---
title: ExVideo-CogVideoX-LoRA-129f-v1
canonical_url: "https://www.modelscope.cn/models/ECNU-CILab/ExVideo-CogVideoX-LoRA-129f-v1"
md_url: "https://www.modelscope.cn/models/ECNU-CILab/ExVideo-CogVideoX-LoRA-129f-v1.md"
repository: ECNU-CILab/ExVideo-CogVideoX-LoRA-129f-v1
chinese_name: "ExVideo 129 帧视频生成模型（基于 CogVideoX 扩展）"
last_updated: 2024-10-10
license: "Apache License 2.0"
pipeline_tag: text-to-video-synthesis
tasks:
- text-to-video-synthesis
parameters: 250.5M
tensor_type:
- F32
library_name:
- pytorch
- safetensors
frameworks:
- Pytorch
downloads: 305
stars: 3
---
# ExVideo-CogVideoX-LoRA-129f-v1
> ExVideo-CogVideoX-LoRA-129f-v1 - ECNU-CILab 在 ModelScope 开源的模型。ExVideo 是一项视频生成模型的后训练技术，旨在通过后训练增强模型的生成能力。我们在 CogVideoX-5B 的基础上进行了扩展，使其能够生成 129 帧长视频。
ECNU-CILab/ExVideo-CogVideoX-LoRA-129f-v1 是 ModelScope 魔搭社区上的 250.5M 参数text-to-video-synthesis模型，采用 Apache License 2.0 许可。
- **Repository**: ECNU-CILab/ExVideo-CogVideoX-LoRA-129f-v1
- **License**: Apache License 2.0
- **Tasks**: text-to-video-synthesis
- **Parameters**: 250.5M
- **Downloads**: 305
- **Stars**: 3
- **Last updated**: 2024-10-10
Source: https://www.modelscope.cn/models/ECNU-CILab/ExVideo-CogVideoX-LoRA-129f-v1
---
# ExVideo
ExVideo 是一项视频生成模型的后训练技术，旨在通过后训练增强模型的生成能力。我们在 CogVideoX-5B 的基础上进行了扩展，使其能够生成 129 帧长视频。
这是我们公开的第二个模型，这个模型以 LoRA 的形式添加到 CogVideoX-5B 的模型结构上。
* [项目页面](https://ecnu-cilab.github.io/ExVideoProjectPage/)
* [开源代码](https://github.com/modelscope/DiffSynth-Studio)
* [技术报告](https://arxiv.org/abs/2406.14130)
## 使用方式
```python
from diffsynth import ModelManager, CogVideoPipeline, save_video, download_models
import torch
download_models(["CogVideoX-5B", "ExVideo-CogVideoX-LoRA-129f-v1"])
model_manager = ModelManager(torch_dtype=torch.bfloat16)
model_manager.load_models([
"models/CogVideo/CogVideoX-5b/text_encoder",
"models/CogVideo/CogVideoX-5b/transformer",
"models/CogVideo/CogVideoX-5b/vae/diffusion_pytorch_model.safetensors",
])
model_manager.load_lora("models/lora/ExVideo-CogVideoX-LoRA-129f-v1.safetensors")
pipe = CogVideoPipeline.from_model_manager(model_manager)
torch.manual_seed(6)
video = pipe(
prompt="an astronaut riding a horse on Mars.",
height=480, width=720, num_frames=129,
cfg_scale=7.0, num_inference_steps=100,
)
save_video(video, "video_with_lora.mp4", fps=8, quality=5)
```
请参考 [DiffSynth](https://github.com/modelscope/DiffSynth-Studio) 获取更多信息。
## 样例展示
提示词：an astronaut riding a horse on Mars.
提示词：Static camera, two men shake hands happily, the background is in a modern office.
提示词：The camera captures the northern lights dancing across an Arctic sky, with stars twinkling above a snow-covered landscape, creating a serene and magical atmosphere.
提示词：FPV aerial shot, the sunshine shines on the snow capped mountains, a quiet atmosphere.
提示词：A Chinese mother, draped in a soft, pastel-colored robe, gently rocks back and forth in a cozy rocking chair positioned in the tranquil setting of a nursery. The dimly lit bedroom is adorned with whimsical mobiles dangling from the ceiling, casting shadows that dance on the walls. Her baby, swaddled in a delicate, patterned blanket, rests against her chest, the child's earlier cries now replaced by contented coos as the mother's soothing voice lulls the little one to sleep. The scent of lavender fills the air, adding to the serene atmosphere, while a warm, orange glow from a nearby nightlight illuminates the scene with a gentle hue, capturing a moment of tender love and comfort.
对比不加 ExVideo 扩展模块的模型，原模型在生成长视频时出现了明显的细节缺失，ExVideo 扩展模块非常显著地提升了画面的细节。