Add metadata and link to paper

Hi there! This PR improves the model card for Longcat-Image-Turbo by adding relevant YAML metadata for better discoverability.

Specifically, I have:
- Added `pipeline_tag: text-to-image`.
- Added `library_name: diffusers` (based on the model structure).
- Added `license: mit`.
- Included a direct link to the paper [Continuous-Time Distribution Matching for Few-Step Diffusion Distillation](https://huggingface.co/papers/2605.06376) and its GitHub repository.

README.md

@@ -1,3 +1,9 @@
+---
+license: mit
+library_name: diffusers
+pipeline_tag: text-to-image
+---
+
 <h1 align="center">
   Continuous-Time Distribution Matching for Few-Step Diffusion Distillation
 </h1>
@@ -16,12 +22,16 @@
 <a href="https://github.com/byliutao/cdm">
     <img src="https://img.shields.io/badge/GitHub-byliutao%2Fcdm-black?logo=github&logoColor=white" alt="GitHub">
 </a>
-<a href="http://arxiv.org/abs/2605.06376">
-    <img src="https://img.shields.io/badge/Paper-2605.06376-b31b1b?logo=arxiv&logoColor=white" alt="arXiv Paper">
+<a href="https://huggingface.co/papers/2605.06376">
+    <img src="https://img.shields.io/badge/Paper-2605.06376-b31b1b?logo=arxiv&logoColor=white" alt="Paper">
 </a>
 
 </div>
 
+This repository contains the weights for Longcat-Image-Turbo, a few-step distilled version of Longcat-Image using the **Continuous-Time Distribution Matching (CDM)** method presented in [Continuous-Time Distribution Matching for Few-Step Diffusion Distillation](https://huggingface.co/papers/2605.06376).
+
+CDM migrates the Distribution Matching Distillation (DMD) framework from discrete anchoring to continuous optimization, allowing for high-quality image generation with very few steps (e.g., 4 NFE).
+
 <p align="center">
   <a href="#algorithm-overview">Algorithm Overview</a> •
   <a href="#4-nfe-generation-results">Results</a> •
@@ -61,22 +71,19 @@
 
 ## Inference
 
+To use this model, please refer to the [GitHub repository](https://github.com/byliutao/cdm).
+
 ```bash
 # Clone this repository
 git clone https://github.com/byliutao/cdm.git
 cd cdm
 
-# [Optional] Use HuggingFace mirror if huggingface.co is not accessible
-export HF_ENDPOINT="https://hf-mirror.com"
-export HF_TOKEN="hf_xxx"
-
 # Create and activate the inference environment
 conda create -n cdm_infer python=3.10
 conda activate cdm_infer
 pip install -r config/requirements_infer.txt
 
 # Run inference
-python scripts/infer/sd3_m.py   # SD3-Medium
 python scripts/infer/longcat.py # LongCat
 ```
 
@@ -87,64 +94,13 @@ python scripts/infer/longcat.py # LongCat
 conda create -n cdm_train python=3.10
 conda activate cdm_train
 pip install -r config/requirements_train.txt
-pip install flash-attn==2.7.4.post1 --no-build-isolation  # May take 1-2 hours
 
 # Launch training with FSDP2
-accelerate launch --config_file config/accelerate_fsdp2.yaml \
-    --num_processes 8 -m scripts.train \
-    --config config/config.py:sd3      # SD3-Medium
-
 accelerate launch --config_file config/accelerate_fsdp2.yaml \
     --num_processes 8 -m scripts.train \
     --config config/config.py:longcat  # LongCat
 ```
 
-## Evaluation
-
-Evaluation is split into two phases: **image generation** and **metric computation**.
-
-### Step 1 — Export a checkpoint to a pipeline
-
-```bash
-conda activate cdm_train
-
-python -m scripts.save \
-    --experiment_dir "logs/experiments/sd3/test" \
-    --output_dir "logs/pipelines/test" \
-    --checkpoint_steps "2000"
-```
-
-### Step 2 — Generate images
-
-```bash
-accelerate launch --num_processes 8 -m scripts.eval \
-    --phase generate \
-    --model_path "logs/pipelines/test/checkpoint-2000" \
-    --eval_metrics imagereward clipscore pickscore hpsv2 hpsv3 aesthetic ocr dpgbench \
-    --output_dir "logs/evaluations/test" \
-    --base_model sd3 \
-    --save_images
-```
-
-### Step 3 — Compute metrics
-
-```bash
-# Create a separate environment for evaluation dependencies
-conda create -n cdm_eval python=3.10
-conda activate cdm_eval
-pip install -r config/requirements_eval.txt
-pip install image-reward --no-deps
-pip install fairseq --no-deps
-
-# NOTE: If running on multiple GPUs, download checkpoints on 1 GPU first.
-# For FID evaluation, place COCO 2014 val images under: dataset/coco2014val_10k/images
-
-accelerate launch --num_processes 8 -m scripts.eval \
-    --phase evaluate \
-    --eval_metrics imagereward clipscore pickscore hpsv2 hpsv3 aesthetic ocr dpgbench \
-    --output_dir "logs/evaluations/test"
-```
-
 ## License
 
 This project is licensed under the MIT License — see the [LICENSE](LICENSE) file for details.
@@ -163,4 +119,4 @@ If our work assists your research, please consider giving us a star ⭐ or citin
       primaryClass={cs.CV},
       url={https://arxiv.org/abs/2605.06376}, 
 }
-```
+```