Add text-to-image pipeline tag and improve model card title (#1)

- Add text-to-image pipeline tag and improve model card title (690969923843c4745535f1a16a15bf0820dcc876)


Co-authored-by: Niels Rogge <[email protected]>

README.md

@@ -1,30 +1,28 @@
 ---
-library_name: transformers
-license: apache-2.0
+base_model:
+- deepseek-ai/Janus-Pro-7B
 datasets:
 - Franklin0/ReasonGen-R1-RL-Geneval-12k
 - Franklin0/ReasonGen-R1-RL-DPG-5k
 - Franklin0/ReasonGen-R1-RL-T2I-11k
-base_model:
-- deepseek-ai/Janus-Pro-7B
+library_name: transformers
+license: apache-2.0
+pipeline_tag: text-to-image
 ---
 
-# Model Card for Model ID
+# Model Card for ReasonGen-R1: Chain-of-Thought Reasoning for Autoregressive Image Generation
 
-An autoregressive image generation with text-based chain-of-thought.
+ReasonGen-R1 is an autoregressive image generation model incorporating chain-of-thought reasoning.
 Official checkpoint for the paper "[ReasonGen-R1: Cot for Autoregressive Image generation models through SFT and RL](https://huggingface.co/papers/2505.24875)".
 
 Website: https://aka.ms/reasongen
 
 Code: https://github.com/Franklin-Zhang0/Image-RL
 
-
-
 <!-- markdownlint-disable first-line-h1 -->
 <!-- markdownlint-disable html -->
 <!-- markdownlint-disable no-duplicate-header -->
 
-
 <h1> 🚀 ReasonGen-R1: <br> Cot for Autoregressive Image generation models through SFT and RL</h1>
 
 </div>
@@ -41,9 +39,6 @@ Code: https://github.com/Franklin-Zhang0/Image-RL
 
 </div>
 
-
-
-
 <p align="center">
   <a href="#2-model-download"><b>📥 Model Download</b></a> |
   <a href="#3-quick-start"><b>⚡ Quick Start</b></a> |
@@ -73,6 +68,9 @@ Evaluations on Geneval, DPG, and the T2I benchmark demonstrate that ReasonGen-R1
 | ReasonGen-R1 | [🤗 Hugging Face](https://huggingface.co/Franklin0/ReasonGen-R1) |
 | ReasonGen-R1-SFT-Only | [🤗 Hugging Face](https://huggingface.co/Franklin0/ReasonGen-R1-SFT) |
 
+| Dataset               | Download                                                                    |
+|-----------------------|-----------------------------------------------------------------------------|
+| ReasonGen-R1-Datasets | [🤗 Hugging Face](https://huggingface.co/collections/Franklin0/reasongen-r1-6836ed61fc4f6db543c0d368) |
 
 
 ## 3. Quick Start
@@ -90,7 +88,7 @@ conda activate image_rl
 pip3 install torch==2.6.0 torchvision --index-url https://download.pytorch.org/whl/cu124
 pip3 install flash-attn --no-build-isolation
 git clone https://github.com/Franklin-Zhang0/ReasonGen-R1.git
-cd Image-RL
+cd ReasonGen-R1
 pip install -r requirements.txt
 pip install -e .
 pip install -e ./Janus
@@ -134,7 +132,7 @@ cd ~
 cd project
 git clone https://github.com/TencentQQGYLab/ELLA.git
 cd ELLA
-cp ~/project/ReasonGen-R1/requirements-for-dpg_bench.txt .
+cp ~/project/ReasonGen-R1/benchmark/requirements-for-dpg_bench.txt .
 conda deactivate
 conda create -n dpg_test python=3.9 -y
 conda activate dpg_test
@@ -152,19 +150,19 @@ bash -i benchmark/dpg_eval.sh
 ### Inference
 To inference with the ReasonGen-R1 model, you can use the following command:
 ```shell
-python Image-RL/Janus/cot_generate_inference.py
+python ReasonGen-R1/Janus/cot_generate_inference.py
 ```
 
 ### SFT Training
 To train the SFT model from Janus-Pro-7B model on the ReasonGen-R1-SFT-200k dataset, you can use the following command:
 ```shell
-bash Image-RL/examples/janus_sft.sh
+bash ReasonGen-R1/examples/janus_sft.sh
 ```
 
 ### RL Training
 To train the RL model from the ReasonGen-R1-SFT model, you can use the following command:
 ```shell
-bash Image-RL/Janus/janus_rl.py
+bash ReasonGen-R1/Janus/janus_rl.py
 ```
 
 
@@ -183,4 +181,4 @@ We would like to thank <a href="https://github.com/volcengine/verl">Verl</a>, up
       primaryClass={cs.CV},
       url={https://arxiv.org/abs/2505.24875}, 
 }
-```
+```