Made Carefully To be understood

Easily customizable to your taste.

The most Simple

Transforming your videos into new artistic styles is now more accessible and powerful than ever, thanks to the combination of ComfyUI's flexible interface and the advanced WAN 2.1 video models. This guide provides the steps to harness this potential for high-fidelity, temporally consistent video-to-video style transfer.

To get started, ensure you have the necessary models downloaded and placed in the correct ComfyUI directories:

WAN 2.1 Core Models (from Comfy-Org Repackaged):

• Diffusion Models: huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/tree/main/split_files/diffusion_models

  • (Place in: ComfyUI/models/diffusion_models/)

• CLIP Vision Model: huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/blob/main/split_files/clip_vision/clip_vision_h.safetensors

  • (Place in: ComfyUI/models/clip_vision/)

• Text Encoder Models: huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/tree/main/split_files/text_encoders

  • (Place in: ComfyUI/models/text_encoders/)

• VAE Model: huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/blob/main/split_files/vae/wan_2.1_vae.safetensors

  • (Place in: ComfyUI/models/vae/)

WAN 2.1 Fun (Control) Models (from Alibaba PAI):

• Wan2.1-Fun-1.3B-Control: huggingface.co/alibaba-pai/Wan2.1-Fun-1.3B-Control

• Wan2.1-Fun-14B-Control: huggingface.co/alibaba-pai/Wan2.1-Fun-14B-Control

  • (Place in: ComfyUI/models/controlnet/ or ComfyUI/models/diffusion_models/ depending on node usage)

Example Styling Resources:

• Ghibli Style LoRA: civitai.com/models/137562/studioghibliredmond-studio-ghibli-lora-for-sd-xl

  • (Place in: ComfyUI/models/loras/)

• DaVinci SDXL Model (Base/Reference): civitai.com/models/130664?modelVersionId=604405

  • (Place in: ComfyUI/models/checkpoints/)

With these resources and the workflow outlined above, you're ready to explore the creative possibilities of AI-driven video style transfer. Dive in, experiment, and bring your cinematic visions to life!