Update README.md

README.md

@@ -1,3 +1,104 @@
----
-license: cc-by-nc-4.0
----
+---
+license: cc-by-nc-4.0
+---
+
+# AudioX
+
+## 🎧 AudioX: Diffusion Transformer for Anything-to-Audio Generation
+
+[TL;DR]: AudioX is a unified Diffusion Transformer model for Anything-to-Audio and Music Generation, capable of generating high-quality general audio and music, offering flexible natural language control, and seamlessly processing various modalities including text, video, image, music, and audio.
+
+### Links
+- **[Paper](https://arxiv.org/abs/2503.10522)**: Explore the research behind AudioX.
+- **[Project](https://zeyuet.github.io/AudioX/)**: Visit the official project page for more information and updates.
+
+
+## Clone the repository
+```bash
+GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/HKUSTAudio/AudioX
+cd AudioX
+
+conda create -n AudioX python=3.8.20
+conda activate AudioX
+pip install git+https://github.com/ZeyueT/AudioX.git
+conda install -c conda-forge ffmpeg libsndfile
+```
+
+## Usage
+
+```py
+import torch
+import torchaudio
+from einops import rearrange
+from stable_audio_tools import get_pretrained_model
+from stable_audio_tools.inference.generation import generate_diffusion_cond
+from stable_audio_tools.data.utils import read_video, merge_video_audio
+from stable_audio_tools.data.utils import load_and_process_audio
+import os
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+# Download model
+model, model_config = get_pretrained_model("HKUSTAudio/AudioX")
+sample_rate = model_config["sample_rate"]
+sample_size = model_config["sample_size"]
+target_fps = model_config["video_fps"]
+seconds_start = 0
+seconds_total = 10
+
+model = model.to(device)
+
+# for video-to-music generation
+video_path = "video.mp4"
+text_prompt = "Generate music for the video" 
+audio_path = None
+
+video_tensor = read_video(video_path, seek_time=0, duration=seconds_total, target_fps=target_fps)
+audio_tensor = load_and_process_audio(audio_path, sample_rate, seconds_start, seconds_total)
+
+conditioning = [{
+    "video_prompt": [video_tensor.unsqueeze(0)],        
+    "text_prompt": text_prompt,
+    "audio_prompt": audio_tensor.unsqueeze(0),
+    "seconds_start": seconds_start,
+    "seconds_total": seconds_total
+}]
+    
+# Generate stereo audio
+output = generate_diffusion_cond(
+    model,
+    steps=250,
+    cfg_scale=7,
+    conditioning=conditioning,
+    sample_size=sample_size,
+    sigma_min=0.3,
+    sigma_max=500,
+    sampler_type="dpmpp-3m-sde",
+    device=device
+)
+
+# Rearrange audio batch to a single sequence
+output = rearrange(output, "b d n -> d (b n)")
+
+# Peak normalize, clip, convert to int16, and save to file
+output = output.to(torch.float32).div(torch.max(torch.abs(output))).clamp(-1, 1).mul(32767).to(torch.int16).cpu()
+torchaudio.save("output.wav", output, sample_rate)
+
+if video_path is not None and os.path.exists(video_path):
+    merge_video_audio(video_path, "output.wav", "output.mp4", 0, seconds_total)
+
+```
+
+
+
+## Citation
+If you find our work useful, please consider citing:
+
+```
+@article{tian2025audiox,
+  title={AudioX: Diffusion Transformer for Anything-to-Audio Generation},
+  author={Tian, Zeyue and Jin, Yizhu and Liu, Zhaoyang and Yuan, Ruibin and Tan, Xu and Chen, Qifeng and Xue, Wei and Guo, Yike},
+  journal={arXiv preprint arXiv:2503.10522},
+  year={2025}
+}
+```