Wan Video Fastest Native GGUF Workflow (I2V&T2V)

This workflow promises to be the fastest of any existing workflow.

Please update latest comfyui and nodes (nightly)

If you want to get good quality video, recommend using a model Q5 or higher.

If you want to use Q5 but lack VRAM, consider using MULTIGPU nodes.

Requirements

T2V Quant Model:

https://huggingface.co/city96/Wan2.1-T2V-14B-gguf/blob/main/wan2.1-t2v-14b-Q4_K_M.gguf

put models/diffusion_models

I2V Quant Model:

https://huggingface.co/city96/Wan2.1-I2V-14B-480P-gguf/blob/main/wan2.1-i2v-14b-480p-Q4_K_M.gguf

put models/diffusion_models

CLIP (DO NOT USE ANOTHER CLIP): https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/blob/main/split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors

put models/clip

CLIP-VISION: https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/blob/main/split_files/clip_vision/clip_vision_h.safetensors

put models/clip_vision

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

put models/vae

UPSCALE MODEL: 4x_foolhardy_Remacri or Download from ComfyUI Model Manager

put models/upscale_models

If need to other models (Non-GGUF version / verified)

I2V Model

https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/blob/main/split_files/diffusion_models/wan2.1_i2v_480p_14B_bf16.safetensors

T2V Model

https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/blob/main/split_files/diffusion_models/wan2.1_t2v_1.3B_bf16.safetensors

Custom Nodes List

• ComfyUI-GGUF

• ComfyUI-KJNodes

• ComfyUI-Impact-Pack

• ComfyUI-VideoHelperSuite

• ComfyUI-Frame-Interpolation

• ComfyUI-Custom-Scripts

• rgthree-comfy

This workflow has been built after extensive testing and validation.