---
title: cogvideox-2b-img2vid
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/cogvideox-2b-img2vid"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/cogvideox-2b-img2vid.md"
repository: AI-ModelScope/cogvideox-2b-img2vid
last_updated: 2024-11-01
license: apache-2.0
pipeline_tag: image-to-video
tasks:
  - image-to-video
parameters: 6.7B
tensor_type:
  - F16
library_name:
  - diffusers
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 2032
stars: 1
tags:
  - cogvideox
  - video-generation
  - image-to-video
  - diffusers
---

# cogvideox-2b-img2vid

> cogvideox-2b-img2vid - AI-ModelScope 在 ModelScope 开源的模型。🎥 CogVideoX-2B-Img2Vid 🚀

AI-ModelScope/cogvideox-2b-img2vid 是 ModelScope 魔搭社区上的 6.7B 参数image-to-video模型，采用 apache-2.0 许可。

- **Repository**: AI-ModelScope/cogvideox-2b-img2vid
- **License**: apache-2.0
- **Tasks**: image-to-video
- **Parameters**: 6.7B
- **Tags**: cogvideox, video-generation, image-to-video, diffusers
- **Downloads**: 2032
- **Stars**: 1
- **Last updated**: 2024-11-01

Source: https://www.modelscope.cn/models/AI-ModelScope/cogvideox-2b-img2vid

---

# 🎥 CogVideoX-2B-Img2Vid 🚀

### Fine-tuned on 10 million videos for high-quality generation at SBS levels comparable to CogVideoX-5B! 🌟


# Model Highlights 🌟

- Fine-tuned on 10 million videos for exceptional image-to-video generation quality.

- Performance benchmarked to match SBS standards at CogVideoX-5B i2v level.


## Usage Examples 🔥

### Try it for free on [nim.video](https://nim.video)

<video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/63fde49f6315a264aba6a7ed/8vOYgS-Wm51BgOKv4Jnpp.mp4"></video>

### CLI Inference 🌐
```bash
python -m inference.cli_demo \
    --video_path "resources/truck.jpg" \
    --prompt "A truck is driving through a dirt road, showcasing its capability for off-roading." \
    --model_path NimVideo/cogvideox-2b-img2vid

```
## Gradio Inference with Web Demo 🖥️
```bash
python -m inference.gradio_web_demo \
    --model_path NimVideo/cogvideox-2b-img2vid
```
### ComfyUI Example 💡

<p align="center">
    <img src="cogvideox-2b-img2vid-workflow.png" width="800" height="400" alt="Workflow Preview" title="Workflow Example Preview"/>
</p>
<p align="center">
    <a href="cogvideox-2b-img2vid-workflow.json">🔗 JSON Workflow Example</a>
</p>


### 🔧 [Find the custom ComfyUI node here.](https://github.com/Nim-Video/ComfyUI-CogVideoXWrapper)

## Quick Start 🚀

1️⃣ Clone the Repository
```bash
git clone https://github.com/Nim-Video/cogvideox-2b-img2vid.git
cd cogvideox-2b-img2vid
```
2️⃣ Set up a Virtual Environment
```bash
python -m venv venv
source venv/bin/activate
```
3️⃣ Install Requirements
```bash
pip install -r requirements.txt
```

## Acknowledgements 🙏

This project builds on the foundational work of [CogVideoX](https://github.com/THUDM/CogVideo/tree/main).