Wan2.1_T2V_14B_FusionX - An open-source text-to-video quantization model, usable in ComfyUI, offering more generation options

Wan2.1 T2V 14B FusionX GGUF

Developed by QuantStack

This is a quantized text-to-video model that converts the base model to the GGUF format and can be used in ComfyUI, providing more options for text-to-video generation.

Text-to-Video EnglishOpen Source License:Apache-2.0 #Text-to-video generation #GGUF quantization #ComfyUI compatibility

Downloads 563

Release Time : 6/7/2025

Model Overview

A GGUF quantized version based on the Wan14BT2VFusioniX_fp16_ model, supporting text-to-video generation tasks in the ComfyUI environment.

Model Features

GGUF quantization

Converts the original FP16 model to the GGUF format, optimizing the model size and running efficiency.

ComfyUI integration

Designed specifically for ComfyUI and can be easily integrated into the workflow through custom nodes.

Multi-component support

Supports cooperation with the text encoder (umt5-xxl) and variational autoencoder (Wan2_1_VAE_bf16).

Model Capabilities

Text-to-video generation

Support for quantized inference

Use Cases

Creative content generation

Short video generation

Automatically generate short video content based on text descriptions

Concept visualization

Convert abstract concepts or ideas into visual videos

🚀 Wan14BT2VFusioniX GGUF Quantized Model

This project offers a GGUF conversion of the Wan14BT2VFusioniX_fp16_.safetensors model. It enables text - to - video generation with quantized models, which can save storage and potentially speed up inference.

🚀 Quick Start

This is a GGUF conversion of Wan14BT2VFusioniX_fp16_.safetensors by @vrgamedevgirl84.

All quantized versions were created from the base T2V FP16 model using the conversion scripts provided by city96, available at the [ComfyUI - GGUF](https://github.com/city96/ComfyUI - GGUF/tree/main/tools) GitHub repository.

💻 Usage Examples

Basic Usage

The model files can be used in ComfyUI with the [ComfyUI - GGUF](https://github.com/city96/ComfyUI - GGUF) custom node. Place the required model(s) in the following folders:

Property	Details
Base Model	vrgamedevgirl84/Wan14BT2VFusioniX
Base Model Relation	quantized
Library Name	gguf
Quantized By	lym00
Tags	text - to - video, quantized
Language	en
License	apache - 2.0

Property	Details
Main Model	Wan2.1_T2V_14B_FusionX - GGUF, placed in `ComfyUI/models/unet`, download from GGUF (this repo)
Text Encoder	umt5 - xxl - encoder, placed in `ComfyUI/models/text_encoders`, download from [Safetensors](https://huggingface.co/Comfy - Org/Wan_2.1_ComfyUI_repackaged/tree/main/split_files/text_encoders) / [GGUF](https://huggingface.co/city96/umt5 - xxl - encoder - gguf/tree/main)
VAE	Wan2_1_VAE_bf16, placed in `ComfyUI/models/vae`, download from Safetensors

[ComfyUI example workflow](https://docs.comfy.org/tutorials/video/wan/wan - video#wan2 - 1 - text - to - video - workflow)

Advanced Usage

There is no specific advanced usage information provided in the original document.

📚 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).

📄 License

This project is licensed under the apache - 2.0 license.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご