ComfyUI model file · Text encoder

t5xxl_fp16.safetensors

T5 v1.1 XXL text encoder (fp16) · T5 text encoder for FLUX.1 and SD3

t5xxl_fp16.safetensors is Google’s T5 v1.1 XXL text encoder in fp16, packaged for ComfyUI. FLUX.1 and SD3 read your prompt through it alongside CLIP. Put it in ComfyUI/models/text_encoders and load it in DualCLIPLoader (FLUX) or TripleCLIPLoader (SD3).

  • FLUX.1 · SD3
  • T5 v1.1 XXL
  • 9.79 GB
  • fp16

The Hugging Face repo needs no sign-in. If your RAM is under 32 GB, the fp8 version is half the size.

t5xxl_fp16.safetensors

Type
Text encoder
Format
Safetensors · fp16
Size
9.79 GB (9,787,841,024 bytes)
SHA256
6e480b09…8a9167635
ComfyUI folder
models/text_encoders/
Loader node
DualCLIPLoader
License
Apache-2.0
SHA256 and size from Hugging Face file metadata (comfyanonymous/flux_text_encoders), checked by RunComfy on .

The short version

What is t5xxl_fp16.safetensors?

T5 v1.1 XXL is the encoder half of Google’s T5 language model. FLUX.1 and Stable Diffusion 3 use it next to CLIP because it understands long, detailed prompts and spelled-out text far better than CLIP alone.

This file holds only the encoder, in fp16, as a single safetensors file that ComfyUI can load directly. The same file works for FLUX.1 dev and schnell, FLUX fine-tunes, SD3 and SD3.5.

Install

Download and install t5xxl_fp16.safetensors

Where it goes
ComfyUI/
└─ models/
   ├─ …
   └─ text_encoders/
      └─ t5xxl_fp16.safetensors
terminal · Linux / macOS
$ cd ComfyUI/models/text_encoders$ wget -O t5xxl_fp16.safetensors \$   https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/t5xxl_fp16.safetensors$ sha256sum t5xxl_fp16.safetensors# 6e480b09fae049a72d2a8c5fbccb8d3e92febeb233bbe9dfe7256958a9167635

Safetensors files hold tensors only and cannot run code. Still compare the SHA256: a failed download often leaves an HTML error page saved under the model’s filename.

Use

How to load t5xxl_fp16.safetensors in ComfyUI

FLUX.1 loads T5 next to clip_l in DualCLIPLoader (type flux). SD3 loads it in TripleCLIPLoader with clip_g and clip_l. Older video models such as CogVideoX load it alone in Load CLIP.

Minimal graph. Click a node to open its reference page.
  • Order does not matter

    DualCLIPLoader accepts T5 in either slot; the type setting decides how each is used.

  • Low on RAM?

    t5xxl_fp8_e4m3fn is half the size of fp16 with a small quality cost.

Works with

Files a FLUX.1 workflow needs

t5xxl_fp16.safetensors is one part of the stack. A workflow that reports a missing model usually needs these too. FLUX.1 dev is a gated download: accept the license on Hugging Face first.

FileRoleFolderSizeDownload
flux1-dev.safetensorsDiffusion modelmodels/diffusion_models/— Get
clip_l.safetensorsText encoder (CLIP-L)models/text_encoders/246 MB Get
ae.safetensorsVAEmodels/vae/— Get

Run it

ComfyUI workflows that can use t5xxl_fp16.safetensors

We match workflows by the model files they load: this exact file first, then other versions of it, then workflows built for the same use, then other models from the same family.

  1. Uses this exact file18
  2. Uses another version of this file24

Uses this exact file

18 workflows

These workflows already load t5xxl_fp16.safetensors. Open one and run it as is.

Uses another version of this file

24 workflows

These workflows load a different precision or format of the same model. Select t5xxl_fp16.safetensors in their DualCLIPLoader node to use this version.

Compare

Same file, other names, and alternatives

FileRelationSizeBest for
t5xxl_fp16.safetensorsThis page · fp169.79 GBBest prompt fidelity
t5xxl_fp8_e4m3fn.safetensorsSame encoder · fp8 e4m3fn4.89 GBHalf the RAM and VRAM
t5xxl_fp8_e4m3fn_scaled.safetensorsSame encoder · fp8 scaled5.16 GBfp8 with better accuracy

Troubleshoot

Common errors and fixes

Value not in list: clip_name2: 't5xxl_fp16.safetensors' not in [...]

Why: The workflow asks for this exact filename, but ComfyUI cannot find it in models/text_encoders. Usually the file is missing, sits in a different folder.

Fix: Move the file into ComfyUI/models/text_encoders/, rename it to match the workflow (or pick it again in the dropdown), then refresh the node list or restart ComfyUI.

SafetensorError: Error while deserializing header

Why: The download is incomplete, or the browser saved an HTML sign-in or error page under the model’s filename.

Fix: Check that the file is exactly 9,787,841,024 bytes and that its SHA256 matches the value above. Download it again from Hugging Face · comfyanonymous/flux_text_encoders if not.

Rather skip the setup?

Run VOID Video Inpainting ComfyUI in your browser on a cloud GPU. Nothing to download.

Run FLUX online

FAQ

t5xxl_fp16.safetensors FAQ

fp16 or fp8 for FLUX?

fp16 if you have about 32 GB of system RAM or more. Otherwise use t5xxl_fp8_e4m3fn.safetensors; most people cannot tell the difference in final images.

Is there another place to download t5xxl_fp16.safetensors besides Hugging Face?

Hugging Face (comfyanonymous/flux_text_encoders) is the official source. Copies elsewhere are fine if the SHA256 matches 6e480b09fae049a72d2a8c5fbccb8d3e92febeb233bbe9dfe7256958a9167635.

Where do I put t5xxl_fp16.safetensors in ComfyUI?

In ComfyUI/models/text_encoders/. Then refresh the node list or restart ComfyUI so DualCLIPLoader lists the file.

Which ComfyUI node loads t5xxl_fp16.safetensors?

DualCLIPLoader. It is built into ComfyUI, so no custom nodes are needed.

Can I use t5xxl_fp16.safetensors commercially?

Yes. T5 v1.1 XXL and this ComfyUI repackage are released under Apache-2.0.

Sources: comfyanonymous/flux_text_encoders · google/t5-v1_1-xxl

RunComfy
Copyright 2026 RunComfy. All Rights Reserved.

RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.