---
license: apache-2.0
tags:
- T5xxl
- Google FLAN
---

# FLAN-T5-XXL Fused Model

This repository contains a fused version of FLAN-T5-XXL, combining the split files available at [Google's FLAN-T5-XXL repository](https://huggingface.co/google/flan-t5-xxl). These files have been merged for easier use in AI applications, including image generation models.

---

## Newly Added: TE-Only Models for Stable Diffusion WebUI Forge & ComfyUI (2025-03-04)
Two additional files provide the **Text Encoder (TE) only** portion of FLAN-T5-XXL, specifically extracted for use with Stable Diffusion WebUI Forge and ComfyUI.

<div style="display: flex; justify-content: center; align-items: center;">
  <div style="text-align: center; margin-right: 1em;">
    <img src="./flan_t5_xxl_TE-only_FP32_sample1.png" alt="flan_t5_xxl_TE-only_FP32_sample1" width="400px" height="400px">
  </div>
  <div style="text-align: center; margin-left: 1em;">
    <img src="./flan_t5_xxl_TE-only_FP32_sample2.png" alt="flan_t5_xxl_TE-only_FP32_sample2" width="400px" height="400px">
  </div>
</div>

- `flan_t5_xxl_TE-only_FP32.safetensors`: Full-precision FP32 TE-only model.  
- `flan_t5_xxl_TE-only_FP16.safetensors`: Half-precision FP16 TE-only model for memory-efficient inference.

These models retain only the text encoding functionality of FLAN-T5-XXL, reducing resource consumption while maintaining high-quality prompt processing in AI image generation workflows.  

Also can be used as drop-in replacements for standard text encoders in Stable Diffusion-based workflows.


---

## Full Models
- `flan_t5_xxl_fp32.safetensors`: Full-precision FP32 Full model.
- `flan_t5_xxl_fp16.safetensors`: Half-precision FP16 Full model for memory-efficient inference.

---

## Comparison: FLAN-T5-XXL-FP32 vs FLAN-T5-XXL-FP16 on Flux.1[dev] (base model: [blue_pencil-flux1_v0.0.1](https://huggingface.co/bluepen5805/blue_pencil-flux1))

<div style="text-align: center; margin-left: auto; margin-right: auto;width:600px;max-width:80%;">
  <img src="./Flan-T5xxl-FP32_FP16_compare.png" alt="Flan-T5xxl-FP32_FP16_compare">
</div>

---

## Comparison: FLAN-T5-XXL vs T5-XXL v1.1

<div style="display: flex; justify-content: center; align-items: center;">
  <div style="text-align: center; margin-right: 1em;">
    <img src="./flan_t5_xxl_image.png" alt="FLAN-T5-XXL Image" width="400px" height="400px">
    <p>FLAN-T5-XXL Output</p>
  </div>
  <div style="text-align: center; margin-left: 1em;">
    <img src="./t5_xxl_v1_1_image.png" alt="T5-XXL v1.1 Image" width="400px" height="400px">
    <p>T5-XXL v1.1 Output</p>
  </div>
</div>

These example images generated using **FLAN-T5-XXL** and [**T5-XXL v1.1**](https://huggingface.co/google/t5-v1_1-xxl) models in Flux.1.

FLAN-T5-XXL provides more accurate responses to prompts.

---

## Further Comparison

- [FLAN-T5-XXL vs T5-XXL v1.1](https://www.ai-image-journey.com/2024/12/clip-t5xxl-text-encoder.html)
- [FLAN-T5-XXL FP32 vs FP16 and other quantization](https://www.ai-image-journey.com/2024/12/image-difference-t5xxl-clip-l.html)

---

## License
This model is provided under the [Apache 2.0 License](https://www.apache.org/licenses/LICENSE-2.0).  
The uploader does not claim any rights over the model.

---

## Acknowledgments
- Original source: [Google's FLAN-T5-XXL repository](https://huggingface.co/google/flan-t5-xxl).
- GGUF version: [dumb-dev's Hugging Face repository](https://huggingface.co/dumb-dev/flan-t5-xxl-gguf).