Update README.md
Browse files
README.md
CHANGED
@@ -11,7 +11,9 @@ tags:
|
|
11 |
- text-rendering
|
12 |
---
|
13 |
|
14 |
-
|
|
|
|
|
15 |
|
16 |
**LeX-Enhancer** is a lightweight **prompt enhancement model** distilled from [DeepSeek-R1](https://huggingface.co/deepseek-ai/DeepSeek-R1).
|
17 |
We collected **60,856 caption pairs** — before and after DeepSeek-R1 enhancement — and fine-tuned a [DeepSeek-R1-Distilled-Qwen-14B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B) model using **LoRA** to reproduce high-quality, richly visualized prompt outputs.
|
|
|
11 |
- text-rendering
|
12 |
---
|
13 |
|
14 |
+
[](https://arxiv.org/abs/2503.21749)
|
15 |
+
|
16 |
+
# 🎨 LeX-Enhancer: Prompt Enhancer
|
17 |
|
18 |
**LeX-Enhancer** is a lightweight **prompt enhancement model** distilled from [DeepSeek-R1](https://huggingface.co/deepseek-ai/DeepSeek-R1).
|
19 |
We collected **60,856 caption pairs** — before and after DeepSeek-R1 enhancement — and fine-tuned a [DeepSeek-R1-Distilled-Qwen-14B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B) model using **LoRA** to reproduce high-quality, richly visualized prompt outputs.
|