Update README.md
Browse files
README.md
CHANGED
|
@@ -10,7 +10,7 @@ license_link: LICENSE
|
|
| 10 |
<h1 align="center">SkyReels V2: Infinite-Length Film Generative Model</h1>
|
| 11 |
|
| 12 |
<p align="center">
|
| 13 |
-
馃搼 <a href="https://arxiv.org/pdf/2504.13074">Technical Report</a> 路 馃憢 <a href="https://www.skyreels.ai/home?utm_campaign=
|
| 14 |
</p>
|
| 15 |
|
| 16 |
---
|
|
@@ -218,7 +218,7 @@ python3 generate_video.py \
|
|
| 218 |
--offload
|
| 219 |
```
|
| 220 |
> **Note**:
|
| 221 |
-
> - When using an **image-to-video (I2V)** model, you must provide an input image using the `--image ${image_path}` parameter.
|
| 222 |
|
| 223 |
|
| 224 |
- **Prompt Enhancer**
|
|
@@ -294,6 +294,9 @@ torchrun --nproc_per_node=2 generate_video.py \
|
|
| 294 |
--use_usp \
|
| 295 |
--seed 42
|
| 296 |
```
|
|
|
|
|
|
|
|
|
|
| 297 |
|
| 298 |
## Contents
|
| 299 |
- [Abstract](#abstract)
|
|
|
|
| 10 |
<h1 align="center">SkyReels V2: Infinite-Length Film Generative Model</h1>
|
| 11 |
|
| 12 |
<p align="center">
|
| 13 |
+
馃搼 <a href="https://arxiv.org/pdf/2504.13074">Technical Report</a> 路 馃憢 <a href="https://www.skyreels.ai/home?utm_campaign=huggingface_skyreels_v2" target="_blank">Playground</a> 路 馃挰 <a href="https://discord.gg/PwM6NYtccQ" target="_blank">Discord</a> 路 馃 <a href="https://huggingface.co/collections/Skywork/skyreels-v2-6801b1b93df627d441d0d0d9" target="_blank">Hugging Face</a> 路 馃 <a href="https://www.modelscope.cn/collections/SkyReels-V2-f665650130b144" target="_blank">ModelScope</a> 路 馃寪 <a href="https://github.com/SkyworkAI/SkyReels-V2" target="_blank">GitHub</a>
|
| 14 |
</p>
|
| 15 |
|
| 16 |
---
|
|
|
|
| 218 |
--offload
|
| 219 |
```
|
| 220 |
> **Note**:
|
| 221 |
+
> - When using an **image-to-video (I2V)** model, you must provide an input image using the `--image ${image_path}` parameter. The `--guidance_scale 5.0` and `--shift 3.0` is recommanded for I2V model.
|
| 222 |
|
| 223 |
|
| 224 |
- **Prompt Enhancer**
|
|
|
|
| 294 |
--use_usp \
|
| 295 |
--seed 42
|
| 296 |
```
|
| 297 |
+
> **Note**:
|
| 298 |
+
> - When using an **image-to-video (I2V)** model, you must provide an input image using the `--image ${image_path}` parameter. The `--guidance_scale 5.0` and `--shift 3.0` is recommanded for I2V model.
|
| 299 |
+
|
| 300 |
|
| 301 |
## Contents
|
| 302 |
- [Abstract](#abstract)
|