flux_text_encoders

flux_text_encoders

Supplies text encoder checkpoints for Flux image models, made for ComfyUI's DualClipLoader node. For ComfyUI users who run Flux on their own machine.

Made by comfyanonymous on Hugging Face. These notes are Mindket's, written from its model page and model card; the model's own files and license are on Hugging Face.

About

What it is: This repository holds text encoder checkpoints for Flux image models. They are made to load through the DualClipLoader node in ComfyUI. A text encoder reads your prompt and turns it into the form the image model works from.

Who it suits: ComfyUI users who run Flux on their own computer and need the matching text encoders. The card is short, so it suits people who already know their way around ComfyUI.

Industry | Who uses it | How they use it | Example
Image generation | ComfyUI users | Load the encoders in a Flux workflow | Add the DualClipLoader node and pick the checkpoints
Creative work | Digital artists | Run Flux on a local machine | Type a prompt and let the encoders prepare it
Tooling | Workflow builders | Build Flux graphs in ComfyUI | Start from the Flux examples the card points to

You can skip it if you do not use ComfyUI or Flux.

Where to use it:

• ComfyUI, through its DualClipLoader node
• Flux workflows, such as the ones in ComfyUI's own Flux examples
• Windows, macOS or Linux, where ComfyUI runs

Use case | Who | What they get back
Prompt encoding | ComfyUI users | Encoded prompts that a Flux model can use
Flux workflows | Artists | Images made from a Flux graph that uses these encoders

How to set it up: You need ComfyUI and Python for the download tool.

• ComfyUI installed on your computer
• Python, to run the Hugging Face tool
• A Flux workflow, such as one from ComfyUI's Flux examples

1. Install ComfyUI if you do not have it.
2. Install the Hugging Face hub tool and download the repository.
3. Put the checkpoints where ComfyUI expects text encoders, following its Flux examples.
4. Open a Flux workflow in ComfyUI.

pip install -U huggingface_hub
hf download comfyanonymous/flux_text_encoders

How to use it: In your Flux workflow, add the DualClipLoader node and choose the encoder checkpoints in it. Then connect it as ComfyUI's Flux examples show. The card gives no other commands.

Tool | What it does
DualClipLoader | The ComfyUI node that loads these text encoder checkpoints

Example: You download the repository, add the DualClipLoader node to a Flux graph and select the encoder checkpoints. When you type a prompt and run the graph, the encoders prepare the text for the image model.

For newcomers and experts: Image models do not read your words directly. A text encoder first turns the prompt into numbers. A first small step is to open ComfyUI's Flux examples and see where the DualClipLoader node sits in the graph.

The node's name suggests it loads two encoders together, though the card does not say which ones. It lists no file names, sizes or formats, so check the repository's file list after downloading.

Download the checkpoints
Add DualClipLoader to a Flux graph
Select the encoder checkpoints
Run the graph with your prompt

Good to know:

• The card is brief and gives no file names, sizes or hardware needs.
• It points to ComfyUI's Flux examples for how to use the files.
• License: apache-2.0.
• Cost to run: none named, you use your own hardware.
• Data it reaches: files downloaded from Hugging Face, plus the prompts you type on your own machine.
• Not for: the card names no limits, but it is meant for ComfyUI and Flux.

On Hugging Face, 13 November 2026

• Downloads in the last 30 days: 0
• Likes: 1,507
• License: apache-2.0

Links

• Model: https://huggingface.co/comfyanonymous/flux_text_encoders
• Files: https://huggingface.co/comfyanonymous/flux_text_encoders/tree/main

Get the model

Download its files with Hugging Face's command line:

pip install -U huggingface_hub
hf download comfyanonymous/flux_text_encoders

Then follow the usage in its model card. Nothing in this kit runs by itself.