Update README.md

README.md

@@ -1,3 +1,161 @@
----
-license: apache-2.0
----
+<h1 align="center">
+  Continuous-Time Distribution Matching for Few-Step Diffusion Distillation
+</h1>
+
+<div align="center">
+
+<a href="https://byliutao.github.io/cdm_page/">
+    <img src="https://img.shields.io/badge/Project_Page-0055b3?logo=githubpages&logoColor=white" alt="Project Page">
+</a>
+<a href="https://huggingface.co/byliutao/stable-diffusion-3-medium-turbo">
+    <img src="https://img.shields.io/badge/%F0%9F%A4%97%20Model-SD3.5_Medium-ffc107" alt="SD3.5-Medium Model">
+</a>
+<a href="https://huggingface.co/byliutao/Longcat-Image-Turbo">
+    <img src="https://img.shields.io/badge/%F0%9F%A4%97%20Model-LongCat-ffc107" alt="LongCat Model">
+</a>
+<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="https://arxiv.org/abs/">
+    <img src="https://img.shields.io/badge/Paper-2509.161-b31b1b?logo=arxiv&logoColor=white" alt="arXiv Paper">
+</a>
+
+</div>
+
+<p align="center">
+  <a href="#algorithm-overview">Algorithm Overview</a> •
+  <a href="#4-nfe-generation-results">Results</a> •
+  <a href="#inference">Inference</a> •
+  <a href="#training">Training</a> •
+  <a href="#evaluation">Evaluation</a> •
+  <a href="#citation">Citation</a>
+</p>
+
+<p align="center">
+  <img src="assets/teaser.png" width="95%" alt="Teaser: High-quality images generated with only 4 NFE">
+</p>
+
+## Algorithm Overview
+
+<p align="center">
+  <img src="assets/pipe.png" width="90%" alt="Pipeline overview of Continuous-Time Distribution Matching">
+</p>
+
+**Overview of Continuous-Time Distribution Matching (CDM).** **Top:** Our approach employs a dynamic continuous time schedule during backward simulation, sampling intermediate anchors uniformly from (0, 1]. **Bottom Left:** CFG augmentation (CA) and distribution matching (DM) operate on this dynamic schedule to align text-image conditions and data distributions at on-trajectory anchors. **Bottom Right:** To address inter-anchor inconsistency, the proposed CDM objective explicitly extrapolates off-trajectory latents using the predicted velocity.
+
+## 4-NFE Generation Results
+
+### SD3.5-Medium
+
+<p align="center">
+  <img src="assets/sd3.png" width="90%" alt="SD3.5-Medium 4-NFE generation samples">
+</p>
+
+### LongCat
+
+<p align="center">
+  <img src="assets/longcat.png" width="90%" alt="LongCat 4-NFE generation samples">
+</p>
+
+---
+
+## Inference
+
+```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   # SD3.5-Medium
+python scripts/infer/longcat.py # LongCat
+```
+
+## Training
+
+```bash
+# Clone this repository
+git clone https://github.com/NVlabs/DiffusionNFT.git
+cd DiffusionNFT
+
+# Create and activate the training environment
+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 1 -m scripts.train \
+    --config config/config.py:sd3      # SD3.5-Medium
+
+accelerate launch --config_file config/accelerate_fsdp2.yaml \
+    --num_processes 1 -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 "10"
+```
+
+### Step 2 — Generate images
+
+```bash
+accelerate launch --num_processes 1 -m scripts.eval \
+    --phase generate \
+    --model_path "logs/pipelines/test/checkpoint-2000" \
+    --eval_metrics imagereward clipscore pickscore hpsv2 hpsv3 aesthetic ocr dpgbench fid \
+    --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 1 -m scripts.eval \
+    --phase evaluate \
+    --eval_metrics imagereward clipscore pickscore hpsv2 hpsv3 aesthetic ocr dpgbench fid \
+    --output_dir "logs/evaluations/test"
+```
+
+## License
+
+This project is licensed under the MIT License — see the [LICENSE](LICENSE) file for details.
+
+## Citation
+
+If our work assists your research, please consider giving us a star ⭐ or citing us:
+
+```bibtex
+```