Improve model card: add metadata, license, and link to paper (#1)

- Improve model card: add metadata, license, and link to paper (023a67af9a8f0bbe318d059d64f6e6191ec6ecd5)


Co-authored-by: Niels Rogge <nielsr@users.noreply.huggingface.co>

README.md

@@ -1,21 +1,29 @@
 ---
 base_model: black-forest-labs/FLUX.1-dev
 library_name: peft
+pipeline_tag: text-to-image
+license: apache-2.0
+tags:
+- flux
+- lora
+- diffusers
+- text-rendering
+- visual-text-rendering
 ---
-# Model Card for Model ID
 
-<!-- Provide a quick summary of what the model is/does. -->
-This model is trained using Flow-GRPO with LoRA. We provide only the LoRA weights here, so you will need to download the Flux.1-dev base model first.
+# TextPecker: Flux.1-dev-TextPecker-SQPA
 
-## Model Details
+This model is a LoRA adapter for [FLUX.1-dev](https://huggingface.co/black-forest-labs/FLUX.1-dev) optimized using the **TextPecker** strategy, as presented in the paper [TextPecker: Rewarding Structural Anomaly Quantification for Enhancing Visual Text Rendering](https://huggingface.co/papers/2602.20903).
 
-### Model Sources
+TextPecker is a plug-and-play structural anomaly perceptive RL strategy that improves the structural fidelity and semantic alignment of visual text rendering in text-to-image generators. This repository provides the LoRA weights trained using Flow-GRPO.
 
-<!-- Provide the basic links for the model. -->
+- **Repository:** https://github.com/CIawevy/TextPecker
+- **Paper:** [https://arxiv.org/abs/2602.20903](https://arxiv.org/abs/2602.20903)
+
+## Usage
+
+This model provides only the LoRA weights. You will need to load the Flux.1-dev base model first.
 
-- **Repository:** https://github.com/CIawevy/TextPecker/tree/main
-- **Paper:** https://www.arxiv.org/pdf/2602.20903
-## Uses
 ```python
 import os
 import torch
@@ -86,4 +94,17 @@ image = pipe(
 # Save result (FLUX naming convention)
 image.save("TextPecker_flux_demo.png")
 print("Image saved as: TextPecker_flux_demo.png")
+```
+
+## Citation
+
+If you find TextPecker useful in your research or work, please cite the original paper:
+
+```bibtex
+@article{zhu2026TextPecker,
+  title   = {TextPecker: Rewarding Structural Anomaly Quantification for Enhancing Visual Text Rendering},
+  author  = {Zhu, Hanshen and Liu, Yuliang and Wu, Xuecheng and Wang, An-Lan and Feng, Hao and Yang, Dingkang and Feng, Chao and Huang, Can and Tang, Jingqun and Bai, Xiang},
+  journal = {arXiv preprint arXiv:2602.20903},
+  year    = {2026}
+}
 ```