Edit model card

πŸŽ₯ CogVideoX-2B-Img2Vid πŸš€

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 πŸ”₯

Try it for free on nim.video

CLI Inference 🌐

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 πŸ–₯️

python -m inference.gradio_web_demo \
    --model_path NimVideo/cogvideox-2b-img2vid

ComfyUI Example πŸ’‘

Workflow Preview

πŸ”— JSON Workflow Example

πŸ”§ Find the custom ComfyUI node here.

Quick Start πŸš€

1️⃣ Clone the Repository

git clone https://github.com/Nim-Video/cogvideox-2b-img2vid.git
cd cogvideox-2b-img2vid

2️⃣ Set up a Virtual Environment

python -m venv venv
source venv/bin/activate

3️⃣ Install Requirements

pip install -r requirements.txt

Acknowledgements πŸ™

This project builds on the foundational work of CogVideoX.

Downloads last month
498
Inference API
Inference API (serverless) does not yet support diffusers models for this pipeline type.