ResourcesVideo 01

ComfyUI in 30 Minutes: Complete Beginner Guide (2026)

Everything from the video, free: the two workflows it walks through, the prompt that wrote the custom node, and the node's code.

One ZIP, 13 KB. Or take them one at a time below.

Watch ComfyUI in 30 Minutes: Complete Beginner Guide (2026) on YouTube

01Image workflow

A basic FLUX.1 Krea image workflow, with notes.

The image workflow from the video. Nine nodes turn a written prompt into a 1024 × 1024 photograph, and every one of them has a note beside it saying what it does. Every node ships with ComfyUI, so there's nothing extra to install.

Download JSON25 KB · 9 nodes, 9 notes
The FLUX.1 Krea workflow in ComfyUI: model and text-encoder loaders, the prompt, an empty latent, KSampler, VAE Decode and Save Image, each with its note.
The whole graph, drawn from the file. Each note shares its node's colour.

How to use it

  1. Drag the file onto the ComfyUI canvas, or open it from Workflow → Open.
  2. Put the four model files below into the folders listed, then press R so ComfyUI finds them.
  3. Press Run. The first image takes longest, while the models load.

Models it needs

FileFolderSizeLink
flux1-krea-dev_fp8_scaled.safetensorsThe image model. FP8 version of FLUX.1 Krea [dev], 12B parameters.models/diffusion_models/11.90 GBHugging Face (download flux1-krea-dev_fp8_scaled.safetensors)
clip_l.safetensorsFirst text encoder.models/text_encoders/246 MBHugging Face (download clip_l.safetensors)
t5xxl_fp16.safetensorsSecond text encoder. Use t5xxl_fp8_e4m3fn.safetensors instead if VRAM is tight.models/text_encoders/9.79 GBHugging Face (download t5xxl_fp16.safetensors)
ae.safetensorsThe VAE that turns the finished latent into a visible image.models/vae/335 MBHugging Face (download ae.safetensors)

Every node explained, in the blog

02Video workflow

A basic WAN 2.2 video workflow, with notes.

The video workflow from the video. It's the same skeleton as the image one with a frame count added, and it makes five seconds of 704 × 1216 video at 24 fps. Every node has a note beside it, and every node ships with ComfyUI.

Download JSON29 KB · 11 nodes, 11 notes
The WAN 2.2 5B workflow in ComfyUI: loaders, the positive and negative prompts, the video latent, ModelSamplingSD3, KSampler, VAE Decode, Create Video and Save Video, each with its note.
Loaders, two prompts, a video latent, KSampler, then Create Video and Save Video.

How to use it

  1. Drag the file onto the ComfyUI canvas, or open it from Workflow → Open.
  2. Put the three model files below into the folders listed, then press R so ComfyUI finds them.
  3. Press Run. length counts frames, not seconds: 121 frames at 24 fps is about five seconds.

Models it needs

FileFolderSizeLink
wan2.2_ti2v_5B_fp16.safetensorsThe WAN 2.2 TI2V 5B video model.models/diffusion_models/10.00 GBHugging Face (download wan2.2_ti2v_5B_fp16.safetensors)
umt5_xxl_fp8_e4m3fn_scaled.safetensorsThe UMT5 text encoder WAN reads prompts with.models/text_encoders/6.74 GBHugging Face (download umt5_xxl_fp8_e4m3fn_scaled.safetensors)
wan2.2_vae.safetensorsThe VAE that turns generated latent frames into visible ones.models/vae/1.41 GBHugging Face (download wan2.2_vae.safetensors)

How the graph works, in the blog

03Node prompt

The prompt that writes the node.

The exact prompt from the video. It went to Claude Code and came back as one complete, working file. The trick is being specific: the node format, every input, the output and the category are all spelled out.

Download TXTimage-picker-prompt.txt · 302 bytes
Claude Code
Create a simple ComfyUI V3 custom node called Image Picker.

Requirements:
- use comfy_api.latest
- 3 IMAGE inputs: image_1, image_2, image_3
- dropdown with Image 1, Image 2, Image 3
- 1 IMAGE output
- return whichever image is selected
- category: Model Chief
- provide one complete __init__.py file
The exact prompt from the video

Good to know

  • Paste it into Claude Code, or whichever AI coding assistant you use.
  • Asking for a V3 node matters. It's ComfyUI's newer node format, and naming comfy_api.latest keeps the answer on it.
  • Change the name, the inputs or the category, and the same prompt makes a different node.

04Node code

A simple custom node, ready to install.

The complete node from the video. Three image inputs, a dropdown and one output: it passes on whichever image you pick. It's written in ComfyUI's V3 node format, so it needs a recent version of ComfyUI.

model_chief_image_picker/__init__.py
from typing_extensions import override
from comfy_api.latest import ComfyExtension, io


class ImagePicker(io.ComfyNode):

    @classmethod
    def define_schema(cls) -> io.Schema:
        return io.Schema(
            node_id="ModelChiefImagePicker",
            display_name="Image Picker",
            category="Model Chief",
            inputs=[
                io.Image.Input("image_1"),
                io.Image.Input("image_2"),
                io.Image.Input("image_3"),
                io.Combo.Input(
                    "pick",
                    options=["Image 1", "Image 2", "Image 3"],
                ),
            ],
            outputs=[
                io.Image.Output(),
            ],
        )

    @classmethod
    def execute(
        cls,
        image_1,
        image_2,
        image_3,
        pick,
    ) -> io.NodeOutput:

        images = {
            "Image 1": image_1,
            "Image 2": image_2,
            "Image 3": image_3,
        }

        return io.NodeOutput(images[pick])


class ModelChiefExtension(ComfyExtension):

    @override
    async def get_node_list(self) -> list[type[io.ComfyNode]]:
        return [
            ImagePicker,
        ]


async def comfy_entrypoint() -> ModelChiefExtension:
    return ModelChiefExtension()
The Image Picker node running in ComfyUI: three Load Image nodes with a portrait, a fashion photo and a perfume bottle feed image_1, image_2 and image_3; pick is set to Image 2, and Preview Image shows the fashion photo.
The node in ComfyUI, running: three images in, pick set to Image 2, and the second image out.

Install it

  1. Open the custom_nodes folder inside your ComfyUI folder.
  2. Make a new folder in it called model_chief_image_picker.
  3. Save the code inside that folder as __init__.py. Or unzip the folder download straight into custom_nodes.
  4. Restart ComfyUI.
  5. Double-click the canvas and search for Image Picker. It's under Model Chief.
  6. Plug three images into it, choose one from the dropdown and run.