---
base_model:
- gdhe17/Self-Forcing
- Wan-AI/Wan2.1-VACE-1.3B
base_model_relation: merge
tags:
- text-to-video
- image-to-video
- video-to-video
- merge
language:
- en
license: cc-by-nc-sa-4.0
---

This is a merge of [gdhe17/Self-Forcing](https://huggingface.co/gdhe17/Self-Forcing) and [Wan-AI/Wan2.1-VACE-1.3B](https://huggingface.co/Wan-AI/Wan2.1-VACE-1.3B) scopes.

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

- FP16 model weight was 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).

## 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-1.3B-Self-Forcing-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](https://huggingface.co/docs/safetensors/index).