base_model, base_model_relation, tags, language, license

base_model	base_model_relation	tags	language	license
Wan-AI/Wan2.1-VACE-14B vrgamedevgirl84/Wan14BT2VFusioniX	merge	text-to-video image-to-video video-to-video merge	en	apache-2.0

This is a merge of Wan-AI/Wan2.1-VACE-14B and vrgamedevgirl84/Wan14BT2VFusionX to provide additional VACE compatibility.

The process involved extracting VACE scopes and injecting into the target models. Model weights were directly converted to specific FP8 formats (E4M3FN and E5M2) using a custom ComfyUI node developed by lum3on, available at the ComfyUI-ModelQuantizer GitHub repository.

Usage

The model files can be used in ComfyUI with the WanVaceToVideo node. Place the required model(s) in the following folders:

Type	Name	Location	Download
Main Model	Wan-14B-T2V-FusionX-VACE	ComfyUI/models/diffusion_models	Safetensors (this repo)
Text Encoder	umt5-xxl-encoder	ComfyUI/models/text_encoders	Safetensors / GGUF
VAE	Wan2_1_VAE_bf16	ComfyUI/models/vae	Safetensors

ComfyUI example workflow

Notes

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

Reference

• For more information about the GGUF-quantized versions, refer to QuantStack/Wan-14B-T2V-FusionX-VACE-GGUF, where the quantization process is explained.
• For an overview of Safetensors format, please see the Safetensors.