Update README.md
Browse files
README.md
CHANGED
|
@@ -11,17 +11,34 @@ This repository contains a fused version of FLAN-T5-XXL, combining the split fil
|
|
| 11 |
|
| 12 |
---
|
| 13 |
|
| 14 |
-
##
|
| 15 |
-
|
| 16 |
-
- `flan_t5_xxl_fp16.safetensors`: Half-precision FP16 model for memory-efficient inference.
|
| 17 |
|
| 18 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
<img src="./Flan-T5xxl-FP32_FP16_compare.png" alt="Flan-T5xxl-FP32_FP16_compare">
|
| 20 |
</div>
|
| 21 |
|
| 22 |
---
|
| 23 |
|
| 24 |
-
## Comparison: FLAN-T5-XXL vs T5-XXL v1.1
|
| 25 |
|
| 26 |
<div style="display: flex; justify-content: center; align-items: center;">
|
| 27 |
<div style="text-align: center; margin-right: 1em;">
|
|
@@ -40,7 +57,7 @@ FLAN-T5-XXL provides more accurate responses to prompts.
|
|
| 40 |
|
| 41 |
---
|
| 42 |
|
| 43 |
-
|
| 44 |
|
| 45 |
- [FLAN-T5-XXL vs T5-XXL v1.1](https://ai-image-journey.blogspot.com/2024/12/clip-t5xxl-text-encoder.html)
|
| 46 |
- [FLAN-T5-XXL FP32 vs FP16 and other quantization](https://ai-image-journey.blogspot.com/2024/12/image-difference-t5xxl-clip-l.html)
|
|
|
|
| 11 |
|
| 12 |
---
|
| 13 |
|
| 14 |
+
## Newly Added: TE-Only Models for Stable Diffusion WebUI Forge & ComfyUI (2025-03-04)
|
| 15 |
+
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.
|
|
|
|
| 16 |
|
| 17 |
+
- `flan_t5_xxl_TE-only_FP32.safetensors`: Full-precision FP32 TE-only model.
|
| 18 |
+
- `flan_t5_xxl_TE-only_FP16.safetensors`: Half-precision FP16 TE-only model for memory-efficient inference.
|
| 19 |
+
|
| 20 |
+
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.
|
| 21 |
+
|
| 22 |
+
Also can be used as drop-in replacements for standard text encoders in Stable Diffusion-based workflows.
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
---
|
| 26 |
+
|
| 27 |
+
## Full Models
|
| 28 |
+
- `flan_t5_xxl_fp32.safetensors`: Full-precision FP32 Full model.
|
| 29 |
+
- `flan_t5_xxl_fp16.safetensors`: Half-precision FP16 Full model for memory-efficient inference.
|
| 30 |
+
|
| 31 |
+
---
|
| 32 |
+
|
| 33 |
+
## 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))
|
| 34 |
+
|
| 35 |
+
<div style="text-align: center; margin-left: auto; margin-right: auto;width:600px;max-width:80%;">
|
| 36 |
<img src="./Flan-T5xxl-FP32_FP16_compare.png" alt="Flan-T5xxl-FP32_FP16_compare">
|
| 37 |
</div>
|
| 38 |
|
| 39 |
---
|
| 40 |
|
| 41 |
+
## Comparison: FLAN-T5-XXL vs T5-XXL v1.1
|
| 42 |
|
| 43 |
<div style="display: flex; justify-content: center; align-items: center;">
|
| 44 |
<div style="text-align: center; margin-right: 1em;">
|
|
|
|
| 57 |
|
| 58 |
---
|
| 59 |
|
| 60 |
+
## Further Comparison
|
| 61 |
|
| 62 |
- [FLAN-T5-XXL vs T5-XXL v1.1](https://ai-image-journey.blogspot.com/2024/12/clip-t5xxl-text-encoder.html)
|
| 63 |
- [FLAN-T5-XXL FP32 vs FP16 and other quantization](https://ai-image-journey.blogspot.com/2024/12/image-difference-t5xxl-clip-l.html)
|