,
      3,
      3,
      "LATENT"
    ],
    [
      3,
      4,
      1,
      6,
      0,
      "CLIP"
    ],
    [
      4,
      6,
      0,
      3,
      1,
      "CONDITIONING"
    ],
    [
      5,
      4,
      1,
      7,
      0,
      "CLIP"
    ],
    [
      6,
      7,
      0,
      3,
      2,
      "CONDITIONING"
    ],
    [
      7,
      3,
      0,
      8,
      0,
      "LATENT"
    ],
    [
      8,
      4,
      2,
      8,
      1,
      "VAE"
    ],
    [
      9,
      8,
      0,
      9,
      0,
      "IMAGE"
    ]
  ],
  "groups": [],
  "config": {},
  "extra": {
    "ds": {
      "scale": 0.7694864048338369,
      "offset": [
        214.34844915586953,
        127.86277974087162
      ]
    },
    "frontendVersion": "1.30.6",
    "VHS_latentpreview": false,
    "VHS_latentpreviewrate": 0,
    "VHS_MetadataImage": true,
    "VHS_KeepIntermediate": true
  },
  "version": 0.4
}

Please make use of it!

How to Face Generative AI

Generative AI expands possibilities that did not exist before, but it cannot do anything more than we imagine.

Creating an image referencing multiple characters while maintaining consistency. This has not yet been achieved. Making a 1-minute video. It cannot be done.

When AI cannot do what you want to do, you may think there must be some solution, but in most cases, the progress of AI has not yet reached the point of satisfying your wishes.

Don't rush, let's enjoy the immature AI. Only now can we do that.

Questions / Correction Reports

An assistant (?) confused by grabbing a ComfyUI node resides in the lower right of the screen 😏 Please hover your mouse over it.

Please feel free to send reports of typos, corrections of content, requests for themes you want explained, etc.

You can post to GitHub issue or contact me directly at Author.

To the World of ComfyUI

Then, let's study together to use ComfyUI Comfy!