Update README.md
Browse files
README.md
CHANGED
|
@@ -23,6 +23,17 @@ pipeline_tag: image-to-video
|
|
| 23 |
* Mar 17, 2025: 👋 We release the inference code and model weights of Step-Video-Ti2V. [Download](https://huggingface.co/stepfun-ai/stepvideo-ti2v)
|
| 24 |
* Mar 17, 2025: 🎉 We have made our technical report available as open source. [Read](https://arxiv.org/abs/2502.10248)
|
| 25 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
|
| 27 |
## 🚀 Inference Scripts
|
| 28 |
- 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.
|
|
|
|
| 23 |
* Mar 17, 2025: 👋 We release the inference code and model weights of Step-Video-Ti2V. [Download](https://huggingface.co/stepfun-ai/stepvideo-ti2v)
|
| 24 |
* Mar 17, 2025: 🎉 We have made our technical report available as open source. [Read](https://arxiv.org/abs/2502.10248)
|
| 25 |
|
| 26 |
+
## 🔧 4.2 Dependencies and Installation
|
| 27 |
+
|
| 28 |
+
```bash
|
| 29 |
+
git clone https://github.com/stepfun-ai/Step-Video-TI2V.git
|
| 30 |
+
conda create -n stepvideo python=3.10
|
| 31 |
+
conda activate stepvideo
|
| 32 |
+
cd StepFun-StepVideo
|
| 33 |
+
pip install -e .
|
| 34 |
+
|
| 35 |
+
```
|
| 36 |
+
|
| 37 |
|
| 38 |
## 🚀 Inference Scripts
|
| 39 |
- 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.
|