---
license: mit
library_name: diffusers
pipeline_tag: image-to-video
---

<p align="center">
  <img src="assets/logo.png"  height=100>
</p>
<div align="center">
  <a href="https://yuewen.cn/videos"><img src="https://img.shields.io/static/v1?label=Step-Video&message=Web&color=green"></a> &ensp;
  <a href="https://arxiv.org/abs/2502.10248"><img src="https://img.shields.io/static/v1?label=Tech Report&message=Arxiv&color=red"></a> &ensp;
  <a href="https://x.com/StepFun_ai"><img src="https://img.shields.io/static/v1?label=X.com&message=Web&color=blue"></a> &ensp;
</div>

<div align="center">
  <a href="https://huggingface.co/stepfun-ai/stepvideo-t2v"><img src="https://img.shields.io/static/v1?label=Step-Video-T2V&message=HuggingFace&color=yellow"></a> &ensp;
  <a href="https://huggingface.co/stepfun-ai/stepvideo-t2v-turbo"><img src="https://img.shields.io/static/v1?label=Step-Video-T2V-Turbo&message=HuggingFace&color=yellow"></a> &ensp;
  <a href="https://github.com/stepfun-ai/Step-Video-T2V"><img src="https://img.shields.io/static/v1?label=Code&message=Github&color=black"></a> &ensp;
</div>

## 🔥🔥🔥 News!!
* Mar 17, 2025: 👋 We release the inference code and model weights of Step-Video-Ti2V. [Download](https://huggingface.co/stepfun-ai/stepvideo-ti2v)
* Mar 17, 2025: 🎉 We have made our technical report available as open source. [Read](https://arxiv.org/abs/2502.10248)

## 🔧 4.2 Dependencies and Installation

```bash
git clone https://github.com/stepfun-ai/Step-Video-TI2V.git
conda create -n stepvideo python=3.10
conda activate stepvideo
cd StepFun-StepVideo
pip install -e .

```


##  🚀 Inference Scripts
- We employed a decoupling strategy for the text encoder, VAE decoding, and DiT to optimize GPU resource utilization by DiT. As a result, a dedicated GPU is needed to handle the API services for the text encoder's embeddings and VAE decoding.
```bash
python api/call_remote_server.py --model_dir where_you_download_dir &  ## We assume you have more than 4 GPUs available. This command will return the URL for both the caption API and the VAE API. Please use the returned URL in the following command.

parallel=4  # or parallel=8
url='127.0.0.1'
model_dir=where_you_download_dir

torchrun --nproc_per_node $parallel run_parallel.py \
    --model_dir $model_dir \
    --vae_url $url \
    --caption_url $url  \
    --ulysses_degree  $parallel \
    --prompt "男孩笑起来" \
    --first_image_path ./assets/demo.png \
    --infer_steps 50 \
    --save_path ./results \
    --cfg_scale 9.0 \
    --motion_score 5.0 \
    --time_shift 12.573
```

The following table shows the requirements for running Step-Video-T2V model (batch size = 1, w/o cfg distillation) to generate videos:

| GPU  | height/width/frame | Peak GPU Memory | 50 steps |
|------|--------------------|-----------------|----------|
| 1    | 768px × 768px × 102f | 76.42 GB        | 1061s    |
| 1    | 544px × 992px × 102f | 75.49 GB        | 929s     |
| 4    | 768px × 768px × 102f | 64.63 GB        | 288s     |
| 4    | 544px × 992px × 102f | 64.34 GB        | 251s     |