WAN 14B VACE FUSIONX [GGUF]

8 steps, 1.0 cfg, 81 frames.

https://github.com/MushroomFleet/DJZ-Workflows/tree/main/WAN-video/WAN-14B-FusionX-VACE

You Will Need:

Q8_0 18GB https://huggingface.co/QuantStack/Wan2.1_T2V_14B_FusionX_VACE-GGUF/resolve/main/Wan2.1_T2V_14B_FusionX_VACE-Q8_0.gguf
Q4_0 10GB https://huggingface.co/QuantStack/Wan2.1_T2V_14B_FusionX_VACE-GGUF/resolve/main/Wan2.1_T2V_14B_FusionX_VACE-Q4_0.gguf
place inside: /models/diffusion_models

use the CLIP and VAE for WAN 2.1 14b
Q8_0 6GB https://huggingface.co/city96/umt5-xxl-encoder-gguf/resolve/main/umt5-xxl-encoder-Q8_0.gguf
Q4_KM 3.6GB https://huggingface.co/city96/umt5-xxl-encoder-gguf/resolve/main/umt5-xxl-encoder-Q4_K_M.gguf

place inside: /models/text_encoders

VAE
https://huggingface.co/Wan-AI/Wan2.1-T2V-14B/resolve/main/Wan2.1_VAE.pth?download=true
place inside: /models/vae