<h3 id="wan2.2-speech-to-video">Wan2.2 Speech to Video</h3>Base model: /ComfyUI/models/diffusion_modelsAudio Encoder: ComfyUI/models/audio_encoders/Text encoder: save it in: ComfyUI/models/text_encoders/VAE: (same as Wan2.1) ComfyUI/models/vaeThis is a Q3_K_M GGUF quantized version is ideal for systems with limited VRAM (under 10GB vram) or for users prioritizing faster inference over maximum accuracy.

Wan2.2-S2V-14B GGUF  Q_3_K_M

save it in: ComfyUI/models/audio_encoders

Files with SHA256: f0017a43ea57ef6b3d4866be607844bbd8cada6d30966f7d70044ed0d63d3f9e