Wan2.1 T2V 14B LightX2V StepCfgDistill VACE GGUF

🚀 GGUF Conversion for Text-to-Video Model

This project offers a GGUF conversion of an addon that combines scopes from lightx2v/Wan2.1-T2V-14B-StepDistill-CfgDistill and Wan-AI/Wan2.1-VACE-14B. It enables text - to - video, image - to - video, and video - to - video tasks with quantized models.

✨ Features

• Scope Integration: Extracts VACE scopes and injects them into the target models using scripts from wsbagnsv1.
• Quantization: All quantized versions are created from the FP16 model using conversion scripts by city96, available at ComfyUI - GGUF.

📦 Installation

The model files can be used in ComfyUI with the ComfyUI - GGUF custom node. Place the required model(s) in the following folders:

💻 Usage Examples

You can refer to the ComfyUI example workflow for practical usage.

📚 Documentation

Notes

⚠️ Important Note

All original licenses and restrictions from the base models still apply.

Reference

For an overview of quantization types, please see the [GGUF quantization types](https://huggingface.co/docs/hub/gguf#quantization - types).