|
|
--- |
|
|
license: apache-2.0 |
|
|
--- |
|
|
|
|
|
> [!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) |
|
|
|
|
|
|
|
|
--- |
|
|
|
