Buckets:

---

fzhio

/

WanVideo_comfy-bucket

🚀 WanVideo Model Suite

Combined & Quantized Models for ComfyUI Workflows
Derived from Wan-AI/Wan2.1-VACE-14B

---

📋 Overview

This repository provides optimized models for WanVideo—a high-fidelity video generation framework. Models are quantized to balance performance and resource efficiency while retaining visual quality. Designed for seamless integration with ComfyUI via:

• WanVideo Wrapper (Third-party extension)
• Native WanVideo nodes in ComfyUI

---

🔧 Key Components

1. Core Diffusion Models

2. Text & Vision Encoders

---

📁 ComfyUI Setup Guide

Place files in these directories within your ComfyUI installation:

models/  
├── diffusion_models/  
│   ├── wan2.1_i2v_720p_14B_fp8_e4m3fn.safetensors  
│   └── fantasytalking_fp16.safetensors  
├── clip_vision/  
│   └── clip_vision_h.safetensors  
└── text_encoders/  
    └── umt5-xxl-enc-bf16.safetensors  

---

🔗 Dependencies & Resources

1. Vision Encoder Resources

   • Download clip_vision_h.safetensors from:
     Comfy-Org/Wan_2.1_ComfyUI_repackaged

2. FantasyTalking Model

   • Source code & usage: GitHub Repository

3. Base Model

   • Full precision version: Wan-AI/Wan2.1-VACE-14B

---

💡 Usage Notes

• Quantization Benefits: FP8 reduces VRAM usage by ~50% vs FP16, enabling 720p generation on consumer GPUs.
• Workflow Compatibility: Combine with Text-to-Video, Image-to-Video, or FantasyTalking nodes in ComfyUI.
• Multi-Modal Inputs: UMT5-XXL encoder supports multilingual prompts (e.g., English, Chinese).

---

⚖️ License

Inherited from parent models (Check Wan-AI License). Non-commercial/research use recommended pending verification.

---

✨ Pro Tip: For optimal results, pair with WanVideo’s temporal consistency modules to reduce frame flickering in long sequences.

---

Model Card curated by the ComfyUI community. Maintained for reproducibility and ease of deployment.