---
title: Wan2.2_T2V_A14B_VACE-test
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/Wan2.2_T2V_A14B_VACE-test"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/Wan2.2_T2V_A14B_VACE-test.md"
repository: AI-ModelScope/Wan2.2_T2V_A14B_VACE-test
last_updated: 2025-07-29
license: apache-2.0
parameters: 34.7B
tensor_type:
  - F16
  - BF16
library_name:
  - gguf
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 3074
stars: 5
tags:
  - gguf
---

# Wan2.2_T2V_A14B_VACE-test

> Wan2.2_T2V_A14B_VACE-test - AI-ModelScope 在 ModelScope 开源的模型。[!IMPORTANT] ⚠️ Notice This project is intended for experimental use only.

AI-ModelScope/Wan2.2_T2V_A14B_VACE-test 是 ModelScope 魔搭社区上的 34.7B 参数机器学习模型，采用 apache-2.0 许可。

- **Repository**: AI-ModelScope/Wan2.2_T2V_A14B_VACE-test
- **License**: apache-2.0
- **Parameters**: 34.7B
- **Tags**: gguf
- **Downloads**: 3074
- **Stars**: 5
- **Last updated**: 2025-07-29

Source: https://www.modelscope.cn/models/AI-ModelScope/Wan2.2_T2V_A14B_VACE-test

---

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

This is an addon experiment of **[Wan2.2 T2V A14B](https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B)** and VACE scopes from **[Wan2.1 VACE T2V 14B](https://huggingface.co/Wan-AI/Wan2.1-VACE-14B)**. 

The process involved injecting [VACE scopes](https://huggingface.co/Wan-AI/Wan2.1-VACE-14B/blob/main/diffusion_pytorch_model-00007-of-00007.safetensors) into the target models, using scripts provided by [wsbagnsv1](https://huggingface.co/wsbagnsv1). 

All [GGUF quantized](https://huggingface.co/docs/hub/en/gguf#quantization-types) versions were created from the 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. 

## Notes

Tested with **2-step High Noise** and **2-step Low Noise** dual sampling with the [LightX2V LoRA](https://huggingface.co/Kijai/WanVideo_comfy/tree/main/Lightx2v), it's working fine in [ComfyUI](https://docs.comfy.org/). 

There's news where VACE team might have a **fix for the [color shifting](https://github.com/ali-vilab/VACE/issues/44) issue** to be released (discussions on the [Banodoco Discord Server](https://discord.com/channels/1076117621407223829/1342763350815277067/1399409879017459903)).  

Will be waiting for the official fix before testing further. 

---

## References

🔗 [Wan2.2 MoE](https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B#1-mixture-of-experts-moe-architecture)

>- **Wan2.2** separates expert models by timestep:
>  The **High-Noise expert** focuses on generating overall layout and motion.
>  The **Low-Noise expert** refines textures and details.
>- The **A14B model** includes both High-Noise and Low-Noise experts, which are activated at different denoising stages.

🔗 [ComfyUI Wan2.2 14B T2V Workflow Examples](https://docs.comfy.org/tutorials/video/wan/wan2_2#wan2-2-14b-t2v-text-to-video-workflow-example)

🔗 [ComfyUI Wan2.1 VACE Workflow Examples](https://docs.comfy.org/tutorials/video/wan/vace)


---