---
title: Wan2.1_T2V_14B_LightX2V_StepCfgDistill_VACE
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/Wan2.1_T2V_14B_LightX2V_StepCfgDistill_VACE"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/Wan2.1_T2V_14B_LightX2V_StepCfgDistill_VACE.md"
repository: AI-ModelScope/Wan2.1_T2V_14B_LightX2V_StepCfgDistill_VACE
last_updated: 2025-07-11
license: apache-2.0
parameters: 52.0B
tensor_type:
  - BF16
  - F8_E5M2
  - F8_E4M3
  - F16
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 425
stars: 0
---

# Wan2.1_T2V_14B_LightX2V_StepCfgDistill_VACE

> Wan2.1_T2V_14B_LightX2V_StepCfgDistill_VACE - AI-ModelScope 在 ModelScope 开源的模型。lightx2v/Wan2.1-T2V-14B-StepDistill-CfgDistill & Wan-AI/Wan2.1-VACE-14B Scopes Addon Experiment

AI-ModelScope/Wan2.1_T2V_14B_LightX2V_StepCfgDistill_VACE 是 ModelScope 魔搭社区上的 52.0B 参数机器学习模型，采用 apache-2.0 许可。

- **Repository**: AI-ModelScope/Wan2.1_T2V_14B_LightX2V_StepCfgDistill_VACE
- **License**: apache-2.0
- **Parameters**: 52.0B
- **Downloads**: 425
- **Stars**: 0
- **Last updated**: 2025-07-11

Source: https://www.modelscope.cn/models/AI-ModelScope/Wan2.1_T2V_14B_LightX2V_StepCfgDistill_VACE

---

# lightx2v/Wan2.1-T2V-14B-StepDistill-CfgDistill & Wan-AI/Wan2.1-VACE-14B Scopes Addon Experiment

--- 

> [!IMPORTANT]
> ⚠️ **Notice:**  
> This project is intended for experimental use only. 
>

---

This is an addon experiment of [lightx2v/Wan2.1-T2V-14B-StepDistill-CfgDistill](https://huggingface.co/lightx2v/Wan2.1-T2V-14B-StepDistill-CfgDistill) and [Wan-AI/Wan2.1-VACE-14B](https://huggingface.co/Wan-AI/Wan2.1-VACE-14B) scopes. 

The process involved extracting VACE scopes and injecting into the target models, using scripts provided by [wsbagnsv1](https://huggingface.co/wsbagnsv1). 

The FP16 model weights were then quantized 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). 

For GGUF quants, please visit [QuantStack/Wan2.1_T2V_14B_LightX2V_StepCfgDistill_VACE-GGUF](https://huggingface.co/QuantStack/Wan2.1_T2V_14B_LightX2V_StepCfgDistill_VACE-GGUF). 

## 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_LightX2V_StepCfgDistill_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 an overview of Safetensors format, please see the [Safetensors format](https://huggingface.co/docs/safetensors/index#format).