---
title: Wan2.1-14B-T2V-FusionX-VACE
canonical_url: "https://www.modelscope.cn/models/QuantStack/Wan2.1-14B-T2V-FusionX-VACE"
md_url: "https://www.modelscope.cn/models/QuantStack/Wan2.1-14B-T2V-FusionX-VACE.md"
repository: QuantStack/Wan2.1-14B-T2V-FusionX-VACE
last_updated: 2025-06-12
license: apache-2.0
pipeline_tag: image-to-video
tasks:
  - image-to-video
base_model:
  - Wan-AI/Wan2.1-VACE-14B
  - vrgamedevgirl84/Wan14BT2VFusioniX
base_model_relation: merge
parameters: 69.4B
tensor_type:
  - F8_E4M3
  - F32
  - BF16
  - F16
  - F8_E5M2
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 2274
stars: 10
tags:
  - text-to-video
  - image-to-video
  - video-to-video
  - merge
---

# Wan2.1-14B-T2V-FusionX-VACE

> Wan2.1-14B-T2V-FusionX-VACE - QuantStack 在 ModelScope 开源的模型。This is a merge of Wan-AI/Wan2.1-VACE-14B scopes and vrgamedevgirl84/Wan14BT2VFusionX.

QuantStack/Wan2.1-14B-T2V-FusionX-VACE 是 ModelScope 魔搭社区上的 69.4B 参数image-to-video模型，采用 apache-2.0 许可，基于 Wan-AI/Wan2.1-VACE-14B、vrgamedevgirl84/Wan14BT2VFusioniX 构建。

- **Repository**: QuantStack/Wan2.1-14B-T2V-FusionX-VACE
- **License**: apache-2.0
- **Tasks**: image-to-video
- **Parameters**: 69.4B
- **Base model**: Wan-AI/Wan2.1-VACE-14B, vrgamedevgirl84/Wan14BT2VFusioniX
- **Tags**: text-to-video, image-to-video, video-to-video, merge
- **Downloads**: 2274
- **Stars**: 10
- **Last updated**: 2025-06-12

Source: https://www.modelscope.cn/models/QuantStack/Wan2.1-14B-T2V-FusionX-VACE

---

This is a merge of [Wan-AI/Wan2.1-VACE-14B](https://huggingface.co/Wan-AI/Wan2.1-VACE-14B) scopes and [vrgamedevgirl84/Wan14BT2VFusionX](https://huggingface.co/vrgamedevgirl84/Wan14BT2VFusioniX). 

The process involved extracting VACE scopes and injecting into the target models. 

- FP8 model weight was then converted to specific FP8 formats (E4M3FN and E5M2) using ComfyUI custom node [ComfyUI-ModelQuantizer](https://github.com/lum3on/ComfyUI-ModelQuantizer) by [lum3on](https://github.com/lum3on). 

## Usage

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

| Type         | Name                          | Location                          | Download                |
| ------------ | ----------------------------- | --------------------------------- | ----------------------- |
| Main Model   | Wan2.1_T2V_14B_FusionX_VACE   | `ComfyUI/models/diffusion_models` | Safetensors (this repo) |
| Text Encoder | umt5-xxl-encoder              | `ComfyUI/models/text_encoders`    | [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               | `ComfyUI/models/vae`              | [Safetensors](https://huggingface.co/Kijai/WanVideo_comfy/blob/main/Wan2_1_VAE_bf16.safetensors) |

[**ComfyUI example workflow**](https://docs.comfy.org/tutorials/video/wan/vace)

### Notes

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

 ## Reference

- For more information about the GGUF-quantized versions, refer to [QuantStack/Wan2.1_T2V_14B_FusionX_VACE-GGUF](https://huggingface.co/QuantStack/Wan2.1_T2V_14B_FusionX_VACE-GGUF).
- For an overview of Safetensors format, please see the [Safetensors](https://huggingface.co/docs/safetensors/index).