Improve model card with correct metadata and paper links

This PR improves the model card by:
- Adding the `text-to-image` pipeline tag for better discoverability.
- Updating the paper link to the correct arXiv ID (2605.08063).
- Adding links to the official GitHub repository and project page.
- Adding a citation section for the research paper.

README.md

@@ -1,40 +1,52 @@
 ---
 base_model: stabilityai/stable-diffusion-3.5-medium
 library_name: peft
+pipeline_tag: text-to-image
 ---
 
-# Model Card for Model ID
+# Flow-OPD: On-Policy Distillation for Flow Matching Models
 
-<!-- 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 SD 3.5 Medium base model first.
+This repository contains LoRA weights for text-to-image generation, specifically the PickScore-specialized teacher model used in the **Flow-OPD** framework. Flow-OPD is a unified post-training framework that integrates on-policy distillation into Flow Matching models to replace sparse scalar rewards with dense, trajectory-level supervision.
 
-## Model Details
-
-### Model Sources
+- **Paper:** [Flow-OPD: On-Policy Distillation for Flow Matching Models](https://arxiv.org/abs/2605.08063)
+- **Project Page:** [https://costaliya.github.io/Flow-OPD/](https://costaliya.github.io/Flow-OPD/)
+- **Repository:** [https://github.com/CostaliyA/Flow-OPD](https://github.com/CostaliyA/Flow-OPD)
 
-<!-- Provide the basic links for the model. -->
+## Model Details
 
-- **Repository:** https://github.com/yifan123/flow_grpo
-- **Paper:** https://www.arxiv.org/pdf/2505.05470
+This model is a LoRA adapter trained using Flow-GRPO. To use it, you must first download the [Stable Diffusion 3.5 Medium](https://huggingface.co/stabilityai/stable-diffusion-3.5-medium) base model.
 
 ## Uses
+
 ```python
 import torch
 from diffusers import StableDiffusion3Pipeline
-from diffusers.schedulers import FlowMatchEulerDiscreteScheduler
 from peft import PeftModel
 
 model_id = "stabilityai/stable-diffusion-3.5-medium"
+# This repository's LoRA weights
 lora_ckpt_path = "jieliu/SD3.5M-FlowGRPO-PickScore"
 device = "cuda"
 
-
 pipe = StableDiffusion3Pipeline.from_pretrained(model_id, torch_dtype=torch.float16)
 pipe.transformer = PeftModel.from_pretrained(pipe.transformer, lora_ckpt_path)
 pipe.transformer = pipe.transformer.merge_and_unload()
 pipe = pipe.to(device)
 
-prompt = 'a jung male cyborg with white hair sitting down on a throne in a dystopian world, digital art, epic'
-image = pipe(prompt, height=512, width=512, num_inference_steps=40,guidance_scale=4.5,negative_prompt="").images[0]  
+prompt = 'a young male cyborg with white hair sitting down on a throne in a dystopian world, digital art, epic'
+image = pipe(prompt, height=512, width=512, num_inference_steps=40, guidance_scale=4.5, negative_prompt="").images[0]  
 image.save("flow_grpo_pickscore.png")
+```
+
+## Citation
+
+If you find this work useful, please cite:
+
+```bibtex
+@article{fang2026flow,
+  title={Flow-OPD: On-Policy Distillation for Flow Matching Models},
+  author={Fang, Zhen and Huang, Wenxuan and Zeng, Yu and Zhao, Yiming and Chen, Shuang and Feng, Kaituo and Lin, Yunlong and Chen, Lin and Chen, Zehui and Cao, Shaosheng and others},
+  journal={arXiv preprint arXiv:2605.08063},
+  year={2026}
+}
 ```