HaawkeNeural/framepack-i2v

FramePack - Image to Video Generation

This is a modified version of the FramePack model with a 5-second maximum video length limit.

Features

• —Generate realistic videos from still images
• —Simple and intuitive interface
• —Bilingual support (English/Chinese)
• —Maximum video length of 5 seconds to ensure quick generation times

Usage

1. 1.Upload an image
2. 2.Enter a prompt describing the desired motion
3. 3.Adjust parameters if needed (seed, video length, etc.)
4. 4.Click "Generate" and wait for the result

Technical Details

This application uses the HunyuanVideo transformer model for image-to-video generation. The model has been optimized to work efficiently with videos up to 5 seconds in length.

Credits

Based on the original FramePack model by lllyasviel.