README.md

---
library_name: diffusers
pipeline_tag: image-to-image
---

# Stream-DiffVSR: Low-Latency Streamable Video Super-Resolution via Auto-Regressive Diffusion

Stream-DiffVSR is a causally conditioned diffusion framework designed for efficient online Video Super-Resolution (VSR). It operates strictly on past frames to maintain low latency, making it suitable for real-time deployment.

[[Paper](https://huggingface.co/papers/2512.23709)] [[Project Page](https://jamichss.github.io/stream-diffvsr-project-page/)] [[GitHub](https://github.com/jamichss/Stream-DiffVSR)]

## Description
Diffusion-based VSR methods often struggle with latency due to multi-step denoising and reliance on future frames. Stream-DiffVSR addresses this with:
- **Causal Conditioning:** Operates only on past frames for online processing.
- **Four-step Distilled Denoiser:** Enables fast inference without sacrificing quality.
- **Auto-regressive Temporal Guidance (ARTG):** Injects motion-aligned cues during denoising.
- **Lightweight Temporal Decoder:** Enhances temporal coherence and fine details.

Stream-DiffVSR can process 720p frames in 0.328 seconds on an RTX 4090, achieving significant latency reductions compared to prior diffusion-based VSR methods.

## Usage

### Installation
```bash
git clone https://github.com/jamichss/Stream-DiffVSR.git
cd Stream-DiffVSR
conda env create -f requirements.yml
conda activate stream-diffvsr
```

### Inference
You can run inference using the following command. The script will automatically fetch the necessary weights from this repository.

```bash
python inference.py \
    --model_id 'Jamichsu/Stream-DiffVSR' \
    --out_path 'YOUR_OUTPUT_PATH' \
    --in_path 'YOUR_INPUT_PATH' \
    --num_inference_steps 4
```

The expected file structure for the inference input data is as follows:
```
YOUR_INPUT_PATH/
├── seq1/
│   ├── frame_0001.png
│   ├── frame_0002.png
│   └── ...
├── seq2/
│   ├── frame_0001.png
│   ├── frame_0002.png
│   └── ...
```

For NVIDIA TensorRT acceleration:
```bash
python inference.py \
    --model_id 'Jamichsu/Stream-DiffVSR' \
    --out_path 'YOUR_OUTPUT_PATH' \
    --in_path 'YOUR_INPUT_PATH' \
    --num_inference_steps 4 \
    --enable_tensorrt \
    --image_height <YOUR_TARGET_HEIGHT> \
    --image_width <YOUR_TARGET_WIDTH>
```

## Note

The provided checkpoint is a **toy / proof-of-concept model** trained on a limited amount of data. As a result, it does not yet cover the full diversity of real-world videos.

This checkpoint is mainly intended to demonstrate the **overall pipeline and low-latency feasibility**, rather than to deliver production-level upscaling quality.

Artifacts and inconsistent visual quality are therefore expected at this stage.


## Citation
If you find this work useful, please cite:
```bibtex
@article{shiu2025stream,
  title={Stream-DiffVSR: Low-Latency Streamable Video Super-Resolution via Auto-Regressive Diffusion},
  author={Shiu, Hau-Shiang and Lin, Chin-Yang and Wang, Zhixiang and Hsiao, Chi-Wei and Yu, Po-Fan and Chen, Yu-Chih and Liu, Yu-Lun},
  journal={arXiv preprint arXiv:2512.23709},
  year={2025}
}
```